| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0-only /* * 32-bit compatibility support for ELF format executables and core dumps. * * Copyright (C) 2007 Red Hat, Inc. All rights reserved. * * Red Hat Author: Roland McGrath. * * This file is used in a 64-bit kernel that wants to support 32-bit ELF. * asm/elf.h is responsible for defining the compat_* and COMPAT_* macros * used below, with definitions appropriate for 32-bit ABI compatibility. * * We use macros to rename the ABI types and machine-dependent * functions used in binfmt_elf.c to compat versions. */ #include <linux/elfcore-compat.h> #include <linux/time.h> #define ELF_COMPAT 1 /* * Rename the basic ELF layout types to refer to the 32-bit class of files. */ #undef ELF_CLASS #define ELF_CLASS ELFCLASS32 #undef elfhdr #undef elf_phdr #undef elf_shdr #undef elf_note #undef elf_addr_t #undef ELF_GNU_PROPERTY_ALIGN #define elfhdr elf32_hdr #define elf_phdr elf32_phdr #define elf_shdr elf32_shdr #define elf_note elf32_note #define elf_addr_t Elf32_Addr #define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN /* * Some data types as stored in coredump. */ #define user_long_t compat_long_t #define user_siginfo_t compat_siginfo_t #define copy_siginfo_to_external copy_siginfo_to_external32 /* * The machine-dependent core note format types are defined in elfcore-compat.h, * which requires asm/elf.h to define compat_elf_gregset_t et al. */ #define elf_prstatus compat_elf_prstatus #define elf_prstatus_common compat_elf_prstatus_common #define elf_prpsinfo compat_elf_prpsinfo #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 /* * To use this file, asm/elf.h must define compat_elf_check_arch. * The other following macros can be defined if the compat versions * differ from the native ones, or omitted when they match. */ #undef elf_check_arch #define elf_check_arch compat_elf_check_arch #ifdef COMPAT_ELF_PLATFORM #undef ELF_PLATFORM #define ELF_PLATFORM COMPAT_ELF_PLATFORM #endif #ifdef COMPAT_ELF_HWCAP #undef ELF_HWCAP #define ELF_HWCAP COMPAT_ELF_HWCAP #endif #ifdef COMPAT_ELF_HWCAP2 #undef ELF_HWCAP2 #define ELF_HWCAP2 COMPAT_ELF_HWCAP2 #endif #ifdef COMPAT_ELF_HWCAP3 #undef ELF_HWCAP3 #define ELF_HWCAP3 COMPAT_ELF_HWCAP3 #endif #ifdef COMPAT_ELF_HWCAP4 #undef ELF_HWCAP4 #define ELF_HWCAP4 COMPAT_ELF_HWCAP4 #endif #ifdef COMPAT_ARCH_DLINFO #undef ARCH_DLINFO #define ARCH_DLINFO COMPAT_ARCH_DLINFO #endif #ifdef COMPAT_ELF_ET_DYN_BASE #undef ELF_ET_DYN_BASE #define ELF_ET_DYN_BASE COMPAT_ELF_ET_DYN_BASE #endif #ifdef COMPAT_ELF_PLAT_INIT #undef ELF_PLAT_INIT #define ELF_PLAT_INIT COMPAT_ELF_PLAT_INIT #endif #ifdef COMPAT_SET_PERSONALITY #undef SET_PERSONALITY #define SET_PERSONALITY COMPAT_SET_PERSONALITY #endif #ifdef compat_start_thread #define COMPAT_START_THREAD(ex, regs, new_ip, new_sp) \ compat_start_thread(regs, new_ip, new_sp) #endif #ifdef COMPAT_START_THREAD #undef START_THREAD #define START_THREAD COMPAT_START_THREAD #endif #ifdef compat_arch_setup_additional_pages #define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \ compat_arch_setup_additional_pages(bprm, interpreter) #endif #ifdef COMPAT_ARCH_SETUP_ADDITIONAL_PAGES #undef ARCH_HAS_SETUP_ADDITIONAL_PAGES #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 #undef ARCH_SETUP_ADDITIONAL_PAGES #define ARCH_SETUP_ADDITIONAL_PAGES COMPAT_ARCH_SETUP_ADDITIONAL_PAGES #endif #ifdef compat_elf_read_implies_exec #undef elf_read_implies_exec #define elf_read_implies_exec compat_elf_read_implies_exec #endif /* * Rename a few of the symbols that binfmt_elf.c will define. * These are all local so the names don't really matter, but it * might make some debugging less confusing not to duplicate them. */ #define elf_format compat_elf_format #define init_elf_binfmt init_compat_elf_binfmt #define exit_elf_binfmt exit_compat_elf_binfmt #define binfmt_elf_test_cases compat_binfmt_elf_test_cases #define binfmt_elf_test_suite compat_binfmt_elf_test_suite /* * We share all the actual code with the native (64-bit) version. */ #include "binfmt_elf.c" |
| 33 33 33 33 33 33 198 198 197 70 70 70 33 33 33 181 191 181 38 206 1 1 1 1 14 177 14 164 165 73 17 17 17 83 136 83 73 73 309 209 165 165 287 287 1 109 220 105 286 166 166 3 27 34 138 40 166 73 73 3 17 47 42 73 87 87 6 17 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/switchdev/switchdev.c - Switch device API * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us> * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com> */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <linux/list.h> #include <linux/workqueue.h> #include <linux/if_vlan.h> #include <linux/rtnetlink.h> #include <net/switchdev.h> static bool switchdev_obj_eq(const struct switchdev_obj *a, const struct switchdev_obj *b) { const struct switchdev_obj_port_vlan *va, *vb; const struct switchdev_obj_port_mdb *ma, *mb; if (a->id != b->id || a->orig_dev != b->orig_dev) return false; switch (a->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: va = SWITCHDEV_OBJ_PORT_VLAN(a); vb = SWITCHDEV_OBJ_PORT_VLAN(b); return va->flags == vb->flags && va->vid == vb->vid && va->changed == vb->changed; case SWITCHDEV_OBJ_ID_PORT_MDB: case SWITCHDEV_OBJ_ID_HOST_MDB: ma = SWITCHDEV_OBJ_PORT_MDB(a); mb = SWITCHDEV_OBJ_PORT_MDB(b); return ma->vid == mb->vid && ether_addr_equal(ma->addr, mb->addr); default: break; } BUG(); } static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); typedef void switchdev_deferred_func_t(struct net_device *dev, const void *data); struct switchdev_deferred_item { struct list_head list; struct net_device *dev; netdevice_tracker dev_tracker; switchdev_deferred_func_t *func; unsigned long data[]; }; static struct switchdev_deferred_item *switchdev_deferred_dequeue(void) { struct switchdev_deferred_item *dfitem; spin_lock_bh(&deferred_lock); if (list_empty(&deferred)) { dfitem = NULL; goto unlock; } dfitem = list_first_entry(&deferred, struct switchdev_deferred_item, list); list_del(&dfitem->list); unlock: spin_unlock_bh(&deferred_lock); return dfitem; } /** * switchdev_deferred_process - Process ops in deferred queue * * Called to flush the ops currently queued in deferred ops queue. * rtnl_lock must be held. */ void switchdev_deferred_process(void) { struct switchdev_deferred_item *dfitem; ASSERT_RTNL(); while ((dfitem = switchdev_deferred_dequeue())) { dfitem->func(dfitem->dev, dfitem->data); netdev_put(dfitem->dev, &dfitem->dev_tracker); kfree(dfitem); } } EXPORT_SYMBOL_GPL(switchdev_deferred_process); static void switchdev_deferred_process_work(struct work_struct *work) { rtnl_lock(); switchdev_deferred_process(); rtnl_unlock(); } static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work); static int switchdev_deferred_enqueue(struct net_device *dev, const void *data, size_t data_len, switchdev_deferred_func_t *func) { struct switchdev_deferred_item *dfitem; dfitem = kmalloc_flex(*dfitem, data, data_len, GFP_ATOMIC); if (!dfitem) return -ENOMEM; dfitem->dev = dev; dfitem->func = func; memcpy(dfitem->data, data, data_len); netdev_hold(dev, &dfitem->dev_tracker, GFP_ATOMIC); spin_lock_bh(&deferred_lock); list_add_tail(&dfitem->list, &deferred); spin_unlock_bh(&deferred_lock); schedule_work(&deferred_process_work); return 0; } static int switchdev_port_attr_notify(enum switchdev_notifier_type nt, struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { int err; int rc; struct switchdev_notifier_port_attr_info attr_info = { .attr = attr, .handled = false, }; rc = call_switchdev_blocking_notifiers(nt, dev, &attr_info.info, extack); err = notifier_to_errno(rc); if (err) { WARN_ON(!attr_info.handled); return err; } if (!attr_info.handled) return -EOPNOTSUPP; return 0; } static int switchdev_port_attr_set_now(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { return switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr, extack); } static void switchdev_port_attr_set_deferred(struct net_device *dev, const void *data) { const struct switchdev_attr *attr = data; int err; err = switchdev_port_attr_set_now(dev, attr, NULL); if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", err, attr->id); if (attr->complete) attr->complete(dev, err, attr->complete_priv); } static int switchdev_port_attr_set_defer(struct net_device *dev, const struct switchdev_attr *attr) { return switchdev_deferred_enqueue(dev, attr, sizeof(*attr), switchdev_port_attr_set_deferred); } /** * switchdev_port_attr_set - Set port attribute * * @dev: port device * @attr: attribute to set * @extack: netlink extended ack, for error message propagation * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { if (attr->flags & SWITCHDEV_F_DEFER) return switchdev_port_attr_set_defer(dev, attr); ASSERT_RTNL(); return switchdev_port_attr_set_now(dev, attr, extack); } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static size_t switchdev_obj_size(const struct switchdev_obj *obj) { switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: return sizeof(struct switchdev_obj_port_vlan); case SWITCHDEV_OBJ_ID_PORT_MDB: return sizeof(struct switchdev_obj_port_mdb); case SWITCHDEV_OBJ_ID_HOST_MDB: return sizeof(struct switchdev_obj_port_mdb); default: BUG(); } return 0; } static int switchdev_port_obj_notify(enum switchdev_notifier_type nt, struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { int rc; int err; struct switchdev_notifier_port_obj_info obj_info = { .obj = obj, .handled = false, }; rc = call_switchdev_blocking_notifiers(nt, dev, &obj_info.info, extack); err = notifier_to_errno(rc); if (err) { WARN_ON(!obj_info.handled); return err; } if (!obj_info.handled) return -EOPNOTSUPP; return 0; } static void switchdev_obj_id_to_helpful_msg(struct net_device *dev, enum switchdev_obj_id obj_id, int err, bool add) { const char *action = add ? "add" : "del"; const char *reason = ""; const char *problem; const char *obj_str; switch (obj_id) { case SWITCHDEV_OBJ_ID_UNDEFINED: obj_str = "Undefined object"; problem = "Attempted operation is undefined, indicating a possible programming\n" "error.\n"; break; case SWITCHDEV_OBJ_ID_PORT_VLAN: obj_str = "VLAN entry"; problem = "Failure in VLAN settings on this port might disrupt network\n" "segmentation or traffic isolation, affecting network partitioning.\n"; break; case SWITCHDEV_OBJ_ID_PORT_MDB: obj_str = "Port Multicast Database entry"; problem = "Failure in updating the port's Multicast Database could lead to\n" "multicast forwarding issues.\n"; break; case SWITCHDEV_OBJ_ID_HOST_MDB: obj_str = "Host Multicast Database entry"; problem = "Failure in updating the host's Multicast Database may impact multicast\n" "group memberships or traffic delivery, affecting multicast\n" "communication.\n"; break; case SWITCHDEV_OBJ_ID_MRP: obj_str = "Media Redundancy Protocol configuration for port"; problem = "Failure to set MRP ring ID on this port prevents communication with\n" "the specified redundancy ring, resulting in an inability to engage\n" "in MRP-based network operations.\n"; break; case SWITCHDEV_OBJ_ID_RING_TEST_MRP: obj_str = "MRP Test Frame Operations for port"; problem = "Failure to generate/monitor MRP test frames may lead to inability to\n" "assess the ring's operational integrity and fault response, hindering\n" "proactive network management.\n"; break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: obj_str = "MRP Ring Role Configuration"; problem = "Improper MRP ring role configuration may create conflicts in the ring,\n" "disrupting communication for all participants, or isolate the local\n" "system from the ring, hindering its ability to communicate with other\n" "participants.\n"; break; case SWITCHDEV_OBJ_ID_RING_STATE_MRP: obj_str = "MRP Ring State Configuration"; problem = "Failure to correctly set the MRP ring state can result in network\n" "loops or leave segments without communication. In a Closed state,\n" "it maintains loop prevention by blocking one MRM port, while an Open\n" "state activates in response to failures, changing port states to\n" "preserve network connectivity.\n"; break; case SWITCHDEV_OBJ_ID_IN_TEST_MRP: obj_str = "MRP_InTest Frame Generation Configuration"; problem = "Failure in managing MRP_InTest frame generation can misjudge the\n" "interconnection ring's state, leading to incorrect blocking or\n" "unblocking of the I/C port. This misconfiguration might result\n" "in unintended network loops or isolate critical network segments,\n" "compromising network integrity and reliability.\n"; break; case SWITCHDEV_OBJ_ID_IN_ROLE_MRP: obj_str = "Interconnection Ring Role Configuration"; problem = "Failure in incorrect assignment of interconnection ring roles\n" "(MIM/MIC) can impair the formation of the interconnection rings.\n"; break; case SWITCHDEV_OBJ_ID_IN_STATE_MRP: obj_str = "Interconnection Ring State Configuration"; problem = "Failure in updating the interconnection ring state can lead in\n" "case of Open state to incorrect blocking or unblocking of the\n" "I/C port, resulting in unintended network loops or isolation\n" "of critical network\n"; break; default: obj_str = "Unknown object"; problem = "Indicating a possible programming error.\n"; } switch (err) { case -ENOSPC: reason = "Current HW/SW setup lacks sufficient resources.\n"; break; } netdev_err(dev, "Failed to %s %s (object id=%d) with error: %pe (%d).\n%s%s\n", action, obj_str, obj_id, ERR_PTR(err), err, problem, reason); } static void switchdev_port_obj_add_deferred(struct net_device *dev, const void *data) { const struct switchdev_obj *obj = data; int err; ASSERT_RTNL(); err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, dev, obj, NULL); if (err && err != -EOPNOTSUPP) switchdev_obj_id_to_helpful_msg(dev, obj->id, err, true); if (obj->complete) obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_add_defer(struct net_device *dev, const struct switchdev_obj *obj) { return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj), switchdev_port_obj_add_deferred); } /** * switchdev_port_obj_add - Add port object * * @dev: port device * @obj: object to add * @extack: netlink extended ack * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { if (obj->flags & SWITCHDEV_F_DEFER) return switchdev_port_obj_add_defer(dev, obj); ASSERT_RTNL(); return switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, dev, obj, extack); } EXPORT_SYMBOL_GPL(switchdev_port_obj_add); static int switchdev_port_obj_del_now(struct net_device *dev, const struct switchdev_obj *obj) { return switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_DEL, dev, obj, NULL); } static void switchdev_port_obj_del_deferred(struct net_device *dev, const void *data) { const struct switchdev_obj *obj = data; int err; err = switchdev_port_obj_del_now(dev, obj); if (err && err != -EOPNOTSUPP) switchdev_obj_id_to_helpful_msg(dev, obj->id, err, false); if (obj->complete) obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_del_defer(struct net_device *dev, const struct switchdev_obj *obj) { return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj), switchdev_port_obj_del_deferred); } /** * switchdev_port_obj_del - Delete port object * * @dev: port device * @obj: object to delete * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { if (obj->flags & SWITCHDEV_F_DEFER) return switchdev_port_obj_del_defer(dev, obj); ASSERT_RTNL(); return switchdev_port_obj_del_now(dev, obj); } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); /** * switchdev_port_obj_act_is_deferred - Is object action pending? * * @dev: port device * @nt: type of action; add or delete * @obj: object to test * * Returns true if a deferred item is pending, which is * equivalent to the action @nt on an object @obj. * * rtnl_lock must be held. */ bool switchdev_port_obj_act_is_deferred(struct net_device *dev, enum switchdev_notifier_type nt, const struct switchdev_obj *obj) { struct switchdev_deferred_item *dfitem; bool found = false; ASSERT_RTNL(); spin_lock_bh(&deferred_lock); list_for_each_entry(dfitem, &deferred, list) { if (dfitem->dev != dev) continue; if ((dfitem->func == switchdev_port_obj_add_deferred && nt == SWITCHDEV_PORT_OBJ_ADD) || (dfitem->func == switchdev_port_obj_del_deferred && nt == SWITCHDEV_PORT_OBJ_DEL)) { if (switchdev_obj_eq((const void *)dfitem->data, obj)) { found = true; break; } } } spin_unlock_bh(&deferred_lock); return found; } EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); static RAW_NOTIFIER_HEAD(switchdev_blocking_notif_chain); /** * register_switchdev_notifier - Register notifier * @nb: notifier_block * * Register switch device notifier. */ int register_switchdev_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&switchdev_notif_chain, nb); } EXPORT_SYMBOL_GPL(register_switchdev_notifier); /** * unregister_switchdev_notifier - Unregister notifier * @nb: notifier_block * * Unregister switch device notifier. */ int unregister_switchdev_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&switchdev_notif_chain, nb); } EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); /** * call_switchdev_notifiers - Call notifiers * @val: value passed unmodified to notifier function * @dev: port device * @info: notifier information data * @extack: netlink extended ack * Call all network notifier blocks. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info, struct netlink_ext_ack *extack) { info->dev = dev; info->extack = extack; return atomic_notifier_call_chain(&switchdev_notif_chain, val, info); } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); int register_switchdev_blocking_notifier(struct notifier_block *nb) { struct raw_notifier_head *chain = &switchdev_blocking_notif_chain; int err; rtnl_lock(); err = raw_notifier_chain_register(chain, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(register_switchdev_blocking_notifier); int unregister_switchdev_blocking_notifier(struct notifier_block *nb) { struct raw_notifier_head *chain = &switchdev_blocking_notif_chain; int err; rtnl_lock(); err = raw_notifier_chain_unregister(chain, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(unregister_switchdev_blocking_notifier); int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info, struct netlink_ext_ack *extack) { ASSERT_RTNL(); info->dev = dev; info->extack = extack; return raw_notifier_call_chain(&switchdev_blocking_notif_chain, val, info); } EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); struct switchdev_nested_priv { bool (*check_cb)(const struct net_device *dev); bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev); const struct net_device *dev; struct net_device *lower_dev; }; static int switchdev_lower_dev_walk(struct net_device *lower_dev, struct netdev_nested_priv *priv) { struct switchdev_nested_priv *switchdev_priv = priv->data; bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev); bool (*check_cb)(const struct net_device *dev); const struct net_device *dev; check_cb = switchdev_priv->check_cb; foreign_dev_check_cb = switchdev_priv->foreign_dev_check_cb; dev = switchdev_priv->dev; if (check_cb(lower_dev) && !foreign_dev_check_cb(lower_dev, dev)) { switchdev_priv->lower_dev = lower_dev; return 1; } return 0; } static struct net_device * switchdev_lower_dev_find_rcu(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev)) { struct switchdev_nested_priv switchdev_priv = { .check_cb = check_cb, .foreign_dev_check_cb = foreign_dev_check_cb, .dev = dev, .lower_dev = NULL, }; struct netdev_nested_priv priv = { .data = &switchdev_priv, }; netdev_walk_all_lower_dev_rcu(dev, switchdev_lower_dev_walk, &priv); return switchdev_priv.lower_dev; } static struct net_device * switchdev_lower_dev_find(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev)) { struct switchdev_nested_priv switchdev_priv = { .check_cb = check_cb, .foreign_dev_check_cb = foreign_dev_check_cb, .dev = dev, .lower_dev = NULL, }; struct netdev_nested_priv priv = { .data = &switchdev_priv, }; netdev_walk_all_lower_dev(dev, switchdev_lower_dev_walk, &priv); return switchdev_priv.lower_dev; } static int __switchdev_handle_fdb_event_to_device(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const struct switchdev_notifier_fdb_info *fdb_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info)) { const struct switchdev_notifier_info *info = &fdb_info->info; struct net_device *br, *lower_dev, *switchdev; struct list_head *iter; int err = -EOPNOTSUPP; if (check_cb(dev)) return mod_cb(dev, orig_dev, event, info->ctx, fdb_info); /* Recurse through lower interfaces in case the FDB entry is pointing * towards a bridge or a LAG device. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { /* Do not propagate FDB entries across bridges */ if (netif_is_bridge_master(lower_dev)) continue; /* Bridge ports might be either us, or LAG interfaces * that we offload. */ if (!check_cb(lower_dev) && !switchdev_lower_dev_find_rcu(lower_dev, check_cb, foreign_dev_check_cb)) continue; err = __switchdev_handle_fdb_event_to_device(lower_dev, orig_dev, event, fdb_info, check_cb, foreign_dev_check_cb, mod_cb); if (err && err != -EOPNOTSUPP) return err; } /* Event is neither on a bridge nor a LAG. Check whether it is on an * interface that is in a bridge with us. */ br = netdev_master_upper_dev_get_rcu(dev); if (!br || !netif_is_bridge_master(br)) return 0; switchdev = switchdev_lower_dev_find_rcu(br, check_cb, foreign_dev_check_cb); if (!switchdev) return 0; if (!foreign_dev_check_cb(switchdev, dev)) return err; return __switchdev_handle_fdb_event_to_device(br, orig_dev, event, fdb_info, check_cb, foreign_dev_check_cb, mod_cb); } int switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long event, const struct switchdev_notifier_fdb_info *fdb_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info)) { int err; err = __switchdev_handle_fdb_event_to_device(dev, dev, event, fdb_info, check_cb, foreign_dev_check_cb, mod_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_fdb_event_to_device); static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { struct switchdev_notifier_info *info = &port_obj_info->info; struct net_device *br, *lower_dev, *switchdev; struct netlink_ext_ack *extack; struct list_head *iter; int err = -EOPNOTSUPP; extack = switchdev_notifier_info_to_extack(info); if (check_cb(dev)) { err = add_cb(dev, info->ctx, port_obj_info->obj, extack); if (err != -EOPNOTSUPP) port_obj_info->handled = true; return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the * unsupported devices, another driver might be able to handle them. But * propagate to the callers any hard errors. * * If the driver does its own bookkeeping of stacked ports, it's not * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { if (netif_is_bridge_master(lower_dev)) continue; /* When searching for switchdev interfaces that are neighbors * of foreign ones, and @dev is a bridge, do not recurse on the * foreign interface again, it was already visited. */ if (foreign_dev_check_cb && !check_cb(lower_dev) && !switchdev_lower_dev_find(lower_dev, check_cb, foreign_dev_check_cb)) continue; err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info, check_cb, foreign_dev_check_cb, add_cb); if (err && err != -EOPNOTSUPP) return err; } /* Event is neither on a bridge nor a LAG. Check whether it is on an * interface that is in a bridge with us. */ if (!foreign_dev_check_cb || port_obj_info->obj->flags & SWITCHDEV_F_NO_FOREIGN) return err; br = netdev_master_upper_dev_get(dev); if (!br || !netif_is_bridge_master(br)) return err; switchdev = switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb); if (!switchdev) return err; if (!foreign_dev_check_cb(switchdev, dev)) return err; return __switchdev_handle_port_obj_add(br, port_obj_info, check_cb, foreign_dev_check_cb, add_cb); } /* Pass through a port object addition, if @dev passes @check_cb, or replicate * it towards all lower interfaces of @dev that pass @check_cb, if @dev is a * bridge or a LAG. */ int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { int err; err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb, NULL, add_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add); /* Same as switchdev_handle_port_obj_add(), except if object is notified on a * @dev that passes @foreign_dev_check_cb, it is replicated towards all devices * that pass @check_cb and are in the same bridge as @dev. */ int switchdev_handle_port_obj_add_foreign(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { int err; err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb, foreign_dev_check_cb, add_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add_foreign); static int __switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { struct switchdev_notifier_info *info = &port_obj_info->info; struct net_device *br, *lower_dev, *switchdev; struct list_head *iter; int err = -EOPNOTSUPP; if (check_cb(dev)) { err = del_cb(dev, info->ctx, port_obj_info->obj); if (err != -EOPNOTSUPP) port_obj_info->handled = true; return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the * unsupported devices, another driver might be able to handle them. But * propagate to the callers any hard errors. * * If the driver does its own bookkeeping of stacked ports, it's not * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { if (netif_is_bridge_master(lower_dev)) continue; /* When searching for switchdev interfaces that are neighbors * of foreign ones, and @dev is a bridge, do not recurse on the * foreign interface again, it was already visited. */ if (foreign_dev_check_cb && !check_cb(lower_dev) && !switchdev_lower_dev_find(lower_dev, check_cb, foreign_dev_check_cb)) continue; err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info, check_cb, foreign_dev_check_cb, del_cb); if (err && err != -EOPNOTSUPP) return err; } /* Event is neither on a bridge nor a LAG. Check whether it is on an * interface that is in a bridge with us. */ if (!foreign_dev_check_cb) return err; br = netdev_master_upper_dev_get(dev); if (!br || !netif_is_bridge_master(br)) return err; switchdev = switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb); if (!switchdev) return err; if (!foreign_dev_check_cb(switchdev, dev)) return err; return __switchdev_handle_port_obj_del(br, port_obj_info, check_cb, foreign_dev_check_cb, del_cb); } /* Pass through a port object deletion, if @dev passes @check_cb, or replicate * it towards all lower interfaces of @dev that pass @check_cb, if @dev is a * bridge or a LAG. */ int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { int err; err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb, NULL, del_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del); /* Same as switchdev_handle_port_obj_del(), except if object is notified on a * @dev that passes @foreign_dev_check_cb, it is replicated towards all devices * that pass @check_cb and are in the same bridge as @dev. */ int switchdev_handle_port_obj_del_foreign(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, const struct net_device *foreign_dev), int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { int err; err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb, foreign_dev_check_cb, del_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del_foreign); static int __switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { struct switchdev_notifier_info *info = &port_attr_info->info; struct netlink_ext_ack *extack; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; extack = switchdev_notifier_info_to_extack(info); if (check_cb(dev)) { err = set_cb(dev, info->ctx, port_attr_info->attr, extack); if (err != -EOPNOTSUPP) port_attr_info->handled = true; return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the * unsupported devices, another driver might be able to handle them. But * propagate to the callers any hard errors. * * If the driver does its own bookkeeping of stacked ports, it's not * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { if (netif_is_bridge_master(lower_dev)) continue; err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info, check_cb, set_cb); if (err && err != -EOPNOTSUPP) return err; } return err; } int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { int err; err = __switchdev_handle_port_attr_set(dev, port_attr_info, check_cb, set_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set); int switchdev_bridge_port_offload(struct net_device *brport_dev, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, bool tx_fwd_offload, struct netlink_ext_ack *extack) { struct switchdev_notifier_brport_info brport_info = { .brport = { .dev = dev, .ctx = ctx, .atomic_nb = atomic_nb, .blocking_nb = blocking_nb, .tx_fwd_offload = tx_fwd_offload, }, }; int err; ASSERT_RTNL(); err = call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_OFFLOADED, brport_dev, &brport_info.info, extack); return notifier_to_errno(err); } EXPORT_SYMBOL_GPL(switchdev_bridge_port_offload); void switchdev_bridge_port_unoffload(struct net_device *brport_dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb) { struct switchdev_notifier_brport_info brport_info = { .brport = { .ctx = ctx, .atomic_nb = atomic_nb, .blocking_nb = blocking_nb, }, }; ASSERT_RTNL(); call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_UNOFFLOADED, brport_dev, &brport_info.info, NULL); } EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload); int switchdev_bridge_port_replay(struct net_device *brport_dev, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, struct netlink_ext_ack *extack) { struct switchdev_notifier_brport_info brport_info = { .brport = { .dev = dev, .ctx = ctx, .atomic_nb = atomic_nb, .blocking_nb = blocking_nb, }, }; int err; ASSERT_RTNL(); err = call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_REPLAY, brport_dev, &brport_info.info, extack); return notifier_to_errno(err); } EXPORT_SYMBOL_GPL(switchdev_bridge_port_replay); |
| 25 25 25 25 24 61 61 34 9 25 29 29 29 29 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/list.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/srcu.h> #include <linux/rculist.h> #include <linux/wait.h> #include <linux/memcontrol.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #include <linux/atomic.h> /* * Final freeing of a group */ static void fsnotify_final_destroy_group(struct fsnotify_group *group) { if (group->ops->free_group_priv) group->ops->free_group_priv(group); mem_cgroup_put(group->memcg); mutex_destroy(&group->mark_mutex); kfree(group); } /* * Stop queueing new events for this group. Once this function returns * fsnotify_add_event() will not add any new events to the group's queue. */ void fsnotify_group_stop_queueing(struct fsnotify_group *group) { spin_lock(&group->notification_lock); group->shutdown = true; spin_unlock(&group->notification_lock); } /* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. * Note that another thread calling fsnotify_clear_marks_by_group() may still * hold a ref to the group. */ void fsnotify_destroy_group(struct fsnotify_group *group) { /* * Stop queueing new events. The code below is careful enough to not * require this but fanotify needs to stop queuing events even before * fsnotify_destroy_group() is called and this makes the other callers * of fsnotify_destroy_group() to see the same behavior. */ fsnotify_group_stop_queueing(group); /* Clear all marks for this group and queue them for destruction */ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_ANY); /* * Some marks can still be pinned when waiting for response from * userspace. Wait for those now. fsnotify_prepare_user_wait() will * not succeed now so this wait is race-free. */ wait_event(group->notification_waitq, !atomic_read(&group->user_waits)); /* * Wait until all marks get really destroyed. We could actually destroy * them ourselves instead of waiting for worker to do it, however that * would be racy as worker can already be processing some marks before * we even entered fsnotify_destroy_group(). */ fsnotify_wait_marks_destroyed(); /* * Since we have waited for fsnotify_mark_srcu in * fsnotify_mark_destroy_list() there can be no outstanding event * notification against this group. So clearing the notification queue * of all events is reliable now. */ fsnotify_flush_notify(group); /* * Destroy overflow event (we cannot use fsnotify_destroy_event() as * that deliberately ignores overflow events. */ if (group->overflow_event) group->ops->free_event(group, group->overflow_event); fsnotify_put_group(group); } /* * Get reference to a group. */ void fsnotify_get_group(struct fsnotify_group *group) { refcount_inc(&group->refcnt); } /* * Drop a reference to a group. Free it if it's through. */ void fsnotify_put_group(struct fsnotify_group *group) { if (refcount_dec_and_test(&group->refcnt)) fsnotify_final_destroy_group(group); } EXPORT_SYMBOL_GPL(fsnotify_put_group); static struct fsnotify_group *__fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags, gfp_t gfp) { struct fsnotify_group *group; group = kzalloc_obj(struct fsnotify_group, gfp); if (!group) return ERR_PTR(-ENOMEM); /* set to 0 when there a no external references to this group */ refcount_set(&group->refcnt, 1); atomic_set(&group->user_waits, 0); spin_lock_init(&group->notification_lock); INIT_LIST_HEAD(&group->notification_list); init_waitqueue_head(&group->notification_waitq); group->max_events = UINT_MAX; mutex_init(&group->mark_mutex); INIT_LIST_HEAD(&group->marks_list); group->ops = ops; group->flags = flags; return group; } /* * Create a new fsnotify_group and hold a reference for the group returned. */ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops, int flags) { gfp_t gfp = (flags & FSNOTIFY_GROUP_USER) ? GFP_KERNEL_ACCOUNT : GFP_KERNEL; return __fsnotify_alloc_group(ops, flags, gfp); } EXPORT_SYMBOL_GPL(fsnotify_alloc_group); int fsnotify_fasync(int fd, struct file *file, int on) { struct fsnotify_group *group = file->private_data; return fasync_helper(fd, file, on, &group->fsn_fa) >= 0 ? 0 : -EIO; } |
| 4556 672 672 749 68 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(folio) ( \ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); __entry->lru = folio_lru_list(folio); __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); ), TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 879 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 | // SPDX-License-Identifier: GPL-2.0 /* * Deferred user space unwinding */ #include <linux/sched/task_stack.h> #include <linux/unwind_deferred.h> #include <linux/sched/clock.h> #include <linux/task_work.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sizes.h> #include <linux/slab.h> #include <linux/mm.h> /* * For requesting a deferred user space stack trace from NMI context * the architecture must support a safe cmpxchg in NMI context. * For those architectures that do not have that, then it cannot ask * for a deferred user space stack trace from an NMI context. If it * does, then it will get -EINVAL. */ #if defined(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) # define CAN_USE_IN_NMI 1 static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt) { u32 old = 0; return try_cmpxchg(&info->id.cnt, &old, cnt); } #else # define CAN_USE_IN_NMI 0 /* When NMIs are not allowed, this always succeeds */ static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt) { info->id.cnt = cnt; return true; } #endif /* Make the cache fit in a 4K page */ #define UNWIND_MAX_ENTRIES \ ((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long)) /* Guards adding to or removing from the list of callbacks */ static DEFINE_MUTEX(callback_mutex); static LIST_HEAD(callbacks); #define RESERVED_BITS (UNWIND_PENDING | UNWIND_USED) /* Zero'd bits are available for assigning callback users */ static unsigned long unwind_mask = RESERVED_BITS; DEFINE_STATIC_SRCU(unwind_srcu); static inline bool unwind_pending(struct unwind_task_info *info) { return atomic_long_read(&info->unwind_mask) & UNWIND_PENDING; } /* * This is a unique percpu identifier for a given task entry context. * Conceptually, it's incremented every time the CPU enters the kernel from * user space, so that each "entry context" on the CPU gets a unique ID. In * reality, as an optimization, it's only incremented on demand for the first * deferred unwind request after a given entry-from-user. * * It's combined with the CPU id to make a systemwide-unique "context cookie". */ static DEFINE_PER_CPU(u32, unwind_ctx_ctr); /* * The context cookie is a unique identifier that is assigned to a user * space stacktrace. As the user space stacktrace remains the same while * the task is in the kernel, the cookie is an identifier for the stacktrace. * Although it is possible for the stacktrace to get another cookie if another * request is made after the cookie was cleared and before reentering user * space. */ static u64 get_cookie(struct unwind_task_info *info) { u32 cnt = 1; lockdep_assert_irqs_disabled(); if (info->id.cpu) return info->id.id; /* LSB is always set to ensure 0 is an invalid value */ cnt |= __this_cpu_read(unwind_ctx_ctr) + 2; if (try_assign_cnt(info, cnt)) { /* Update the per cpu counter */ __this_cpu_write(unwind_ctx_ctr, cnt); } /* Interrupts are disabled, the CPU will always be same */ info->id.cpu = smp_processor_id() + 1; /* Must be non zero */ return info->id.id; } /** * unwind_user_faultable - Produce a user stacktrace in faultable context * @trace: The descriptor that will store the user stacktrace * * This must be called in a known faultable context (usually when entering * or exiting user space). Depending on the available implementations * the @trace will be loaded with the addresses of the user space stacktrace * if it can be found. * * Return: 0 on success and negative on error * On success @trace will contain the user space stacktrace */ int unwind_user_faultable(struct unwind_stacktrace *trace) { struct unwind_task_info *info = ¤t->unwind_info; struct unwind_cache *cache; /* Should always be called from faultable context */ might_fault(); if (!current->mm) return -EINVAL; if (!info->cache) { info->cache = kzalloc_flex(*cache, entries, UNWIND_MAX_ENTRIES); if (!info->cache) return -ENOMEM; } cache = info->cache; trace->entries = cache->entries; trace->nr = cache->nr_entries; /* * The user stack has already been previously unwound in this * entry context. Skip the unwind and use the cache. */ if (trace->nr) return 0; unwind_user(trace, UNWIND_MAX_ENTRIES); cache->nr_entries = trace->nr; /* Clear nr_entries on way back to user space */ atomic_long_or(UNWIND_USED, &info->unwind_mask); return 0; } static void process_unwind_deferred(struct task_struct *task) { struct unwind_task_info *info = &task->unwind_info; struct unwind_stacktrace trace; struct unwind_work *work; unsigned long bits; u64 cookie; if (WARN_ON_ONCE(!unwind_pending(info))) return; /* Clear pending bit but make sure to have the current bits */ bits = atomic_long_fetch_andnot(UNWIND_PENDING, &info->unwind_mask); /* * From here on out, the callback must always be called, even if it's * just an empty trace. */ trace.nr = 0; trace.entries = NULL; unwind_user_faultable(&trace); if (info->cache) bits &= ~(info->cache->unwind_completed); cookie = info->id.id; guard(srcu)(&unwind_srcu); list_for_each_entry_srcu(work, &callbacks, list, srcu_read_lock_held(&unwind_srcu)) { if (test_bit(work->bit, &bits)) { work->func(work, &trace, cookie); if (info->cache) info->cache->unwind_completed |= BIT(work->bit); } } } static void unwind_deferred_task_work(struct callback_head *head) { process_unwind_deferred(current); } void unwind_deferred_task_exit(struct task_struct *task) { struct unwind_task_info *info = ¤t->unwind_info; if (!unwind_pending(info)) return; process_unwind_deferred(task); task_work_cancel(task, &info->work); } /** * unwind_deferred_request - Request a user stacktrace on task kernel exit * @work: Unwind descriptor requesting the trace * @cookie: The cookie of the first request made for this task * * Schedule a user space unwind to be done in task work before exiting the * kernel. * * The returned @cookie output is the generated cookie of the very first * request for a user space stacktrace for this task since it entered the * kernel. It can be from a request by any caller of this infrastructure. * Its value will also be passed to the callback function. It can be * used to stitch kernel and user stack traces together in post-processing. * * It's valid to call this function multiple times for the same @work within * the same task entry context. Each call will return the same cookie * while the task hasn't left the kernel. If the callback is not pending * because it has already been previously called for the same entry context, * it will be called again with the same stack trace and cookie. * * Return: 0 if the callback successfully was queued. * 1 if the callback is pending or was already executed. * Negative if there's an error. * @cookie holds the cookie of the first request by any user */ int unwind_deferred_request(struct unwind_work *work, u64 *cookie) { struct unwind_task_info *info = ¤t->unwind_info; int twa_mode = TWA_RESUME; unsigned long old, bits; unsigned long bit; int ret; *cookie = 0; if ((current->flags & (PF_KTHREAD | PF_EXITING)) || !user_mode(task_pt_regs(current))) return -EINVAL; /* * NMI requires having safe cmpxchg operations. * Trigger a warning to make it obvious that an architecture * is using this in NMI when it should not be. */ if (in_nmi()) { if (WARN_ON_ONCE(!CAN_USE_IN_NMI)) return -EINVAL; twa_mode = TWA_NMI_CURRENT; } /* Do not allow cancelled works to request again */ bit = READ_ONCE(work->bit); if (WARN_ON_ONCE(bit < 0)) return -EINVAL; /* Only need the mask now */ bit = BIT(bit); guard(irqsave)(); *cookie = get_cookie(info); old = atomic_long_read(&info->unwind_mask); /* Is this already queued or executed */ if (old & bit) return 1; /* * This work's bit hasn't been set yet. Now set it with the PENDING * bit and fetch the current value of unwind_mask. If ether the * work's bit or PENDING was already set, then this is already queued * to have a callback. */ bits = UNWIND_PENDING | bit; old = atomic_long_fetch_or(bits, &info->unwind_mask); if (old & bits) { /* * If the work's bit was set, whatever set it had better * have also set pending and queued a callback. */ WARN_ON_ONCE(!(old & UNWIND_PENDING)); return old & bit; } /* The work has been claimed, now schedule it. */ ret = task_work_add(current, &info->work, twa_mode); if (WARN_ON_ONCE(ret)) atomic_long_set(&info->unwind_mask, 0); return ret; } void unwind_deferred_cancel(struct unwind_work *work) { struct task_struct *g, *t; int bit; if (!work) return; bit = work->bit; /* No work should be using a reserved bit */ if (WARN_ON_ONCE(BIT(bit) & RESERVED_BITS)) return; guard(mutex)(&callback_mutex); list_del_rcu(&work->list); /* Do not allow any more requests and prevent callbacks */ work->bit = -1; __clear_bit(bit, &unwind_mask); synchronize_srcu(&unwind_srcu); guard(rcu)(); /* Clear this bit from all threads */ for_each_process_thread(g, t) { atomic_long_andnot(BIT(bit), &t->unwind_info.unwind_mask); if (t->unwind_info.cache) clear_bit(bit, &t->unwind_info.cache->unwind_completed); } } int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { memset(work, 0, sizeof(*work)); guard(mutex)(&callback_mutex); /* See if there's a bit in the mask available */ if (unwind_mask == ~0UL) return -EBUSY; work->bit = ffz(unwind_mask); __set_bit(work->bit, &unwind_mask); list_add_rcu(&work->list, &callbacks); work->func = func; return 0; } void unwind_task_init(struct task_struct *task) { struct unwind_task_info *info = &task->unwind_info; memset(info, 0, sizeof(*info)); init_task_work(&info->work, unwind_deferred_task_work); atomic_long_set(&info->unwind_mask, 0); } void unwind_task_free(struct task_struct *task) { struct unwind_task_info *info = &task->unwind_info; kfree(info->cache); task_work_cancel(task, &info->work); } |
| 5 2 2 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2003-2008 Takahiro Hirofuchi * Copyright (C) 2015 Nobuo Iwata */ #include <linux/kthread.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/workqueue.h> #include "usbip_common.h" struct usbip_event { struct list_head node; struct usbip_device *ud; }; static DEFINE_SPINLOCK(event_lock); static LIST_HEAD(event_list); static void set_event(struct usbip_device *ud, unsigned long event) { unsigned long flags; spin_lock_irqsave(&ud->lock, flags); ud->event |= event; spin_unlock_irqrestore(&ud->lock, flags); } static void unset_event(struct usbip_device *ud, unsigned long event) { unsigned long flags; spin_lock_irqsave(&ud->lock, flags); ud->event &= ~event; spin_unlock_irqrestore(&ud->lock, flags); } static struct usbip_device *get_event(void) { struct usbip_event *ue = NULL; struct usbip_device *ud = NULL; unsigned long flags; spin_lock_irqsave(&event_lock, flags); if (!list_empty(&event_list)) { ue = list_first_entry(&event_list, struct usbip_event, node); list_del(&ue->node); } spin_unlock_irqrestore(&event_lock, flags); if (ue) { ud = ue->ud; kfree(ue); } return ud; } static struct task_struct *worker_context; static void event_handler(struct work_struct *work) { struct usbip_device *ud; if (worker_context == NULL) { worker_context = current; } while ((ud = get_event()) != NULL) { usbip_dbg_eh("pending event %lx\n", ud->event); mutex_lock(&ud->sysfs_lock); /* * NOTE: shutdown must come first. * Shutdown the device. */ if (ud->event & USBIP_EH_SHUTDOWN) { ud->eh_ops.shutdown(ud); unset_event(ud, USBIP_EH_SHUTDOWN); } /* Reset the device. */ if (ud->event & USBIP_EH_RESET) { ud->eh_ops.reset(ud); unset_event(ud, USBIP_EH_RESET); } /* Mark the device as unusable. */ if (ud->event & USBIP_EH_UNUSABLE) { ud->eh_ops.unusable(ud); unset_event(ud, USBIP_EH_UNUSABLE); } mutex_unlock(&ud->sysfs_lock); wake_up(&ud->eh_waitq); } } int usbip_start_eh(struct usbip_device *ud) { init_waitqueue_head(&ud->eh_waitq); ud->event = 0; return 0; } EXPORT_SYMBOL_GPL(usbip_start_eh); void usbip_stop_eh(struct usbip_device *ud) { unsigned long pending = ud->event & ~USBIP_EH_BYE; if (!(ud->event & USBIP_EH_BYE)) usbip_dbg_eh("usbip_eh stopping but not removed\n"); if (pending) usbip_dbg_eh("usbip_eh waiting completion %lx\n", pending); wait_event_interruptible(ud->eh_waitq, !(ud->event & ~USBIP_EH_BYE)); usbip_dbg_eh("usbip_eh has stopped\n"); } EXPORT_SYMBOL_GPL(usbip_stop_eh); #define WORK_QUEUE_NAME "usbip_event" static struct workqueue_struct *usbip_queue; static DECLARE_WORK(usbip_work, event_handler); int usbip_init_eh(void) { usbip_queue = create_singlethread_workqueue(WORK_QUEUE_NAME); if (usbip_queue == NULL) { pr_err("failed to create usbip_event\n"); return -ENOMEM; } return 0; } void usbip_finish_eh(void) { destroy_workqueue(usbip_queue); usbip_queue = NULL; } void usbip_event_add(struct usbip_device *ud, unsigned long event) { struct usbip_event *ue; unsigned long flags; if (ud->event & USBIP_EH_BYE) return; set_event(ud, event); spin_lock_irqsave(&event_lock, flags); list_for_each_entry_reverse(ue, &event_list, node) { if (ue->ud == ud) goto out; } ue = kmalloc_obj(struct usbip_event, GFP_ATOMIC); if (ue == NULL) goto out; ue->ud = ud; list_add_tail(&ue->node, &event_list); queue_work(usbip_queue, &usbip_work); out: spin_unlock_irqrestore(&event_lock, flags); } EXPORT_SYMBOL_GPL(usbip_event_add); int usbip_event_happened(struct usbip_device *ud) { int happened = 0; unsigned long flags; spin_lock_irqsave(&ud->lock, flags); if (ud->event != 0) happened = 1; spin_unlock_irqrestore(&ud->lock, flags); return happened; } EXPORT_SYMBOL_GPL(usbip_event_happened); int usbip_in_eh(struct task_struct *task) { if (task == worker_context) return 1; return 0; } EXPORT_SYMBOL_GPL(usbip_in_eh); |
| 12 106 25 5 55 74 382 33 69 69 69 68 68 12 12 68 4 21 49 2714 6 36 33 2659 33 58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2001 Jens Axboe <axboe@suse.de> */ #ifndef __LINUX_BIO_H #define __LINUX_BIO_H #include <linux/mempool.h> /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include <linux/blk_types.h> #include <linux/uio.h> #define BIO_MAX_VECS 256U #define BIO_MAX_INLINE_VECS UIO_MAXIOV struct queue_limits; static inline unsigned int bio_max_segs(unsigned int nr_segs) { return min(nr_segs, BIO_MAX_VECS); } #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) #define bio_iter_page(bio, iter) \ bvec_iter_page((bio)->bi_io_vec, (iter)) #define bio_iter_len(bio, iter) \ bvec_iter_len((bio)->bi_io_vec, (iter)) #define bio_iter_offset(bio, iter) \ bvec_iter_offset((bio)->bi_io_vec, (iter)) #define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) #define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter) #define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter) /* * Return the data direction, READ or WRITE. */ #define bio_data_dir(bio) \ (op_is_write(bio_op(bio)) ? WRITE : READ) static inline bool bio_flagged(const struct bio *bio, unsigned int bit) { return bio->bi_flags & (1U << bit); } static inline void bio_set_flag(struct bio *bio, unsigned int bit) { bio->bi_flags |= (1U << bit); } static inline void bio_clear_flag(struct bio *bio, unsigned int bit) { bio->bi_flags &= ~(1U << bit); } /* * Check whether this bio carries any data or not. A NULL bio is allowed. */ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && bio_op(bio) != REQ_OP_DISCARD && bio_op(bio) != REQ_OP_SECURE_ERASE && bio_op(bio) != REQ_OP_WRITE_ZEROES) return true; return false; } static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || bio_op(bio) == REQ_OP_WRITE_ZEROES; } static inline void *bio_data(struct bio *bio) { if (bio_has_data(bio)) return page_address(bio_page(bio)) + bio_offset(bio); return NULL; } static inline bool bio_next_segment(const struct bio *bio, struct bvec_iter_all *iter) { if (iter->idx >= bio->bi_vcnt) return false; bvec_advance(&bio->bi_io_vec[iter->idx], iter); return true; } /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) static inline void bio_advance_iter(const struct bio *bio, struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ } /* @bytes should be less or equal to bvec[i->bi_idx].bv_len */ static inline void bio_advance_iter_single(const struct bio *bio, struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance_single(bio->bi_io_vec, iter, bytes); } void __bio_advance(struct bio *, unsigned bytes); /** * bio_advance - increment/complete a bio by some number of bytes * @bio: bio to advance * @nbytes: number of bytes to complete * * This updates bi_sector, bi_size and bi_idx; if the number of bytes to * complete doesn't align with a bvec boundary, then bv_len and bv_offset will * be updated on the last bvec as well. * * @bio will then represent the remaining, uncompleted portion of the io. */ static inline void bio_advance(struct bio *bio, unsigned int nbytes) { if (nbytes == bio->bi_iter.bi_size) { bio->bi_iter.bi_size = 0; return; } __bio_advance(bio, nbytes); } #define __bio_for_each_segment(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bio_iter_iovec((bio), (iter))), 1); \ bio_advance_iter_single((bio), &(iter), (bvl).bv_len)) #define bio_for_each_segment(bvl, bio, iter) \ __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) #define __bio_for_each_bvec(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \ bio_advance_iter_single((bio), &(iter), (bvl).bv_len)) /* iterate over multi-page bvec */ #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) /* * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the * same reasons as bio_for_each_segment_all(). */ #define bio_for_each_bvec_all(bvl, bio, i) \ for (i = 0, bvl = bio_first_bvec_all(bio); \ i < (bio)->bi_vcnt; i++, bvl++) #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) { unsigned segs = 0; struct bio_vec bv; struct bvec_iter iter; /* * We special case discard/write same/write zeroes, because they * interpret bi_size differently: */ switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; default: break; } bio_for_each_segment(bv, bio, iter) segs++; return segs; } /* * get a reference to a bio, so it won't disappear. the intended use is * something like: * * bio_get(bio); * submit_bio(rw, bio); * if (bio->bi_flags ...) * do_something * bio_put(bio); * * without the bio_get(), it could potentially complete I/O before submit_bio * returns. and then bio would be freed memory when if (bio->bi_flags ...) * runs */ static inline void bio_get(struct bio *bio) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb__before_atomic(); atomic_inc(&bio->__bi_cnt); } static inline void bio_cnt_set(struct bio *bio, unsigned int count) { if (count != 1) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb(); } atomic_set(&bio->__bi_cnt, count); } static inline struct bio_vec *bio_first_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return bio->bi_io_vec; } static inline struct page *bio_first_page_all(struct bio *bio) { return bio_first_bvec_all(bio)->bv_page; } static inline struct folio *bio_first_folio_all(struct bio *bio) { return page_folio(bio_first_page_all(bio)); } /** * struct folio_iter - State for iterating all folios in a bio. * @folio: The current folio we're iterating. NULL after the last folio. * @offset: The byte offset within the current folio. * @length: The number of bytes in this iteration (will not cross folio * boundary). */ struct folio_iter { struct folio *folio; size_t offset; size_t length; /* private: for use by the iterator */ struct folio *_next; size_t _seg_count; int _i; }; static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, int i) { struct bio_vec *bvec = bio_first_bvec_all(bio) + i; if (unlikely(i >= bio->bi_vcnt)) { fi->folio = NULL; return; } fi->folio = bvec_folio(bvec); fi->offset = bvec->bv_offset + PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); fi->_next = folio_next(fi->folio); fi->_i = i; } static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) { fi->_seg_count -= fi->length; if (fi->_seg_count) { fi->folio = fi->_next; fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); fi->_next = folio_next(fi->folio); } else { bio_first_folio(fi, bio, fi->_i + 1); } } /** * bio_for_each_folio_all - Iterate over each folio in a bio. * @fi: struct folio_iter which is updated for each folio. * @bio: struct bio to iterate over. */ #define bio_for_each_folio_all(fi, bio) \ for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio)) void bio_trim(struct bio *bio, sector_t offset, sector_t size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); int bio_split_io_at(struct bio *bio, const struct queue_limits *lim, unsigned *segs, unsigned max_bytes, unsigned len_align); u8 bio_seg_gap(struct request_queue *q, struct bio *prev, struct bio *next, u8 gaps_bit); /** * bio_next_split - get next @sectors from a bio, splitting if necessary * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Return: a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { if (sectors >= bio_sectors(bio)) return bio; return bio_split(bio, sectors, gfp, bs); } enum { BIOSET_NEED_BVECS = BIT(0), BIOSET_NEED_RESCUER = BIT(1), BIOSET_PERCPU_CACHE = BIT(2), }; extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp, struct bio_set *bs); struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, gfp_t gfp, struct bio_set *bs); int bio_init_clone(struct block_device *bdev, struct bio *bio, struct bio *bio_src, gfp_t gfp); extern struct bio_set fs_bio_set; static inline struct bio *bio_alloc(struct block_device *bdev, unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp_mask) { return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set); } void submit_bio(struct bio *bio); extern void bio_endio(struct bio *); /** * bio_endio_status - end I/O on a bio with a specific status * @bio: bio * @status: status to set * * Set @bio->bi_status to @status and call bio_endio(). **/ static inline void bio_endio_status(struct bio *bio, blk_status_t status) { bio->bi_status = status; bio_endio(bio); } static inline void bio_io_error(struct bio *bio) { bio_endio_status(bio, BLK_STS_IOERR); } static inline void bio_wouldblock_error(struct bio *bio) { bio_endio_status(bio, BLK_STS_AGAIN); } /* * Calculate number of bvec segments that should be allocated to fit data * pointed by @iter. If @iter is backed by bvec it's going to be reused * instead of allocating a new one. */ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) { if (iov_iter_is_bvec(iter)) return 0; return iov_iter_npages(iter, max_segs); } /** * bio_iov_bounce_nr_vecs - calculate number of bvecs for a bounce bio * @iter: iter to bounce from * @op: REQ_OP_* for the bio * * Calculates how many bvecs are needed for the next bio to bounce from/to * @iter. */ static inline unsigned short bio_iov_bounce_nr_vecs(struct iov_iter *iter, blk_opf_t op) { /* * We still need to bounce bvec iters, so don't special case them * here unlike in bio_iov_vecs_to_alloc. * * For reads we need to use a vector for the bounce buffer, account * for that here. */ if (op_is_write(op)) return iov_iter_npages(iter, BIO_MAX_VECS); return iov_iter_npages(iter, BIO_MAX_VECS - 1) + 1; } struct request_queue; void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, unsigned short max_vecs, blk_opf_t opf); static inline void bio_init_inline(struct bio *bio, struct block_device *bdev, unsigned short max_vecs, blk_opf_t opf) { bio_init(bio, bdev, bio_inline_vecs(bio), max_vecs, opf); } extern void bio_uninit(struct bio *); void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf); void bio_reuse(struct bio *bio, blk_opf_t opf); void bio_chain(struct bio *, struct bio *); void bio_await(struct bio *bio, void *priv, void (*submit)(struct bio *bio, void *priv)); int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len, unsigned off); bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t off); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, size_t off); void bio_add_virt_nofail(struct bio *bio, void *vaddr, unsigned len); /** * bio_add_max_vecs - number of bio_vecs needed to add data to a bio * @kaddr: kernel virtual address to add * @len: length in bytes to add * * Calculate how many bio_vecs need to be allocated to add the kernel virtual * address range in [@kaddr:@len] in the worse case. */ static inline unsigned int bio_add_max_vecs(void *kaddr, unsigned int len) { if (is_vmalloc_addr(kaddr)) return DIV_ROUND_UP(offset_in_page(kaddr) + len, PAGE_SIZE); return 1; } unsigned int bio_add_vmalloc_chunk(struct bio *bio, void *vaddr, unsigned len); bool bio_add_vmalloc(struct bio *bio, void *vaddr, unsigned int len); int submit_bio_wait(struct bio *bio); int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data, size_t len, enum req_op op); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, unsigned len_align_mask); void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen, size_t minsize); void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); void zero_fill_bio(struct bio *bio); void guard_bio_eod(struct bio *bio); static inline void bio_release_pages(struct bio *bio, bool mark_dirty) { if (bio_flagged(bio, BIO_PAGE_PINNED)) __bio_release_pages(bio, mark_dirty); } #define bio_dev(bio) \ disk_devt((bio)->bi_bdev->bd_disk) #ifdef CONFIG_BLK_CGROUP void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); void blkcg_punt_bio_submit(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } static inline void blkcg_punt_bio_submit(struct bio *bio) { submit_bio(bio); } #endif /* CONFIG_BLK_CGROUP */ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) { bio_clear_flag(bio, BIO_REMAPPED); if (bio->bi_bdev != bdev) bio_clear_flag(bio, BIO_BPS_THROTTLED); bio->bi_bdev = bdev; bio_associate_blkg(bio); } /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * * A bio_list anchors a singly-linked list of bios chained through the bi_next * member of the bio. The bio_list also caches the last list member to allow * fast access to the tail. */ struct bio_list { struct bio *head; struct bio *tail; }; static inline int bio_list_empty(const struct bio_list *bl) { return bl->head == NULL; } static inline void bio_list_init(struct bio_list *bl) { bl->head = bl->tail = NULL; } #define BIO_EMPTY_LIST { NULL, NULL } #define bio_list_for_each(bio, bl) \ for (bio = (bl)->head; bio; bio = bio->bi_next) static inline unsigned bio_list_size(const struct bio_list *bl) { unsigned sz = 0; struct bio *bio; bio_list_for_each(bio, bl) sz++; return sz; } static inline void bio_list_add(struct bio_list *bl, struct bio *bio) { bio->bi_next = NULL; if (bl->tail) bl->tail->bi_next = bio; else bl->head = bio; bl->tail = bio; } static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio) { bio->bi_next = bl->head; bl->head = bio; if (!bl->tail) bl->tail = bio; } static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->tail) bl->tail->bi_next = bl2->head; else bl->head = bl2->head; bl->tail = bl2->tail; } static inline void bio_list_merge_init(struct bio_list *bl, struct bio_list *bl2) { bio_list_merge(bl, bl2); bio_list_init(bl2); } static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->head) bl2->tail->bi_next = bl->head; else bl->tail = bl2->tail; bl->head = bl2->head; } static inline struct bio *bio_list_peek(struct bio_list *bl) { return bl->head; } static inline struct bio *bio_list_pop(struct bio_list *bl) { struct bio *bio = bl->head; if (bio) { bl->head = bl->head->bi_next; if (!bl->head) bl->tail = NULL; bio->bi_next = NULL; } return bio; } static inline struct bio *bio_list_get(struct bio_list *bl) { struct bio *bio = bl->head; bl->head = bl->tail = NULL; return bio; } /* * Increment chain count for the bio. Make sure the CHAIN flag update * is visible before the raised count. */ static inline void bio_inc_remaining(struct bio *bio) { bio_set_flag(bio, BIO_CHAIN); smp_mb__before_atomic(); atomic_inc(&bio->__bi_remaining); } /* * bio_set is used to allow other portions of the IO system to * allocate their own private memory pools for bio and iovec structures. * These memory pools in turn all allocate from the bio_slab * and the bvec_slabs[]. */ #define BIO_POOL_SIZE 2 struct bio_set { struct kmem_cache *bio_slab; unsigned int front_pad; /* * per-cpu bio alloc cache */ struct bio_alloc_cache __percpu *cache; mempool_t bio_pool; mempool_t bvec_pool; unsigned int back_pad; /* * Deadlock avoidance for stacking block drivers: see comments in * bio_alloc_bioset() for details */ spinlock_t rescue_lock; struct bio_list rescue_list; struct work_struct rescue_work; struct workqueue_struct *rescue_workqueue; /* * Hot un-plug notifier for the per-cpu cache, if used */ struct hlist_node cpuhp_dead; }; static inline bool bioset_initialized(struct bio_set *bs) { return bs->bio_slab != NULL; } static inline void bio_clear_polled(struct bio *bio) { bio->bi_opf &= ~REQ_POLLED; } /** * bio_is_zone_append - is this a zone append bio? * @bio: bio to check * * Check if @bio is a zone append operation. Core block layer code and end_io * handlers must use this instead of an open coded REQ_OP_ZONE_APPEND check * because the block layer can rewrite REQ_OP_ZONE_APPEND to REQ_OP_WRITE if * it is not natively supported. */ static inline bool bio_is_zone_append(struct bio *bio) { if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) return false; return bio_op(bio) == REQ_OP_ZONE_APPEND || bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); } struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); struct bio *blk_alloc_discard_bio(struct block_device *bdev, sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask); #endif /* __LINUX_BIO_H */ |
| 4 2 5 2 7 1 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * TCPv6 GSO/GRO support */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> #include <net/inet6_hashtables.h> #include <net/gro.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, struct tcphdr *th) { #if IS_ENABLED(CONFIG_IPV6) const struct ipv6hdr *hdr; struct sk_buff *p; struct sock *sk; struct net *net; int iif, sdif; p = tcp_gro_lookup(head, th); if (p) { NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; return; } inet6_get_iif_sdif(skb, &iif, &sdif); hdr = skb_gro_network_header(skb); net = dev_net_rcu(skb->dev); sk = __inet6_lookup_established(net, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), iif, sdif); NAPI_GRO_CB(skb)->is_flist = !sk; if (sk) sock_gen_put(sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ } static __always_inline struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct tcphdr *th; /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, ip6_gro_compute_pseudo)) goto flush; th = tcp_gro_pull_header(skb); if (!th) goto flush; if (unlikely(skb->dev->features & NETIF_F_GRO_FRAGLIST)) tcp6_check_fraglist_gro(head, skb, th); return tcp_gro_receive(head, skb, th); flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } static __always_inline int tcp6_gro_complete(struct sk_buff *skb, int thoff) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset); struct tcphdr *th = tcp_hdr(skb); if (unlikely(NAPI_GRO_CB(skb)->is_flist)) { skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV6; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; tcp_gro_complete(skb); return 0; } static void __tcpv6_gso_segment_csum(struct sk_buff *seg, struct in6_addr *oldip, const struct in6_addr *newip, __be16 *oldport, __be16 newport) { struct tcphdr *th = tcp_hdr(seg); if (!ipv6_addr_equal(oldip, newip)) { inet_proto_csum_replace16(&th->check, seg, oldip->s6_addr32, newip->s6_addr32, true); *oldip = *newip; } if (*oldport == newport) return; inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false); *oldport = newport; } static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs) { const struct tcphdr *th; const struct ipv6hdr *iph; struct sk_buff *seg; struct tcphdr *th2; struct ipv6hdr *iph2; seg = segs; th = tcp_hdr(seg); iph = ipv6_hdr(seg); th2 = tcp_hdr(seg->next); iph2 = ipv6_hdr(seg->next); if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) && ipv6_addr_equal(&iph->saddr, &iph2->saddr) && ipv6_addr_equal(&iph->daddr, &iph2->daddr)) return segs; while ((seg = seg->next)) { th2 = tcp_hdr(seg); iph2 = ipv6_hdr(seg); __tcpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &th2->source, th->source); __tcpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &th2->dest, th->dest); } return segs; } static struct sk_buff *__tcp6_gso_segment_list(struct sk_buff *skb, netdev_features_t features) { skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); if (IS_ERR(skb)) return skb; return __tcpv6_gso_segment_list_csum(skb); } static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct tcphdr *th; if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL); if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) { struct tcphdr *th = tcp_hdr(skb); if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) && !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) return __tcp6_gso_segment_list(skb, features); skb->ip_summed = CHECKSUM_NONE; } if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); /* Set up pseudo header, usually expect stack to have done * this. */ th->check = 0; skb->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); } return tcp_gso_segment(skb, features); } int __init tcpv6_offload_init(void) { net_hotdata.tcpv6_offload = (struct net_offload) { .callbacks = { .gso_segment = tcp6_gso_segment, .gro_receive = tcp6_gro_receive, .gro_complete = tcp6_gro_complete, }, }; return inet6_add_offload(&net_hotdata.tcpv6_offload, IPPROTO_TCP); } |
| 3 44 42 2 16 23 51 4 4 48 46 23 23 4 3 10 13 1 3 1 58 5 55 2 52 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 | // SPDX-License-Identifier: GPL-2.0-only /* * kexec.c - kexec_load system call * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/security.h> #include <linux/kexec.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/syscalls.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include "kexec_internal.h" static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, unsigned long nr_segments, struct kexec_segment *segments, unsigned long flags) { int ret; struct kimage *image; bool kexec_on_panic = flags & KEXEC_ON_CRASH; #ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Verify we have a valid entry point */ if ((entry < phys_to_boot_phys(crashk_res.start)) || (entry > phys_to_boot_phys(crashk_res.end))) return -EADDRNOTAVAIL; } #endif /* Allocate and initialize a controlling structure */ image = do_kimage_alloc_init(); if (!image) return -ENOMEM; image->start = entry; image->nr_segments = nr_segments; memcpy(image->segment, segments, nr_segments * sizeof(*segments)); #ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Enable special crash kernel control page alloc policy. */ image->control_page = crashk_res.start; image->type = KEXEC_TYPE_CRASH; } #endif ret = sanity_check_segment_list(image); if (ret) goto out_free_image; /* * Find a location for the control code buffer, and add it * the vector of segments so that it's pages will also be * counted as destination pages. */ ret = -ENOMEM; image->control_code_page = kimage_alloc_control_pages(image, get_order(KEXEC_CONTROL_PAGE_SIZE)); if (!image->control_code_page) { pr_err("Could not allocate control_code_buffer\n"); goto out_free_image; } if (!kexec_on_panic) { image->swap_page = kimage_alloc_control_pages(image, 0); if (!image->swap_page) { pr_err("Could not allocate swap buffer\n"); goto out_free_control_pages; } } *rimage = image; return 0; out_free_control_pages: kimage_free_page_list(&image->control_pages); out_free_image: kfree(image); return ret; } static int do_kexec_load(unsigned long entry, unsigned long nr_segments, struct kexec_segment *segments, unsigned long flags) { struct kimage **dest_image, *image; unsigned long i; int ret; /* * Because we write directly to the reserved memory region when loading * crash kernels we need a serialization here to prevent multiple crash * kernels from attempting to load simultaneously. */ if (!kexec_trylock()) return -EBUSY; #ifdef CONFIG_CRASH_DUMP if (flags & KEXEC_ON_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); } else #endif dest_image = &kexec_image; if (nr_segments == 0) { /* Uninstall image */ kimage_free(xchg(dest_image, NULL)); ret = 0; goto out_unlock; } if (flags & KEXEC_ON_CRASH) { /* * Loading another kernel to switch to if this one * crashes. Free any current crash dump kernel before * we corrupt it. */ kimage_free(xchg(&kexec_crash_image, NULL)); } ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags); if (ret) goto out_unlock; if (flags & KEXEC_PRESERVE_CONTEXT) image->preserve_context = 1; #ifdef CONFIG_CRASH_HOTPLUG if ((flags & KEXEC_ON_CRASH) && arch_crash_hotplug_support(image, flags)) image->hotplug_support = 1; #endif ret = machine_kexec_prepare(image); if (ret) goto out; /* * Some architecture(like S390) may touch the crash memory before * machine_kexec_prepare(), we must copy vmcoreinfo data after it. */ ret = kimage_crash_copy_vmcoreinfo(image); if (ret) goto out; for (i = 0; i < nr_segments; i++) { ret = kimage_load_segment(image, i); if (ret) goto out; } kimage_terminate(image); ret = machine_kexec_post_load(image); if (ret) goto out; /* Install the new kernel and uninstall the old */ image = xchg(dest_image, image); out: #ifdef CONFIG_CRASH_DUMP if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); #endif kimage_free(image); out_unlock: kexec_unlock(); return ret; } /* * Exec Kernel system call: for obvious reasons only root may call it. * * This call breaks up into three pieces. * - A generic part which loads the new kernel from the current * address space, and very carefully places the data in the * allocated pages. * * - A generic part that interacts with the kernel and tells all of * the devices to shut down. Preventing on-going dmas, and placing * the devices in a consistent state so a later kernel can * reinitialize them. * * - A machine specific part that includes the syscall number * and then copies the image to it's final destination. And * jumps into the image at entry. * * kexec does not sync, or unmount filesystems so if you need * that to happen you need to do that yourself. */ static inline int kexec_load_check(unsigned long nr_segments, unsigned long flags) { int image_type = (flags & KEXEC_ON_CRASH) ? KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT; int result; /* We only trust the superuser with rebooting the system. */ if (!kexec_load_permitted(image_type)) return -EPERM; /* Permit LSMs and IMA to fail the kexec */ result = security_kernel_load_data(LOADING_KEXEC_IMAGE, false); if (result < 0) return result; /* * kexec can be used to circumvent module loading restrictions, so * prevent loading in that case */ result = security_locked_down(LOCKDOWN_KEXEC); if (result) return result; /* * Verify we have a legal set of flags * This leaves us room for future extensions. */ if ((flags & KEXEC_FLAGS) != (flags & ~KEXEC_ARCH_MASK)) return -EINVAL; /* Put an artificial cap on the number * of segments passed to kexec_load. */ if (nr_segments > KEXEC_SEGMENT_MAX) return -EINVAL; return 0; } SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, struct kexec_segment __user *, segments, unsigned long, flags) { struct kexec_segment *ksegments; unsigned long result; result = kexec_load_check(nr_segments, flags); if (result) return result; /* Verify we are on the appropriate architecture */ if (((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH) && ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) return -EINVAL; ksegments = memdup_array_user(segments, nr_segments, sizeof(ksegments[0])); if (IS_ERR(ksegments)) return PTR_ERR(ksegments); result = do_kexec_load(entry, nr_segments, ksegments, flags); kfree(ksegments); return result; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, compat_ulong_t, nr_segments, struct compat_kexec_segment __user *, segments, compat_ulong_t, flags) { struct compat_kexec_segment in; struct kexec_segment *ksegments; unsigned long i, result; result = kexec_load_check(nr_segments, flags); if (result) return result; /* Don't allow clients that don't understand the native * architecture to do anything. */ if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT) return -EINVAL; ksegments = kmalloc_objs(ksegments[0], nr_segments); if (!ksegments) return -ENOMEM; for (i = 0; i < nr_segments; i++) { result = copy_from_user(&in, &segments[i], sizeof(in)); if (result) goto fail; ksegments[i].buf = compat_ptr(in.buf); ksegments[i].bufsz = in.bufsz; ksegments[i].mem = in.mem; ksegments[i].memsz = in.memsz; } result = do_kexec_load(entry, nr_segments, ksegments, flags); fail: kfree(ksegments); return result; } #endif |
| 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * inode.c -- user mode filesystem api for usb gadget controllers * * Copyright (C) 2003-2004 David Brownell * Copyright (C) 2003 Agilent Technologies */ /* #define VERBOSE_DEBUG */ #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/pagemap.h> #include <linux/uts.h> #include <linux/wait.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/string_choices.h> #include <linux/poll.h> #include <linux/kthread.h> #include <linux/aio.h> #include <linux/uio.h> #include <linux/refcount.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/moduleparam.h> #include <linux/usb/gadgetfs.h> #include <linux/usb/gadget.h> #include <linux/usb/composite.h> /* for USB_GADGET_DELAYED_STATUS */ /* Undef helpers from linux/usb/composite.h as gadgetfs redefines them */ #undef DBG #undef ERROR #undef INFO /* * The gadgetfs API maps each endpoint to a file descriptor so that you * can use standard synchronous read/write calls for I/O. There's some * O_NONBLOCK and O_ASYNC/FASYNC style i/o support. Example usermode * drivers show how this works in practice. You can also use AIO to * eliminate I/O gaps between requests, to help when streaming data. * * Key parts that must be USB-specific are protocols defining how the * read/write operations relate to the hardware state machines. There * are two types of files. One type is for the device, implementing ep0. * The other type is for each IN or OUT endpoint. In both cases, the * user mode driver must configure the hardware before using it. * * - First, dev_config() is called when /dev/gadget/$CHIP is configured * (by writing configuration and device descriptors). Afterwards it * may serve as a source of device events, used to handle all control * requests other than basic enumeration. * * - Then, after a SET_CONFIGURATION control request, ep_config() is * called when each /dev/gadget/ep* file is configured (by writing * endpoint descriptors). Afterwards these files are used to write() * IN data or to read() OUT data. To halt the endpoint, a "wrong * direction" request is issued (like reading an IN endpoint). * * Unlike "usbfs" the only ioctl()s are for things that are rare, and maybe * not possible on all hardware. For example, precise fault handling with * respect to data left in endpoint fifos after aborted operations; or * selective clearing of endpoint halts, to implement SET_INTERFACE. */ #define DRIVER_DESC "USB Gadget filesystem" #define DRIVER_VERSION "24 Aug 2004" static const char driver_desc [] = DRIVER_DESC; static const char shortname [] = "gadgetfs"; MODULE_DESCRIPTION (DRIVER_DESC); MODULE_AUTHOR ("David Brownell"); MODULE_LICENSE ("GPL"); static int ep_open(struct inode *, struct file *); /*----------------------------------------------------------------------*/ #define GADGETFS_MAGIC 0xaee71ee7 /* /dev/gadget/$CHIP represents ep0 and the whole device */ enum ep0_state { /* DISABLED is the initial state. */ STATE_DEV_DISABLED = 0, /* Only one open() of /dev/gadget/$CHIP; only one file tracks * ep0/device i/o modes and binding to the controller. Driver * must always write descriptors to initialize the device, then * the device becomes UNCONNECTED until enumeration. */ STATE_DEV_OPENED, /* From then on, ep0 fd is in either of two basic modes: * - (UN)CONNECTED: read usb_gadgetfs_event(s) from it * - SETUP: read/write will transfer control data and succeed; * or if "wrong direction", performs protocol stall */ STATE_DEV_UNCONNECTED, STATE_DEV_CONNECTED, STATE_DEV_SETUP, /* UNBOUND means the driver closed ep0, so the device won't be * accessible again (DEV_DISABLED) until all fds are closed. */ STATE_DEV_UNBOUND, }; /* enough for the whole queue: most events invalidate others */ #define N_EVENT 5 #define RBUF_SIZE 256 struct dev_data { spinlock_t lock; refcount_t count; int udc_usage; enum ep0_state state; /* P: lock */ struct usb_gadgetfs_event event [N_EVENT]; unsigned ev_next; struct fasync_struct *fasync; u8 current_config; /* drivers reading ep0 MUST handle control requests (SETUP) * reported that way; else the host will time out. */ unsigned usermode_setup : 1, setup_in : 1, setup_can_stall : 1, setup_out_ready : 1, setup_out_error : 1, setup_abort : 1, gadget_registered : 1; unsigned setup_wLength; /* the rest is basically write-once */ struct usb_config_descriptor *config, *hs_config; struct usb_device_descriptor *dev; struct usb_request *req; struct usb_gadget *gadget; struct list_head epfiles; void *buf; wait_queue_head_t wait; struct super_block *sb; /* except this scratch i/o buffer for ep0 */ u8 rbuf[RBUF_SIZE]; }; static inline void get_dev (struct dev_data *data) { refcount_inc (&data->count); } static void put_dev (struct dev_data *data) { if (likely (!refcount_dec_and_test (&data->count))) return; /* needs no more cleanup */ BUG_ON (waitqueue_active (&data->wait)); kfree (data); } static struct dev_data *dev_new (void) { struct dev_data *dev; dev = kzalloc_obj(*dev); if (!dev) return NULL; dev->state = STATE_DEV_DISABLED; refcount_set (&dev->count, 1); spin_lock_init (&dev->lock); INIT_LIST_HEAD (&dev->epfiles); init_waitqueue_head (&dev->wait); return dev; } /*----------------------------------------------------------------------*/ /* other /dev/gadget/$ENDPOINT files represent endpoints */ enum ep_state { STATE_EP_DISABLED = 0, STATE_EP_READY, STATE_EP_ENABLED, STATE_EP_UNBOUND, }; struct ep_data { struct mutex lock; enum ep_state state; refcount_t count; struct dev_data *dev; /* must hold dev->lock before accessing ep or req */ struct usb_ep *ep; struct usb_request *req; ssize_t status; char name [16]; struct usb_endpoint_descriptor desc, hs_desc; struct list_head epfiles; wait_queue_head_t wait; }; static inline void get_ep (struct ep_data *data) { refcount_inc (&data->count); } static void put_ep (struct ep_data *data) { if (likely (!refcount_dec_and_test (&data->count))) return; put_dev (data->dev); /* needs no more cleanup */ BUG_ON (!list_empty (&data->epfiles)); BUG_ON (waitqueue_active (&data->wait)); kfree (data); } /*----------------------------------------------------------------------*/ /* most "how to use the hardware" policy choices are in userspace: * mapping endpoint roles (which the driver needs) to the capabilities * which the usb controller has. most of those capabilities are exposed * implicitly, starting with the driver name and then endpoint names. */ static const char *CHIP; static DEFINE_MUTEX(sb_mutex); /* Serialize superblock operations */ /*----------------------------------------------------------------------*/ /* NOTE: don't use dev_printk calls before binding to the gadget * at the end of ep0 configuration, or after unbind. */ /* too wordy: dev_printk(level , &(d)->gadget->dev , fmt , ## args) */ #define xprintk(d,level,fmt,args...) \ printk(level "%s: " fmt , shortname , ## args) #ifdef DEBUG #define DBG(dev,fmt,args...) \ xprintk(dev , KERN_DEBUG , fmt , ## args) #else #define DBG(dev,fmt,args...) \ do { } while (0) #endif /* DEBUG */ #ifdef VERBOSE_DEBUG #define VDEBUG DBG #else #define VDEBUG(dev,fmt,args...) \ do { } while (0) #endif /* DEBUG */ #define ERROR(dev,fmt,args...) \ xprintk(dev , KERN_ERR , fmt , ## args) #define INFO(dev,fmt,args...) \ xprintk(dev , KERN_INFO , fmt , ## args) /*----------------------------------------------------------------------*/ /* SYNCHRONOUS ENDPOINT OPERATIONS (bulk/intr/iso) * * After opening, configure non-control endpoints. Then use normal * stream read() and write() requests; and maybe ioctl() to get more * precise FIFO status when recovering from cancellation. */ static void epio_complete (struct usb_ep *ep, struct usb_request *req) { struct ep_data *epdata = ep->driver_data; if (!req->context) return; if (req->status) epdata->status = req->status; else epdata->status = req->actual; complete ((struct completion *)req->context); } /* tasklock endpoint, returning when it's connected. * still need dev->lock to use epdata->ep. */ static int get_ready_ep (unsigned f_flags, struct ep_data *epdata, bool is_write) { int val; if (f_flags & O_NONBLOCK) { if (!mutex_trylock(&epdata->lock)) goto nonblock; if (epdata->state != STATE_EP_ENABLED && (!is_write || epdata->state != STATE_EP_READY)) { mutex_unlock(&epdata->lock); nonblock: val = -EAGAIN; } else val = 0; return val; } val = mutex_lock_interruptible(&epdata->lock); if (val < 0) return val; switch (epdata->state) { case STATE_EP_ENABLED: return 0; case STATE_EP_READY: /* not configured yet */ if (is_write) return 0; fallthrough; case STATE_EP_UNBOUND: /* clean disconnect */ break; // case STATE_EP_DISABLED: /* "can't happen" */ default: /* error! */ pr_debug ("%s: ep %p not available, state %d\n", shortname, epdata, epdata->state); } mutex_unlock(&epdata->lock); return -ENODEV; } static ssize_t ep_io (struct ep_data *epdata, void *buf, unsigned len) { DECLARE_COMPLETION_ONSTACK (done); int value; spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { struct usb_request *req = epdata->req; req->context = &done; req->complete = epio_complete; req->buf = buf; req->length = len; value = usb_ep_queue (epdata->ep, req, GFP_ATOMIC); } else value = -ENODEV; spin_unlock_irq (&epdata->dev->lock); if (likely (value == 0)) { value = wait_for_completion_interruptible(&done); if (value != 0) { spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { DBG (epdata->dev, "%s i/o interrupted\n", epdata->name); usb_ep_dequeue (epdata->ep, epdata->req); spin_unlock_irq (&epdata->dev->lock); wait_for_completion(&done); if (epdata->status == -ECONNRESET) epdata->status = -EINTR; } else { spin_unlock_irq (&epdata->dev->lock); DBG (epdata->dev, "endpoint gone\n"); wait_for_completion(&done); epdata->status = -ENODEV; } } return epdata->status; } return value; } static int ep_release (struct inode *inode, struct file *fd) { struct ep_data *data = fd->private_data; int value; value = mutex_lock_interruptible(&data->lock); if (value < 0) return value; /* clean up if this can be reopened */ if (data->state != STATE_EP_UNBOUND) { data->state = STATE_EP_DISABLED; data->desc.bDescriptorType = 0; data->hs_desc.bDescriptorType = 0; usb_ep_disable(data->ep); } mutex_unlock(&data->lock); put_ep (data); return 0; } static long ep_ioctl(struct file *fd, unsigned code, unsigned long value) { struct ep_data *data = fd->private_data; int status; if ((status = get_ready_ep (fd->f_flags, data, false)) < 0) return status; spin_lock_irq (&data->dev->lock); if (likely (data->ep != NULL)) { switch (code) { case GADGETFS_FIFO_STATUS: status = usb_ep_fifo_status (data->ep); break; case GADGETFS_FIFO_FLUSH: usb_ep_fifo_flush (data->ep); break; case GADGETFS_CLEAR_HALT: status = usb_ep_clear_halt (data->ep); break; default: status = -ENOTTY; } } else status = -ENODEV; spin_unlock_irq (&data->dev->lock); mutex_unlock(&data->lock); return status; } /*----------------------------------------------------------------------*/ /* ASYNCHRONOUS ENDPOINT I/O OPERATIONS (bulk/intr/iso) */ struct kiocb_priv { struct usb_request *req; struct ep_data *epdata; struct kiocb *iocb; struct mm_struct *mm; struct work_struct work; void *buf; struct iov_iter to; const void *to_free; unsigned actual; }; static int ep_aio_cancel(struct kiocb *iocb) { struct kiocb_priv *priv = iocb->private; struct ep_data *epdata; int value; local_irq_disable(); epdata = priv->epdata; // spin_lock(&epdata->dev->lock); if (likely(epdata && epdata->ep && priv->req)) value = usb_ep_dequeue (epdata->ep, priv->req); else value = -EINVAL; // spin_unlock(&epdata->dev->lock); local_irq_enable(); return value; } static void ep_user_copy_worker(struct work_struct *work) { struct kiocb_priv *priv = container_of(work, struct kiocb_priv, work); struct mm_struct *mm = priv->mm; struct kiocb *iocb = priv->iocb; size_t ret; kthread_use_mm(mm); ret = copy_to_iter(priv->buf, priv->actual, &priv->to); kthread_unuse_mm(mm); if (!ret) ret = -EFAULT; /* completing the iocb can drop the ctx and mm, don't touch mm after */ iocb->ki_complete(iocb, ret); kfree(priv->buf); kfree(priv->to_free); kfree(priv); } static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) { struct kiocb *iocb = req->context; struct kiocb_priv *priv = iocb->private; struct ep_data *epdata = priv->epdata; /* lock against disconnect (and ideally, cancel) */ spin_lock(&epdata->dev->lock); priv->req = NULL; priv->epdata = NULL; /* if this was a write or a read returning no data then we * don't need to copy anything to userspace, so we can * complete the aio request immediately. */ if (priv->to_free == NULL || unlikely(req->actual == 0)) { kfree(req->buf); kfree(priv->to_free); kfree(priv); iocb->private = NULL; iocb->ki_complete(iocb, req->actual ? req->actual : (long)req->status); } else { /* ep_copy_to_user() won't report both; we hide some faults */ if (unlikely(0 != req->status)) DBG(epdata->dev, "%s fault %d len %d\n", ep->name, req->status, req->actual); priv->buf = req->buf; priv->actual = req->actual; INIT_WORK(&priv->work, ep_user_copy_worker); schedule_work(&priv->work); } usb_ep_free_request(ep, req); spin_unlock(&epdata->dev->lock); put_ep(epdata); } static ssize_t ep_aio(struct kiocb *iocb, struct kiocb_priv *priv, struct ep_data *epdata, char *buf, size_t len) { struct usb_request *req; ssize_t value; iocb->private = priv; priv->iocb = iocb; kiocb_set_cancel_fn(iocb, ep_aio_cancel); get_ep(epdata); priv->epdata = epdata; priv->actual = 0; priv->mm = current->mm; /* mm teardown waits for iocbs in exit_aio() */ /* each kiocb is coupled to one usb_request, but we can't * allocate or submit those if the host disconnected. */ spin_lock_irq(&epdata->dev->lock); value = -ENODEV; if (unlikely(epdata->ep == NULL)) goto fail; req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC); value = -ENOMEM; if (unlikely(!req)) goto fail; priv->req = req; req->buf = buf; req->length = len; req->complete = ep_aio_complete; req->context = iocb; value = usb_ep_queue(epdata->ep, req, GFP_ATOMIC); if (unlikely(0 != value)) { usb_ep_free_request(epdata->ep, req); goto fail; } spin_unlock_irq(&epdata->dev->lock); return -EIOCBQUEUED; fail: spin_unlock_irq(&epdata->dev->lock); kfree(priv->to_free); kfree(priv); put_ep(epdata); return value; } static ssize_t ep_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct ep_data *epdata = file->private_data; size_t len = iov_iter_count(to); ssize_t value; char *buf; if ((value = get_ready_ep(file->f_flags, epdata, false)) < 0) return value; /* halt any endpoint by doing a "wrong direction" i/o call */ if (usb_endpoint_dir_in(&epdata->desc)) { if (usb_endpoint_xfer_isoc(&epdata->desc) || !is_sync_kiocb(iocb)) { mutex_unlock(&epdata->lock); return -EINVAL; } DBG (epdata->dev, "%s halt\n", epdata->name); spin_lock_irq(&epdata->dev->lock); if (likely(epdata->ep != NULL)) usb_ep_set_halt(epdata->ep); spin_unlock_irq(&epdata->dev->lock); mutex_unlock(&epdata->lock); return -EBADMSG; } buf = kmalloc(len, GFP_KERNEL); if (unlikely(!buf)) { mutex_unlock(&epdata->lock); return -ENOMEM; } if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); if (value >= 0 && (copy_to_iter(buf, value, to) != value)) value = -EFAULT; } else { struct kiocb_priv *priv = kzalloc_obj(*priv); value = -ENOMEM; if (!priv) goto fail; priv->to_free = dup_iter(&priv->to, to, GFP_KERNEL); if (!iter_is_ubuf(&priv->to) && !priv->to_free) { kfree(priv); goto fail; } value = ep_aio(iocb, priv, epdata, buf, len); if (value == -EIOCBQUEUED) buf = NULL; } fail: kfree(buf); mutex_unlock(&epdata->lock); return value; } static ssize_t ep_config(struct ep_data *, const char *, size_t); static ssize_t ep_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct ep_data *epdata = file->private_data; size_t len = iov_iter_count(from); bool configured; ssize_t value; char *buf; if ((value = get_ready_ep(file->f_flags, epdata, true)) < 0) return value; configured = epdata->state == STATE_EP_ENABLED; /* halt any endpoint by doing a "wrong direction" i/o call */ if (configured && !usb_endpoint_dir_in(&epdata->desc)) { if (usb_endpoint_xfer_isoc(&epdata->desc) || !is_sync_kiocb(iocb)) { mutex_unlock(&epdata->lock); return -EINVAL; } DBG (epdata->dev, "%s halt\n", epdata->name); spin_lock_irq(&epdata->dev->lock); if (likely(epdata->ep != NULL)) usb_ep_set_halt(epdata->ep); spin_unlock_irq(&epdata->dev->lock); mutex_unlock(&epdata->lock); return -EBADMSG; } buf = kmalloc(len, GFP_KERNEL); if (unlikely(!buf)) { mutex_unlock(&epdata->lock); return -ENOMEM; } if (unlikely(!copy_from_iter_full(buf, len, from))) { value = -EFAULT; goto out; } if (unlikely(!configured)) { value = ep_config(epdata, buf, len); } else if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); } else { struct kiocb_priv *priv = kzalloc_obj(*priv); value = -ENOMEM; if (priv) { value = ep_aio(iocb, priv, epdata, buf, len); if (value == -EIOCBQUEUED) buf = NULL; } } out: kfree(buf); mutex_unlock(&epdata->lock); return value; } /*----------------------------------------------------------------------*/ /* used after endpoint configuration */ static const struct file_operations ep_io_operations = { .owner = THIS_MODULE, .open = ep_open, .release = ep_release, .unlocked_ioctl = ep_ioctl, .read_iter = ep_read_iter, .write_iter = ep_write_iter, }; /* ENDPOINT INITIALIZATION * * fd = open ("/dev/gadget/$ENDPOINT", O_RDWR) * status = write (fd, descriptors, sizeof descriptors) * * That write establishes the endpoint configuration, configuring * the controller to process bulk, interrupt, or isochronous transfers * at the right maxpacket size, and so on. * * The descriptors are message type 1, identified by a host order u32 * at the beginning of what's written. Descriptor order is: full/low * speed descriptor, then optional high speed descriptor. */ static ssize_t ep_config (struct ep_data *data, const char *buf, size_t len) { struct usb_ep *ep; u32 tag; int value, length = len; if (data->state != STATE_EP_READY) { value = -EL2HLT; goto fail; } value = len; if (len < USB_DT_ENDPOINT_SIZE + 4) goto fail0; /* we might need to change message format someday */ memcpy(&tag, buf, 4); if (tag != 1) { DBG(data->dev, "config %s, bad tag %d\n", data->name, tag); goto fail0; } buf += 4; len -= 4; /* NOTE: audio endpoint extensions not accepted here; * just don't include the extra bytes. */ /* full/low speed descriptor, then high speed */ memcpy(&data->desc, buf, USB_DT_ENDPOINT_SIZE); if (data->desc.bLength != USB_DT_ENDPOINT_SIZE || data->desc.bDescriptorType != USB_DT_ENDPOINT) goto fail0; if (len != USB_DT_ENDPOINT_SIZE) { if (len != 2 * USB_DT_ENDPOINT_SIZE) goto fail0; memcpy(&data->hs_desc, buf + USB_DT_ENDPOINT_SIZE, USB_DT_ENDPOINT_SIZE); if (data->hs_desc.bLength != USB_DT_ENDPOINT_SIZE || data->hs_desc.bDescriptorType != USB_DT_ENDPOINT) { DBG(data->dev, "config %s, bad hs length or type\n", data->name); goto fail0; } } spin_lock_irq (&data->dev->lock); if (data->dev->state == STATE_DEV_UNBOUND) { value = -ENOENT; goto gone; } else { ep = data->ep; if (ep == NULL) { value = -ENODEV; goto gone; } } switch (data->dev->gadget->speed) { case USB_SPEED_LOW: case USB_SPEED_FULL: ep->desc = &data->desc; break; case USB_SPEED_HIGH: /* fails if caller didn't provide that descriptor... */ ep->desc = &data->hs_desc; break; default: DBG(data->dev, "unconnected, %s init abandoned\n", data->name); value = -EINVAL; goto gone; } value = usb_ep_enable(ep); if (value == 0) { data->state = STATE_EP_ENABLED; value = length; } gone: spin_unlock_irq (&data->dev->lock); if (value < 0) { fail: data->desc.bDescriptorType = 0; data->hs_desc.bDescriptorType = 0; } return value; fail0: value = -EINVAL; goto fail; } static int ep_open (struct inode *inode, struct file *fd) { struct ep_data *data = inode->i_private; int value = -EBUSY; if (mutex_lock_interruptible(&data->lock) != 0) return -EINTR; spin_lock_irq (&data->dev->lock); if (data->dev->state == STATE_DEV_UNBOUND) value = -ENOENT; else if (data->state == STATE_EP_DISABLED) { value = 0; data->state = STATE_EP_READY; get_ep (data); fd->private_data = data; VDEBUG (data->dev, "%s ready\n", data->name); } else DBG (data->dev, "%s state %d\n", data->name, data->state); spin_unlock_irq (&data->dev->lock); mutex_unlock(&data->lock); return value; } /*----------------------------------------------------------------------*/ /* EP0 IMPLEMENTATION can be partly in userspace. * * Drivers that use this facility receive various events, including * control requests the kernel doesn't handle. Drivers that don't * use this facility may be too simple-minded for real applications. */ static inline void ep0_readable (struct dev_data *dev) { wake_up (&dev->wait); kill_fasync (&dev->fasync, SIGIO, POLL_IN); } static void clean_req (struct usb_ep *ep, struct usb_request *req) { struct dev_data *dev = ep->driver_data; if (req->buf != dev->rbuf) { kfree(req->buf); req->buf = dev->rbuf; } req->complete = epio_complete; dev->setup_out_ready = 0; } static void ep0_complete (struct usb_ep *ep, struct usb_request *req) { struct dev_data *dev = ep->driver_data; unsigned long flags; int free = 1; /* for control OUT, data must still get to userspace */ spin_lock_irqsave(&dev->lock, flags); if (!dev->setup_in) { dev->setup_out_error = (req->status != 0); if (!dev->setup_out_error) free = 0; dev->setup_out_ready = 1; ep0_readable (dev); } /* clean up as appropriate */ if (free && req->buf != &dev->rbuf) clean_req (ep, req); req->complete = epio_complete; spin_unlock_irqrestore(&dev->lock, flags); } static int setup_req (struct usb_ep *ep, struct usb_request *req, u16 len) { struct dev_data *dev = ep->driver_data; if (dev->setup_out_ready) { DBG (dev, "ep0 request busy!\n"); return -EBUSY; } if (len > sizeof (dev->rbuf)) req->buf = kmalloc(len, GFP_ATOMIC); if (req->buf == NULL) { req->buf = dev->rbuf; return -ENOMEM; } req->complete = ep0_complete; req->length = len; req->zero = 0; return 0; } static ssize_t ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t retval; enum ep0_state state; spin_lock_irq (&dev->lock); if (dev->state <= STATE_DEV_OPENED) { retval = -EINVAL; goto done; } /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; retval = -EIDRM; goto done; } /* control DATA stage */ if ((state = dev->state) == STATE_DEV_SETUP) { if (dev->setup_in) { /* stall IN */ VDEBUG(dev, "ep0in stall\n"); (void) usb_ep_set_halt (dev->gadget->ep0); retval = -EL2HLT; dev->state = STATE_DEV_CONNECTED; } else if (len == 0) { /* ack SET_CONFIGURATION etc */ struct usb_ep *ep = dev->gadget->ep0; struct usb_request *req = dev->req; if ((retval = setup_req (ep, req, 0)) == 0) { ++dev->udc_usage; spin_unlock_irq (&dev->lock); retval = usb_ep_queue (ep, req, GFP_KERNEL); spin_lock_irq (&dev->lock); --dev->udc_usage; } dev->state = STATE_DEV_CONNECTED; /* assume that was SET_CONFIGURATION */ if (dev->current_config) { unsigned power; if (gadget_is_dualspeed(dev->gadget) && (dev->gadget->speed == USB_SPEED_HIGH)) power = dev->hs_config->bMaxPower; else power = dev->config->bMaxPower; usb_gadget_vbus_draw(dev->gadget, 2 * power); } } else { /* collect OUT data */ if ((fd->f_flags & O_NONBLOCK) != 0 && !dev->setup_out_ready) { retval = -EAGAIN; goto done; } spin_unlock_irq (&dev->lock); retval = wait_event_interruptible (dev->wait, dev->setup_out_ready != 0); /* FIXME state could change from under us */ spin_lock_irq (&dev->lock); if (retval) goto done; if (dev->state != STATE_DEV_SETUP) { retval = -ECANCELED; goto done; } dev->state = STATE_DEV_CONNECTED; if (dev->setup_out_error) retval = -EIO; else { len = min (len, (size_t)dev->req->actual); ++dev->udc_usage; spin_unlock_irq(&dev->lock); if (copy_to_user (buf, dev->req->buf, len)) retval = -EFAULT; else retval = len; spin_lock_irq(&dev->lock); --dev->udc_usage; clean_req (dev->gadget->ep0, dev->req); /* NOTE userspace can't yet choose to stall */ } } goto done; } /* else normal: return event data */ if (len < sizeof dev->event [0]) { retval = -EINVAL; goto done; } len -= len % sizeof (struct usb_gadgetfs_event); dev->usermode_setup = 1; scan: /* return queued events right away */ if (dev->ev_next != 0) { unsigned i, n; n = len / sizeof (struct usb_gadgetfs_event); if (dev->ev_next < n) n = dev->ev_next; /* ep0 i/o has special semantics during STATE_DEV_SETUP */ for (i = 0; i < n; i++) { if (dev->event [i].type == GADGETFS_SETUP) { dev->state = STATE_DEV_SETUP; n = i + 1; break; } } spin_unlock_irq (&dev->lock); len = n * sizeof (struct usb_gadgetfs_event); if (copy_to_user (buf, &dev->event, len)) retval = -EFAULT; else retval = len; if (len > 0) { /* NOTE this doesn't guard against broken drivers; * concurrent ep0 readers may lose events. */ spin_lock_irq (&dev->lock); if (dev->ev_next > n) { memmove(&dev->event[0], &dev->event[n], sizeof (struct usb_gadgetfs_event) * (dev->ev_next - n)); } dev->ev_next -= n; spin_unlock_irq (&dev->lock); } return retval; } if (fd->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto done; } switch (state) { default: DBG (dev, "fail %s, state %d\n", __func__, state); retval = -ESRCH; break; case STATE_DEV_UNCONNECTED: case STATE_DEV_CONNECTED: spin_unlock_irq (&dev->lock); DBG (dev, "%s wait\n", __func__); /* wait for events */ retval = wait_event_interruptible (dev->wait, dev->ev_next != 0); if (retval < 0) return retval; spin_lock_irq (&dev->lock); goto scan; } done: spin_unlock_irq (&dev->lock); return retval; } static struct usb_gadgetfs_event * next_event (struct dev_data *dev, enum usb_gadgetfs_event_type type) { struct usb_gadgetfs_event *event; unsigned i; switch (type) { /* these events purge the queue */ case GADGETFS_DISCONNECT: if (dev->state == STATE_DEV_SETUP) dev->setup_abort = 1; fallthrough; case GADGETFS_CONNECT: dev->ev_next = 0; break; case GADGETFS_SETUP: /* previous request timed out */ case GADGETFS_SUSPEND: /* same effect */ /* these events can't be repeated */ for (i = 0; i != dev->ev_next; i++) { if (dev->event [i].type != type) continue; DBG(dev, "discard old event[%d] %d\n", i, type); dev->ev_next--; if (i == dev->ev_next) break; /* indices start at zero, for simplicity */ memmove (&dev->event [i], &dev->event [i + 1], sizeof (struct usb_gadgetfs_event) * (dev->ev_next - i)); } break; default: BUG (); } VDEBUG(dev, "event[%d] = %d\n", dev->ev_next, type); event = &dev->event [dev->ev_next++]; BUG_ON (dev->ev_next > N_EVENT); memset (event, 0, sizeof *event); event->type = type; return event; } static ssize_t ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t retval = -ESRCH; /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; retval = -EIDRM; /* data and/or status stage for control request */ } else if (dev->state == STATE_DEV_SETUP) { len = min_t(size_t, len, dev->setup_wLength); if (dev->setup_in) { retval = setup_req (dev->gadget->ep0, dev->req, len); if (retval == 0) { dev->state = STATE_DEV_CONNECTED; ++dev->udc_usage; spin_unlock_irq (&dev->lock); if (copy_from_user (dev->req->buf, buf, len)) retval = -EFAULT; else { if (len < dev->setup_wLength) dev->req->zero = 1; retval = usb_ep_queue ( dev->gadget->ep0, dev->req, GFP_KERNEL); } spin_lock_irq(&dev->lock); --dev->udc_usage; if (retval < 0) { clean_req (dev->gadget->ep0, dev->req); } else retval = len; return retval; } /* can stall some OUT transfers */ } else if (dev->setup_can_stall) { VDEBUG(dev, "ep0out stall\n"); (void) usb_ep_set_halt (dev->gadget->ep0); retval = -EL2HLT; dev->state = STATE_DEV_CONNECTED; } else { DBG(dev, "bogus ep0out stall!\n"); } } else DBG (dev, "fail %s, state %d\n", __func__, dev->state); return retval; } static int ep0_fasync (int f, struct file *fd, int on) { struct dev_data *dev = fd->private_data; // caller must F_SETOWN before signal delivery happens VDEBUG(dev, "%s %s\n", __func__, str_on_off(on)); return fasync_helper (f, fd, on, &dev->fasync); } static struct usb_gadget_driver gadgetfs_driver; static int dev_release (struct inode *inode, struct file *fd) { struct dev_data *dev = fd->private_data; /* closing ep0 === shutdown all */ if (dev->gadget_registered) { usb_gadget_unregister_driver (&gadgetfs_driver); dev->gadget_registered = false; } /* at this point "good" hardware has disconnected the * device from USB; the host won't see it any more. * alternatively, all host requests will time out. */ kfree (dev->buf); dev->buf = NULL; /* other endpoints were all decoupled from this device */ spin_lock_irq(&dev->lock); dev->state = STATE_DEV_DISABLED; spin_unlock_irq(&dev->lock); put_dev (dev); return 0; } static __poll_t ep0_poll (struct file *fd, poll_table *wait) { struct dev_data *dev = fd->private_data; __poll_t mask = 0; if (dev->state <= STATE_DEV_OPENED) return DEFAULT_POLLMASK; poll_wait(fd, &dev->wait, wait); spin_lock_irq(&dev->lock); /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; mask = EPOLLHUP; goto out; } if (dev->state == STATE_DEV_SETUP) { if (dev->setup_in || dev->setup_can_stall) mask = EPOLLOUT; } else { if (dev->ev_next != 0) mask = EPOLLIN; } out: spin_unlock_irq(&dev->lock); return mask; } static long gadget_dev_ioctl (struct file *fd, unsigned code, unsigned long value) { struct dev_data *dev = fd->private_data; struct usb_gadget *gadget = dev->gadget; long ret = -ENOTTY; spin_lock_irq(&dev->lock); if (dev->state == STATE_DEV_OPENED || dev->state == STATE_DEV_UNBOUND) { /* Not bound to a UDC */ } else if (gadget->ops->ioctl) { ++dev->udc_usage; spin_unlock_irq(&dev->lock); ret = gadget->ops->ioctl (gadget, code, value); spin_lock_irq(&dev->lock); --dev->udc_usage; } spin_unlock_irq(&dev->lock); return ret; } /*----------------------------------------------------------------------*/ /* The in-kernel gadget driver handles most ep0 issues, in particular * enumerating the single configuration (as provided from user space). * * Unrecognized ep0 requests may be handled in user space. */ static void make_qualifier (struct dev_data *dev) { struct usb_qualifier_descriptor qual; struct usb_device_descriptor *desc; qual.bLength = sizeof qual; qual.bDescriptorType = USB_DT_DEVICE_QUALIFIER; qual.bcdUSB = cpu_to_le16 (0x0200); desc = dev->dev; qual.bDeviceClass = desc->bDeviceClass; qual.bDeviceSubClass = desc->bDeviceSubClass; qual.bDeviceProtocol = desc->bDeviceProtocol; /* assumes ep0 uses the same value for both speeds ... */ qual.bMaxPacketSize0 = dev->gadget->ep0->maxpacket; qual.bNumConfigurations = 1; qual.bRESERVED = 0; memcpy (dev->rbuf, &qual, sizeof qual); } static int config_buf (struct dev_data *dev, u8 type, unsigned index) { int len; int hs = 0; /* only one configuration */ if (index > 0) return -EINVAL; if (gadget_is_dualspeed(dev->gadget)) { hs = (dev->gadget->speed == USB_SPEED_HIGH); if (type == USB_DT_OTHER_SPEED_CONFIG) hs = !hs; } if (hs) { dev->req->buf = dev->hs_config; len = le16_to_cpu(dev->hs_config->wTotalLength); } else { dev->req->buf = dev->config; len = le16_to_cpu(dev->config->wTotalLength); } ((u8 *)dev->req->buf) [1] = type; return len; } static int gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) { struct dev_data *dev = get_gadget_data (gadget); struct usb_request *req = dev->req; int value = -EOPNOTSUPP; struct usb_gadgetfs_event *event; u16 w_value = le16_to_cpu(ctrl->wValue); u16 w_length = le16_to_cpu(ctrl->wLength); if (w_length > RBUF_SIZE) { if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(RBUF_SIZE); w_length = RBUF_SIZE; } else { return value; } } spin_lock (&dev->lock); dev->setup_abort = 0; if (dev->state == STATE_DEV_UNCONNECTED) { if (gadget_is_dualspeed(gadget) && gadget->speed == USB_SPEED_HIGH && dev->hs_config == NULL) { spin_unlock(&dev->lock); ERROR (dev, "no high speed config??\n"); return -EINVAL; } dev->state = STATE_DEV_CONNECTED; INFO (dev, "connected\n"); event = next_event (dev, GADGETFS_CONNECT); event->u.speed = gadget->speed; ep0_readable (dev); /* host may have given up waiting for response. we can miss control * requests handled lower down (device/endpoint status and features); * then ep0_{read,write} will report the wrong status. controller * driver will have aborted pending i/o. */ } else if (dev->state == STATE_DEV_SETUP) dev->setup_abort = 1; req->buf = dev->rbuf; req->context = NULL; switch (ctrl->bRequest) { case USB_REQ_GET_DESCRIPTOR: if (ctrl->bRequestType != USB_DIR_IN) goto unrecognized; switch (w_value >> 8) { case USB_DT_DEVICE: value = min (w_length, (u16) sizeof *dev->dev); dev->dev->bMaxPacketSize0 = dev->gadget->ep0->maxpacket; req->buf = dev->dev; break; case USB_DT_DEVICE_QUALIFIER: if (!dev->hs_config) break; value = min (w_length, (u16) sizeof (struct usb_qualifier_descriptor)); make_qualifier (dev); break; case USB_DT_OTHER_SPEED_CONFIG: case USB_DT_CONFIG: value = config_buf (dev, w_value >> 8, w_value & 0xff); if (value >= 0) value = min (w_length, (u16) value); break; case USB_DT_STRING: goto unrecognized; default: // all others are errors break; } break; /* currently one config, two speeds */ case USB_REQ_SET_CONFIGURATION: if (ctrl->bRequestType != 0) goto unrecognized; if (0 == (u8) w_value) { value = 0; dev->current_config = 0; usb_gadget_vbus_draw(gadget, 8 /* mA */ ); // user mode expected to disable endpoints } else { u8 config, power; if (gadget_is_dualspeed(gadget) && gadget->speed == USB_SPEED_HIGH) { config = dev->hs_config->bConfigurationValue; power = dev->hs_config->bMaxPower; } else { config = dev->config->bConfigurationValue; power = dev->config->bMaxPower; } if (config == (u8) w_value) { value = 0; dev->current_config = config; usb_gadget_vbus_draw(gadget, 2 * power); } } /* report SET_CONFIGURATION like any other control request, * except that usermode may not stall this. the next * request mustn't be allowed start until this finishes: * endpoints and threads set up, etc. * * NOTE: older PXA hardware (before PXA 255: without UDCCFR) * has bad/racey automagic that prevents synchronizing here. * even kernel mode drivers often miss them. */ if (value == 0) { INFO (dev, "configuration #%d\n", dev->current_config); usb_gadget_set_state(gadget, USB_STATE_CONFIGURED); if (dev->usermode_setup) { dev->setup_can_stall = 0; goto delegate; } } break; #ifndef CONFIG_USB_PXA25X /* PXA automagically handles this request too */ case USB_REQ_GET_CONFIGURATION: if (ctrl->bRequestType != 0x80) goto unrecognized; *(u8 *)req->buf = dev->current_config; value = min (w_length, (u16) 1); break; #endif default: unrecognized: VDEBUG (dev, "%s req%02x.%02x v%04x i%04x l%d\n", dev->usermode_setup ? "delegate" : "fail", ctrl->bRequestType, ctrl->bRequest, w_value, le16_to_cpu(ctrl->wIndex), w_length); /* if there's an ep0 reader, don't stall */ if (dev->usermode_setup) { dev->setup_can_stall = 1; delegate: dev->setup_in = (ctrl->bRequestType & USB_DIR_IN) ? 1 : 0; dev->setup_wLength = w_length; dev->setup_out_ready = 0; dev->setup_out_error = 0; /* read DATA stage for OUT right away */ if (unlikely (!dev->setup_in && w_length)) { value = setup_req (gadget->ep0, dev->req, w_length); if (value < 0) break; ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, dev->req, GFP_KERNEL); spin_lock (&dev->lock); --dev->udc_usage; if (value < 0) { clean_req (gadget->ep0, dev->req); break; } /* we can't currently stall these */ dev->setup_can_stall = 0; } /* state changes when reader collects event */ event = next_event (dev, GADGETFS_SETUP); event->u.setup = *ctrl; ep0_readable (dev); spin_unlock (&dev->lock); /* * Return USB_GADGET_DELAYED_STATUS as a workaround to * stop some UDC drivers (e.g. dwc3) from automatically * proceeding with the status stage for 0-length * transfers. * Should be removed once all UDC drivers are fixed to * always delay the status stage until a response is * queued to EP0. */ return w_length == 0 ? USB_GADGET_DELAYED_STATUS : 0; } } /* proceed with data transfer and status phases? */ if (value >= 0 && dev->state != STATE_DEV_SETUP) { req->length = value; req->zero = value < w_length; ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL); spin_lock(&dev->lock); --dev->udc_usage; spin_unlock(&dev->lock); if (value < 0) { DBG (dev, "ep_queue --> %d\n", value); req->status = 0; } return value; } /* device stalls when value < 0 */ spin_unlock (&dev->lock); return value; } static void destroy_ep_files (struct dev_data *dev) { DBG (dev, "%s %d\n", __func__, dev->state); /* dev->state must prevent interference */ spin_lock_irq (&dev->lock); while (!list_empty(&dev->epfiles)) { struct ep_data *ep; /* break link to FS */ ep = list_first_entry (&dev->epfiles, struct ep_data, epfiles); list_del_init (&ep->epfiles); spin_unlock_irq (&dev->lock); /* break link to controller */ mutex_lock(&ep->lock); if (ep->state == STATE_EP_ENABLED) (void) usb_ep_disable (ep->ep); ep->state = STATE_EP_UNBOUND; usb_ep_free_request (ep->ep, ep->req); ep->ep = NULL; mutex_unlock(&ep->lock); wake_up (&ep->wait); /* break link to dcache */ simple_remove_by_name(dev->sb->s_root, ep->name, NULL); put_ep (ep); spin_lock_irq (&dev->lock); } spin_unlock_irq (&dev->lock); } static int gadgetfs_create_file (struct super_block *sb, char const *name, void *data, const struct file_operations *fops); static int activate_ep_files (struct dev_data *dev) { struct usb_ep *ep; struct ep_data *data; int err; gadget_for_each_ep (ep, dev->gadget) { data = kzalloc_obj(*data); if (!data) goto enomem0; data->state = STATE_EP_DISABLED; mutex_init(&data->lock); init_waitqueue_head (&data->wait); strscpy(data->name, ep->name); refcount_set (&data->count, 1); data->dev = dev; get_dev (dev); data->ep = ep; ep->driver_data = data; data->req = usb_ep_alloc_request (ep, GFP_KERNEL); if (!data->req) goto enomem1; err = gadgetfs_create_file (dev->sb, data->name, data, &ep_io_operations); if (err) goto enomem2; list_add_tail (&data->epfiles, &dev->epfiles); } return 0; enomem2: usb_ep_free_request (ep, data->req); enomem1: put_dev (dev); kfree (data); enomem0: DBG (dev, "%s enomem\n", __func__); destroy_ep_files (dev); return -ENOMEM; } static void gadgetfs_unbind (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); DBG (dev, "%s\n", __func__); spin_lock_irq (&dev->lock); dev->state = STATE_DEV_UNBOUND; while (dev->udc_usage > 0) { spin_unlock_irq(&dev->lock); usleep_range(1000, 2000); spin_lock_irq(&dev->lock); } spin_unlock_irq (&dev->lock); destroy_ep_files (dev); gadget->ep0->driver_data = NULL; set_gadget_data (gadget, NULL); /* we've already been disconnected ... no i/o is active */ if (dev->req) usb_ep_free_request (gadget->ep0, dev->req); DBG (dev, "%s done\n", __func__); put_dev (dev); } static struct dev_data *the_device; static int gadgetfs_bind(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { struct dev_data *dev = the_device; if (!dev) return -ESRCH; if (0 != strcmp (CHIP, gadget->name)) { pr_err("%s expected %s controller not %s\n", shortname, CHIP, gadget->name); return -ENODEV; } set_gadget_data (gadget, dev); dev->gadget = gadget; gadget->ep0->driver_data = dev; /* preallocate control response and buffer */ dev->req = usb_ep_alloc_request (gadget->ep0, GFP_KERNEL); if (!dev->req) goto enomem; dev->req->context = NULL; dev->req->complete = epio_complete; if (activate_ep_files (dev) < 0) goto enomem; INFO (dev, "bound to %s driver\n", gadget->name); spin_lock_irq(&dev->lock); dev->state = STATE_DEV_UNCONNECTED; spin_unlock_irq(&dev->lock); get_dev (dev); return 0; enomem: gadgetfs_unbind (gadget); return -ENOMEM; } static void gadgetfs_disconnect (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); unsigned long flags; spin_lock_irqsave (&dev->lock, flags); if (dev->state == STATE_DEV_UNCONNECTED) goto exit; dev->state = STATE_DEV_UNCONNECTED; INFO (dev, "disconnected\n"); next_event (dev, GADGETFS_DISCONNECT); ep0_readable (dev); exit: spin_unlock_irqrestore (&dev->lock, flags); } static void gadgetfs_suspend (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); unsigned long flags; INFO (dev, "suspended from state %d\n", dev->state); spin_lock_irqsave(&dev->lock, flags); switch (dev->state) { case STATE_DEV_SETUP: // VERY odd... host died?? case STATE_DEV_CONNECTED: case STATE_DEV_UNCONNECTED: next_event (dev, GADGETFS_SUSPEND); ep0_readable (dev); fallthrough; default: break; } spin_unlock_irqrestore(&dev->lock, flags); } static struct usb_gadget_driver gadgetfs_driver = { .function = (char *) driver_desc, .bind = gadgetfs_bind, .unbind = gadgetfs_unbind, .setup = gadgetfs_setup, .reset = gadgetfs_disconnect, .disconnect = gadgetfs_disconnect, .suspend = gadgetfs_suspend, .driver = { .name = shortname, }, }; /*----------------------------------------------------------------------*/ /* DEVICE INITIALIZATION * * fd = open ("/dev/gadget/$CHIP", O_RDWR) * status = write (fd, descriptors, sizeof descriptors) * * That write establishes the device configuration, so the kernel can * bind to the controller ... guaranteeing it can handle enumeration * at all necessary speeds. Descriptor order is: * * . message tag (u32, host order) ... for now, must be zero; it * would change to support features like multi-config devices * . full/low speed config ... all wTotalLength bytes (with interface, * class, altsetting, endpoint, and other descriptors) * . high speed config ... all descriptors, for high speed operation; * this one's optional except for high-speed hardware * . device descriptor * * Endpoints are not yet enabled. Drivers must wait until device * configuration and interface altsetting changes create * the need to configure (or unconfigure) them. * * After initialization, the device stays active for as long as that * $CHIP file is open. Events must then be read from that descriptor, * such as configuration notifications. */ static int is_valid_config(struct usb_config_descriptor *config, unsigned int total) { return config->bDescriptorType == USB_DT_CONFIG && config->bLength == USB_DT_CONFIG_SIZE && total >= USB_DT_CONFIG_SIZE && config->bConfigurationValue != 0 && (config->bmAttributes & USB_CONFIG_ATT_ONE) != 0 && (config->bmAttributes & USB_CONFIG_ATT_WAKEUP) == 0; /* FIXME if gadget->is_otg, _must_ include an otg descriptor */ /* FIXME check lengths: walk to end */ } static ssize_t dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t value, length = len; unsigned total; u32 tag; char *kbuf; spin_lock_irq(&dev->lock); if (dev->state > STATE_DEV_OPENED) { value = ep0_write(fd, buf, len, ptr); spin_unlock_irq(&dev->lock); return value; } spin_unlock_irq(&dev->lock); if ((len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4)) || (len > PAGE_SIZE * 4)) return -EINVAL; /* we might need to change message format someday */ if (copy_from_user (&tag, buf, 4)) return -EFAULT; if (tag != 0) return -EINVAL; buf += 4; length -= 4; kbuf = memdup_user(buf, length); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); spin_lock_irq (&dev->lock); value = -EINVAL; if (dev->buf) { spin_unlock_irq(&dev->lock); kfree(kbuf); return value; } dev->buf = kbuf; /* full or low speed config */ dev->config = (void *) kbuf; total = le16_to_cpu(dev->config->wTotalLength); if (!is_valid_config(dev->config, total) || total > length - USB_DT_DEVICE_SIZE) goto fail; kbuf += total; length -= total; /* optional high speed config */ if (kbuf [1] == USB_DT_CONFIG) { dev->hs_config = (void *) kbuf; total = le16_to_cpu(dev->hs_config->wTotalLength); if (!is_valid_config(dev->hs_config, total) || total > length - USB_DT_DEVICE_SIZE) goto fail; kbuf += total; length -= total; } else { dev->hs_config = NULL; } /* could support multiple configs, using another encoding! */ /* device descriptor (tweaked for paranoia) */ if (length != USB_DT_DEVICE_SIZE) goto fail; dev->dev = (void *)kbuf; if (dev->dev->bLength != USB_DT_DEVICE_SIZE || dev->dev->bDescriptorType != USB_DT_DEVICE || dev->dev->bNumConfigurations != 1) goto fail; dev->dev->bcdUSB = cpu_to_le16 (0x0200); /* triggers gadgetfs_bind(); then we can enumerate. */ spin_unlock_irq (&dev->lock); if (dev->hs_config) gadgetfs_driver.max_speed = USB_SPEED_HIGH; else gadgetfs_driver.max_speed = USB_SPEED_FULL; value = usb_gadget_register_driver(&gadgetfs_driver); if (value != 0) { spin_lock_irq(&dev->lock); goto fail; } else { /* at this point "good" hardware has for the first time * let the USB the host see us. alternatively, if users * unplug/replug that will clear all the error state. * * note: everything running before here was guaranteed * to choke driver model style diagnostics. from here * on, they can work ... except in cleanup paths that * kick in after the ep0 descriptor is closed. */ value = len; dev->gadget_registered = true; } return value; fail: dev->config = NULL; dev->hs_config = NULL; dev->dev = NULL; spin_unlock_irq (&dev->lock); pr_debug ("%s: %s fail %zd, %p\n", shortname, __func__, value, dev); kfree (dev->buf); dev->buf = NULL; return value; } static int gadget_dev_open (struct inode *inode, struct file *fd) { struct dev_data *dev = inode->i_private; int value = -EBUSY; spin_lock_irq(&dev->lock); if (dev->state == STATE_DEV_DISABLED) { dev->ev_next = 0; dev->state = STATE_DEV_OPENED; fd->private_data = dev; get_dev (dev); value = 0; } spin_unlock_irq(&dev->lock); return value; } static const struct file_operations ep0_operations = { .open = gadget_dev_open, .read = ep0_read, .write = dev_config, .fasync = ep0_fasync, .poll = ep0_poll, .unlocked_ioctl = gadget_dev_ioctl, .release = dev_release, }; /*----------------------------------------------------------------------*/ /* FILESYSTEM AND SUPERBLOCK OPERATIONS * * Mounting the filesystem creates a controller file, used first for * device configuration then later for event monitoring. */ /* FIXME PAM etc could set this security policy without mount options * if epfiles inherited ownership and permissons from ep0 ... */ static unsigned default_uid; static unsigned default_gid; static unsigned default_perm = S_IRUSR | S_IWUSR; module_param (default_uid, uint, 0644); module_param (default_gid, uint, 0644); module_param (default_perm, uint, 0644); static struct inode * gadgetfs_make_inode (struct super_block *sb, void *data, const struct file_operations *fops, int mode) { struct inode *inode = new_inode (sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = make_kuid(&init_user_ns, default_uid); inode->i_gid = make_kgid(&init_user_ns, default_gid); simple_inode_init_ts(inode); inode->i_private = data; inode->i_fop = fops; } return inode; } /* creates in fs root directory, so non-renamable and non-linkable. * so inode and dentry are paired, until device reconfig. */ static int gadgetfs_create_file (struct super_block *sb, char const *name, void *data, const struct file_operations *fops) { struct dentry *dentry; struct inode *inode; inode = gadgetfs_make_inode (sb, data, fops, S_IFREG | (default_perm & S_IRWXUGO)); if (!inode) return -ENOMEM; dentry = simple_start_creating(sb->s_root, name); if (IS_ERR(dentry)) { iput(inode); return PTR_ERR(dentry); } d_make_persistent(dentry, inode); simple_done_creating(dentry); return 0; } static const struct super_operations gadget_fs_operations = { .statfs = simple_statfs, .drop_inode = inode_just_drop, }; static int gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dev_data *dev; int rc; mutex_lock(&sb_mutex); if (the_device) { rc = -ESRCH; goto Done; } CHIP = usb_get_gadget_udc_name(); if (!CHIP) { rc = -ENODEV; goto Done; } /* superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = GADGETFS_MAGIC; sb->s_op = &gadget_fs_operations; sb->s_time_gran = 1; /* root inode */ inode = gadgetfs_make_inode (sb, NULL, &simple_dir_operations, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) goto Enomem; inode->i_op = &simple_dir_inode_operations; if (!(sb->s_root = d_make_root (inode))) goto Enomem; /* the ep0 file is named after the controller we expect; * user mode code can use it for sanity checks, like we do. */ dev = dev_new (); if (!dev) goto Enomem; dev->sb = sb; rc = gadgetfs_create_file(sb, CHIP, dev, &ep0_operations); if (rc) { put_dev(dev); goto Enomem; } /* other endpoint files are available after hardware setup, * from binding to a controller. */ the_device = dev; rc = 0; goto Done; Enomem: kfree(CHIP); CHIP = NULL; rc = -ENOMEM; Done: mutex_unlock(&sb_mutex); return rc; } /* "mount -t gadgetfs path /dev/gadget" ends up here */ static int gadgetfs_get_tree(struct fs_context *fc) { return get_tree_single(fc, gadgetfs_fill_super); } static const struct fs_context_operations gadgetfs_context_ops = { .get_tree = gadgetfs_get_tree, }; static int gadgetfs_init_fs_context(struct fs_context *fc) { fc->ops = &gadgetfs_context_ops; return 0; } static void gadgetfs_kill_sb (struct super_block *sb) { mutex_lock(&sb_mutex); kill_anon_super (sb); if (the_device) { put_dev (the_device); the_device = NULL; } kfree(CHIP); CHIP = NULL; mutex_unlock(&sb_mutex); } /*----------------------------------------------------------------------*/ static struct file_system_type gadgetfs_type = { .owner = THIS_MODULE, .name = shortname, .init_fs_context = gadgetfs_init_fs_context, .kill_sb = gadgetfs_kill_sb, }; MODULE_ALIAS_FS("gadgetfs"); /*----------------------------------------------------------------------*/ static int __init gadgetfs_init (void) { int status; status = register_filesystem (&gadgetfs_type); if (status == 0) pr_info ("%s: %s, version " DRIVER_VERSION "\n", shortname, driver_desc); return status; } module_init (gadgetfs_init); static void __exit gadgetfs_cleanup (void) { pr_debug ("unregister %s\n", shortname); unregister_filesystem (&gadgetfs_type); } module_exit (gadgetfs_cleanup); |
| 36 6 5 5 2 4 3 3 2 5 5 3 2 28 28 28 28 12 28 12 28 28 3 2 3 3 3 2 2 2 3 3 3 3 3 3 2 2 4 1 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 | // SPDX-License-Identifier: GPL-2.0-only /* * Power Management Quality of Service (PM QoS) support base. * * Copyright (C) 2020 Intel Corporation * * Authors: * Mark Gross <mgross@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> * * Provided here is an interface for specifying PM QoS dependencies. It allows * entities depending on QoS constraints to register their requests which are * aggregated as appropriate to produce effective constraints (target values) * that can be monitored by entities needing to respect them, either by polling * or through a built-in notification mechanism. * * In addition to the basic functionality, more specific interfaces for managing * global CPU latency QoS requests and frequency QoS requests are provided. */ /*#define DEBUG*/ #include <linux/pm_qos.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/miscdevice.h> #include <linux/string.h> #include <linux/platform_device.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/uaccess.h> #include <linux/export.h> #include <trace/events/power.h> /* * locking rule: all changes to constraints or notifiers lists * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock * held, taken with _irqsave. One lock to rule them all */ static DEFINE_SPINLOCK(pm_qos_lock); /** * pm_qos_read_value - Return the current effective constraint value. * @c: List of PM QoS constraint requests. */ s32 pm_qos_read_value(struct pm_qos_constraints *c) { return READ_ONCE(c->target_value); } static int pm_qos_get_value(struct pm_qos_constraints *c) { if (plist_head_empty(&c->list)) return c->no_constraint_value; switch (c->type) { case PM_QOS_MIN: return plist_first(&c->list)->prio; case PM_QOS_MAX: return plist_last(&c->list)->prio; default: WARN(1, "Unknown PM QoS type in %s\n", __func__); return PM_QOS_DEFAULT_VALUE; } } static void pm_qos_set_value(struct pm_qos_constraints *c, s32 value) { WRITE_ONCE(c->target_value, value); } /** * pm_qos_update_target - Update a list of PM QoS constraint requests. * @c: List of PM QoS requests. * @node: Target list entry. * @action: Action to carry out (add, update or remove). * @value: New request value for the target list entry. * * Update the given list of PM QoS constraint requests, @c, by carrying an * @action involving the @node list entry and @value on it. * * The recognized values of @action are PM_QOS_ADD_REQ (store @value in @node * and add it to the list), PM_QOS_UPDATE_REQ (remove @node from the list, store * @value in it and add it to the list again), and PM_QOS_REMOVE_REQ (remove * @node from the list, ignore @value). * * Return: 1 if the aggregate constraint value has changed, 0 otherwise. */ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, enum pm_qos_req_action action, int value) { int prev_value, curr_value, new_value; unsigned long flags; spin_lock_irqsave(&pm_qos_lock, flags); prev_value = pm_qos_get_value(c); if (value == PM_QOS_DEFAULT_VALUE) new_value = c->default_value; else new_value = value; switch (action) { case PM_QOS_REMOVE_REQ: plist_del(node, &c->list); break; case PM_QOS_UPDATE_REQ: /* * To change the list, atomically remove, reinit with new value * and add, then see if the aggregate has changed. */ plist_del(node, &c->list); fallthrough; case PM_QOS_ADD_REQ: plist_node_init(node, new_value); plist_add(node, &c->list); break; default: /* no action */ ; } curr_value = pm_qos_get_value(c); pm_qos_set_value(c, curr_value); spin_unlock_irqrestore(&pm_qos_lock, flags); trace_pm_qos_update_target(action, prev_value, curr_value); if (prev_value == curr_value) return 0; if (c->notifiers) blocking_notifier_call_chain(c->notifiers, curr_value, NULL); return 1; } /** * pm_qos_flags_remove_req - Remove device PM QoS flags request. * @pqf: Device PM QoS flags set to remove the request from. * @req: Request to remove from the set. */ static void pm_qos_flags_remove_req(struct pm_qos_flags *pqf, struct pm_qos_flags_request *req) { s32 val = 0; list_del(&req->node); list_for_each_entry(req, &pqf->list, node) val |= req->flags; pqf->effective_flags = val; } /** * pm_qos_update_flags - Update a set of PM QoS flags. * @pqf: Set of PM QoS flags to update. * @req: Request to add to the set, to modify, or to remove from the set. * @action: Action to take on the set. * @val: Value of the request to add or modify. * * Return: 1 if the aggregate constraint value has changed, 0 otherwise. */ bool pm_qos_update_flags(struct pm_qos_flags *pqf, struct pm_qos_flags_request *req, enum pm_qos_req_action action, s32 val) { unsigned long irqflags; s32 prev_value, curr_value; spin_lock_irqsave(&pm_qos_lock, irqflags); prev_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags; switch (action) { case PM_QOS_REMOVE_REQ: pm_qos_flags_remove_req(pqf, req); break; case PM_QOS_UPDATE_REQ: pm_qos_flags_remove_req(pqf, req); fallthrough; case PM_QOS_ADD_REQ: req->flags = val; INIT_LIST_HEAD(&req->node); list_add_tail(&req->node, &pqf->list); pqf->effective_flags |= val; break; default: /* no action */ ; } curr_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags; spin_unlock_irqrestore(&pm_qos_lock, irqflags); trace_pm_qos_update_flags(action, prev_value, curr_value); return prev_value != curr_value; } #ifdef CONFIG_CPU_IDLE /* Definitions related to the CPU latency QoS. */ static struct pm_qos_constraints cpu_latency_constraints = { .list = PLIST_HEAD_INIT(cpu_latency_constraints.list), .target_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE, .default_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE, .no_constraint_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE, .type = PM_QOS_MIN, }; static inline bool cpu_latency_qos_value_invalid(s32 value) { return value < 0 && value != PM_QOS_DEFAULT_VALUE; } /** * cpu_latency_qos_limit - Return current system-wide CPU latency QoS limit. */ s32 cpu_latency_qos_limit(void) { return pm_qos_read_value(&cpu_latency_constraints); } /** * cpu_latency_qos_request_active - Check the given PM QoS request. * @req: PM QoS request to check. * * Return: 'true' if @req has been added to the CPU latency QoS list, 'false' * otherwise. */ bool cpu_latency_qos_request_active(struct pm_qos_request *req) { return req->qos == &cpu_latency_constraints; } EXPORT_SYMBOL_GPL(cpu_latency_qos_request_active); static void cpu_latency_qos_apply(struct pm_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret = pm_qos_update_target(req->qos, &req->node, action, value); if (ret > 0) wake_up_all_idle_cpus(); } /** * cpu_latency_qos_add_request - Add new CPU latency QoS request. * @req: Pointer to a preallocated handle. * @value: Requested constraint value. * * Use @value to initialize the request handle pointed to by @req, insert it as * a new entry to the CPU latency QoS list and recompute the effective QoS * constraint for that list. * * Callers need to save the handle for later use in updates and removal of the * QoS request represented by it. */ void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value) { if (!req || cpu_latency_qos_value_invalid(value)) return; if (cpu_latency_qos_request_active(req)) { WARN(1, KERN_ERR "%s called for already added request\n", __func__); return; } trace_pm_qos_add_request(value); req->qos = &cpu_latency_constraints; cpu_latency_qos_apply(req, PM_QOS_ADD_REQ, value); } EXPORT_SYMBOL_GPL(cpu_latency_qos_add_request); /** * cpu_latency_qos_update_request - Modify existing CPU latency QoS request. * @req : QoS request to update. * @new_value: New requested constraint value. * * Use @new_value to update the QoS request represented by @req in the CPU * latency QoS list along with updating the effective constraint value for that * list. */ void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value) { if (!req || cpu_latency_qos_value_invalid(new_value)) return; if (!cpu_latency_qos_request_active(req)) { WARN(1, KERN_ERR "%s called for unknown object\n", __func__); return; } trace_pm_qos_update_request(new_value); if (new_value == req->node.prio) return; cpu_latency_qos_apply(req, PM_QOS_UPDATE_REQ, new_value); } EXPORT_SYMBOL_GPL(cpu_latency_qos_update_request); /** * cpu_latency_qos_remove_request - Remove existing CPU latency QoS request. * @req: QoS request to remove. * * Remove the CPU latency QoS request represented by @req from the CPU latency * QoS list along with updating the effective constraint value for that list. */ void cpu_latency_qos_remove_request(struct pm_qos_request *req) { if (!req) return; if (!cpu_latency_qos_request_active(req)) { WARN(1, KERN_ERR "%s called for unknown object\n", __func__); return; } trace_pm_qos_remove_request(PM_QOS_DEFAULT_VALUE); cpu_latency_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } EXPORT_SYMBOL_GPL(cpu_latency_qos_remove_request); /* User space interface to the CPU latency QoS via misc device. */ static int cpu_latency_qos_open(struct inode *inode, struct file *filp) { struct pm_qos_request *req; req = kzalloc_obj(*req); if (!req) return -ENOMEM; cpu_latency_qos_add_request(req, PM_QOS_DEFAULT_VALUE); filp->private_data = req; return 0; } static int cpu_latency_qos_release(struct inode *inode, struct file *filp) { struct pm_qos_request *req = filp->private_data; filp->private_data = NULL; cpu_latency_qos_remove_request(req); kfree(req); return 0; } static ssize_t cpu_latency_qos_read(struct file *filp, char __user *buf, size_t count, loff_t *f_pos) { struct pm_qos_request *req = filp->private_data; unsigned long flags; s32 value; if (!req || !cpu_latency_qos_request_active(req)) return -EINVAL; spin_lock_irqsave(&pm_qos_lock, flags); value = pm_qos_get_value(&cpu_latency_constraints); spin_unlock_irqrestore(&pm_qos_lock, flags); return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32)); } static ssize_t cpu_latency_qos_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos) { s32 value; if (count == sizeof(s32)) { if (copy_from_user(&value, buf, sizeof(s32))) return -EFAULT; } else { int ret; ret = kstrtos32_from_user(buf, count, 16, &value); if (ret) return ret; } cpu_latency_qos_update_request(filp->private_data, value); return count; } static const struct file_operations cpu_latency_qos_fops = { .write = cpu_latency_qos_write, .read = cpu_latency_qos_read, .open = cpu_latency_qos_open, .release = cpu_latency_qos_release, .llseek = noop_llseek, }; static struct miscdevice cpu_latency_qos_miscdev = { .minor = MISC_DYNAMIC_MINOR, .name = "cpu_dma_latency", .fops = &cpu_latency_qos_fops, }; #ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP /* The CPU system wakeup latency QoS. */ static struct pm_qos_constraints cpu_wakeup_latency_constraints = { .list = PLIST_HEAD_INIT(cpu_wakeup_latency_constraints.list), .target_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT, .default_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT, .no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT, .type = PM_QOS_MIN, }; /** * cpu_wakeup_latency_qos_limit - Current CPU system wakeup latency QoS limit. * * Returns the current CPU system wakeup latency QoS limit that may have been * requested by user space. */ s32 cpu_wakeup_latency_qos_limit(void) { return pm_qos_read_value(&cpu_wakeup_latency_constraints); } static int cpu_wakeup_latency_qos_open(struct inode *inode, struct file *filp) { struct pm_qos_request *req; req = kzalloc_obj(*req); if (!req) return -ENOMEM; req->qos = &cpu_wakeup_latency_constraints; pm_qos_update_target(req->qos, &req->node, PM_QOS_ADD_REQ, PM_QOS_RESUME_LATENCY_NO_CONSTRAINT); filp->private_data = req; return 0; } static int cpu_wakeup_latency_qos_release(struct inode *inode, struct file *filp) { struct pm_qos_request *req = filp->private_data; filp->private_data = NULL; pm_qos_update_target(req->qos, &req->node, PM_QOS_REMOVE_REQ, PM_QOS_RESUME_LATENCY_NO_CONSTRAINT); kfree(req); return 0; } static ssize_t cpu_wakeup_latency_qos_read(struct file *filp, char __user *buf, size_t count, loff_t *f_pos) { s32 value = pm_qos_read_value(&cpu_wakeup_latency_constraints); return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32)); } static ssize_t cpu_wakeup_latency_qos_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos) { struct pm_qos_request *req = filp->private_data; s32 value; if (count == sizeof(s32)) { if (copy_from_user(&value, buf, sizeof(s32))) return -EFAULT; } else { int ret; ret = kstrtos32_from_user(buf, count, 16, &value); if (ret) return ret; } if (value < 0) return -EINVAL; pm_qos_update_target(req->qos, &req->node, PM_QOS_UPDATE_REQ, value); return count; } static const struct file_operations cpu_wakeup_latency_qos_fops = { .open = cpu_wakeup_latency_qos_open, .release = cpu_wakeup_latency_qos_release, .read = cpu_wakeup_latency_qos_read, .write = cpu_wakeup_latency_qos_write, .llseek = noop_llseek, }; static struct miscdevice cpu_wakeup_latency_qos_miscdev = { .minor = MISC_DYNAMIC_MINOR, .name = "cpu_wakeup_latency", .fops = &cpu_wakeup_latency_qos_fops, }; #endif /* CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP */ static int __init cpu_latency_qos_init(void) { int ret; ret = misc_register(&cpu_latency_qos_miscdev); if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_latency_qos_miscdev.name); return ret; } #ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP ret = misc_register(&cpu_wakeup_latency_qos_miscdev); if (ret < 0) { pr_err("%s: %s setup failed\n", __func__, cpu_wakeup_latency_qos_miscdev.name); misc_deregister(&cpu_latency_qos_miscdev); return ret; } #endif return 0; } late_initcall(cpu_latency_qos_init); #endif /* CONFIG_CPU_IDLE */ /* Definitions related to the frequency QoS below. */ static inline bool freq_qos_value_invalid(s32 value) { return value < 0 && value != PM_QOS_DEFAULT_VALUE; } /** * freq_constraints_init - Initialize frequency QoS constraints. * @qos: Frequency QoS constraints to initialize. */ void freq_constraints_init(struct freq_constraints *qos) { struct pm_qos_constraints *c; c = &qos->min_freq; plist_head_init(&c->list); c->target_value = FREQ_QOS_MIN_DEFAULT_VALUE; c->default_value = FREQ_QOS_MIN_DEFAULT_VALUE; c->no_constraint_value = FREQ_QOS_MIN_DEFAULT_VALUE; c->type = PM_QOS_MAX; c->notifiers = &qos->min_freq_notifiers; BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers); c = &qos->max_freq; plist_head_init(&c->list); c->target_value = FREQ_QOS_MAX_DEFAULT_VALUE; c->default_value = FREQ_QOS_MAX_DEFAULT_VALUE; c->no_constraint_value = FREQ_QOS_MAX_DEFAULT_VALUE; c->type = PM_QOS_MIN; c->notifiers = &qos->max_freq_notifiers; BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers); } /** * freq_qos_read_value - Get frequency QoS constraint for a given list. * @qos: Constraints to evaluate. * @type: QoS request type. */ s32 freq_qos_read_value(struct freq_constraints *qos, enum freq_qos_req_type type) { s32 ret; switch (type) { case FREQ_QOS_MIN: ret = IS_ERR_OR_NULL(qos) ? FREQ_QOS_MIN_DEFAULT_VALUE : pm_qos_read_value(&qos->min_freq); break; case FREQ_QOS_MAX: ret = IS_ERR_OR_NULL(qos) ? FREQ_QOS_MAX_DEFAULT_VALUE : pm_qos_read_value(&qos->max_freq); break; default: WARN_ON(1); ret = 0; } return ret; } /** * freq_qos_apply - Add/modify/remove frequency QoS request. * @req: Constraint request to apply. * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. * * This is only meant to be called from inside pm_qos, not drivers. */ int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret; switch(req->type) { case FREQ_QOS_MIN: ret = pm_qos_update_target(&req->qos->min_freq, &req->pnode, action, value); break; case FREQ_QOS_MAX: ret = pm_qos_update_target(&req->qos->max_freq, &req->pnode, action, value); break; default: ret = -EINVAL; } return ret; } /** * freq_qos_add_request - Insert new frequency QoS request into a given list. * @qos: Constraints to update. * @req: Preallocated request object. * @type: Request type. * @value: Request value. * * Insert a new entry into the @qos list of requests, recompute the effective * QoS constraint value for that list and initialize the @req object. The * caller needs to save that object for later use in updates and removal. * * Return 1 if the effective constraint value has changed, 0 if the effective * constraint value has not changed, or a negative error code on failures. */ int freq_qos_add_request(struct freq_constraints *qos, struct freq_qos_request *req, enum freq_qos_req_type type, s32 value) { int ret; if (IS_ERR_OR_NULL(qos) || !req || freq_qos_value_invalid(value)) return -EINVAL; if (WARN(freq_qos_request_active(req), "%s() called for active request\n", __func__)) return -EINVAL; req->qos = qos; req->type = type; ret = freq_qos_apply(req, PM_QOS_ADD_REQ, value); if (ret < 0) { req->qos = NULL; req->type = 0; } return ret; } EXPORT_SYMBOL_GPL(freq_qos_add_request); /** * freq_qos_update_request - Modify existing frequency QoS request. * @req: Request to modify. * @new_value: New request value. * * Update an existing frequency QoS request along with the effective constraint * value for the list of requests it belongs to. * * Return 1 if the effective constraint value has changed, 0 if the effective * constraint value has not changed, or a negative error code on failures. */ int freq_qos_update_request(struct freq_qos_request *req, s32 new_value) { if (!req || freq_qos_value_invalid(new_value)) return -EINVAL; if (WARN(!freq_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (req->pnode.prio == new_value) return 0; return freq_qos_apply(req, PM_QOS_UPDATE_REQ, new_value); } EXPORT_SYMBOL_GPL(freq_qos_update_request); /** * freq_qos_remove_request - Remove frequency QoS request from its list. * @req: Request to remove. * * Remove the given frequency QoS request from the list of constraints it * belongs to and recompute the effective constraint value for that list. * * Return 1 if the effective constraint value has changed, 0 if the effective * constraint value has not changed, or a negative error code on failures. */ int freq_qos_remove_request(struct freq_qos_request *req) { int ret; if (!req) return -EINVAL; if (WARN(!freq_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; ret = freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); req->qos = NULL; req->type = 0; return ret; } EXPORT_SYMBOL_GPL(freq_qos_remove_request); /** * freq_qos_add_notifier - Add frequency QoS change notifier. * @qos: List of requests to add the notifier to. * @type: Request type. * @notifier: Notifier block to add. */ int freq_qos_add_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, struct notifier_block *notifier) { int ret; if (IS_ERR_OR_NULL(qos) || !notifier) return -EINVAL; switch (type) { case FREQ_QOS_MIN: ret = blocking_notifier_chain_register(qos->min_freq.notifiers, notifier); break; case FREQ_QOS_MAX: ret = blocking_notifier_chain_register(qos->max_freq.notifiers, notifier); break; default: WARN_ON(1); ret = -EINVAL; } return ret; } EXPORT_SYMBOL_GPL(freq_qos_add_notifier); /** * freq_qos_remove_notifier - Remove frequency QoS change notifier. * @qos: List of requests to remove the notifier from. * @type: Request type. * @notifier: Notifier block to remove. */ int freq_qos_remove_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, struct notifier_block *notifier) { int ret; if (IS_ERR_OR_NULL(qos) || !notifier) return -EINVAL; switch (type) { case FREQ_QOS_MIN: ret = blocking_notifier_chain_unregister(qos->min_freq.notifiers, notifier); break; case FREQ_QOS_MAX: ret = blocking_notifier_chain_unregister(qos->max_freq.notifiers, notifier); break; default: WARN_ON(1); ret = -EINVAL; } return ret; } EXPORT_SYMBOL_GPL(freq_qos_remove_notifier); |
| 64 64 64 64 61 8 13 13 13 3 3 13 63 24 11 13 13 13 13 13 3 2 2 4 8 61 10 4 4 61 3 15 9 10 371 362 5 69 4 63 63 63 4 3 5 53 10 55 296 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 | // SPDX-License-Identifier: GPL-2.0 /* * Contains the core associated with submission side polling of the SQ * ring, offloading submissions from the application to a kernel thread. */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/audit.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/sched/cputime.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "tctx.h" #include "napi.h" #include "cancel.h" #include "sqpoll.h" #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 #define IORING_TW_CAP_ENTRIES_VALUE 32 enum { IO_SQ_THREAD_SHOULD_STOP = 0, IO_SQ_THREAD_SHOULD_PARK, }; void io_sq_thread_unpark(struct io_sq_data *sqd) __releases(&sqd->lock) { WARN_ON_ONCE(sqpoll_task_locked(sqd) == current); /* * Do the dance but not conditional clear_bit() because it'd race with * other threads incrementing park_pending and setting the bit. */ clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); if (atomic_dec_return(&sqd->park_pending)) set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); mutex_unlock(&sqd->lock); wake_up(&sqd->wait); } void io_sq_thread_park(struct io_sq_data *sqd) __acquires(&sqd->lock) { struct task_struct *tsk; atomic_inc(&sqd->park_pending); set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); mutex_lock(&sqd->lock); tsk = sqpoll_task_locked(sqd); if (tsk) { WARN_ON_ONCE(tsk == current); wake_up_process(tsk); } } void io_sq_thread_stop(struct io_sq_data *sqd) { struct task_struct *tsk; WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)); set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); mutex_lock(&sqd->lock); tsk = sqpoll_task_locked(sqd); if (tsk) { WARN_ON_ONCE(tsk == current); wake_up_process(tsk); } mutex_unlock(&sqd->lock); wait_for_completion(&sqd->exited); } void io_put_sq_data(struct io_sq_data *sqd) { if (refcount_dec_and_test(&sqd->refs)) { WARN_ON_ONCE(atomic_read(&sqd->park_pending)); io_sq_thread_stop(sqd); kfree(sqd); } } static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd) { struct io_ring_ctx *ctx; unsigned sq_thread_idle = 0; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle); sqd->sq_thread_idle = sq_thread_idle; } void io_sq_thread_finish(struct io_ring_ctx *ctx) { struct io_sq_data *sqd = ctx->sq_data; if (sqd) { io_sq_thread_park(sqd); list_del_init(&ctx->sqd_list); io_sqd_update_thread_idle(sqd); io_sq_thread_unpark(sqd); io_put_sq_data(sqd); ctx->sq_data = NULL; } } static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) { struct io_ring_ctx *ctx_attach; struct io_sq_data *sqd; CLASS(fd, f)(p->wq_fd); if (fd_empty(f)) return ERR_PTR(-ENXIO); if (!io_is_uring_fops(fd_file(f))) return ERR_PTR(-EINVAL); ctx_attach = fd_file(f)->private_data; sqd = ctx_attach->sq_data; if (!sqd) return ERR_PTR(-EINVAL); if (sqd->task_tgid != current->tgid) return ERR_PTR(-EPERM); refcount_inc(&sqd->refs); return sqd; } static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, bool *attached) { struct io_sq_data *sqd; *attached = false; if (p->flags & IORING_SETUP_ATTACH_WQ) { sqd = io_attach_sq_data(p); if (!IS_ERR(sqd)) { *attached = true; return sqd; } /* fall through for EPERM case, setup new sqd/task */ if (PTR_ERR(sqd) != -EPERM) return sqd; } sqd = kzalloc_obj(*sqd); if (!sqd) return ERR_PTR(-ENOMEM); atomic_set(&sqd->park_pending, 0); refcount_set(&sqd->refs, 1); INIT_LIST_HEAD(&sqd->ctx_list); mutex_init(&sqd->lock); init_waitqueue_head(&sqd->wait); init_completion(&sqd->exited); return sqd; } static inline bool io_sqd_events_pending(struct io_sq_data *sqd) { return READ_ONCE(sqd->state); } struct io_sq_time { bool started; u64 usec; }; u64 io_sq_cpu_usec(struct task_struct *tsk) { u64 utime, stime; task_cputime_adjusted(tsk, &utime, &stime); do_div(stime, 1000); return stime; } static void io_sq_update_worktime(struct io_sq_data *sqd, struct io_sq_time *ist) { if (!ist->started) return; ist->started = false; sqd->work_time += io_sq_cpu_usec(current) - ist->usec; } static void io_sq_start_worktime(struct io_sq_time *ist) { if (ist->started) return; ist->started = true; ist->usec = io_sq_cpu_usec(current); } static int __io_sq_thread(struct io_ring_ctx *ctx, struct io_sq_data *sqd, bool cap_entries, struct io_sq_time *ist) { unsigned int to_submit; int ret = 0; to_submit = io_sqring_entries(ctx); /* if we're handling multiple rings, cap submit size for fairness */ if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; if (to_submit || !list_empty(&ctx->iopoll_list)) { const struct cred *creds = NULL; io_sq_start_worktime(ist); if (ctx->sq_creds != current_cred()) creds = override_creds(ctx->sq_creds); mutex_lock(&ctx->uring_lock); if (!list_empty(&ctx->iopoll_list)) io_do_iopoll(ctx, true); /* * Don't submit if refs are dying, good for io_uring_register(), * but also it is relied upon by io_ring_exit_work() */ if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) && !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) revert_creds(creds); } return ret; } static bool io_sqd_handle_event(struct io_sq_data *sqd) { bool did_sig = false; struct ksignal ksig; if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || signal_pending(current)) { mutex_unlock(&sqd->lock); if (signal_pending(current)) did_sig = get_signal(&ksig); wait_event(sqd->wait, !atomic_read(&sqd->park_pending)); mutex_lock(&sqd->lock); sqd->sq_cpu = raw_smp_processor_id(); } return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); } /* * Run task_work, processing no more than max_entries at a time. If more * than that is pending, it simply stays on the queue for the next run. */ static unsigned int io_sq_tw(int max_entries) { struct io_uring_task *tctx = current->io_uring; unsigned int count = 0; tctx_task_work_run(tctx, max_entries, &count); if (task_work_pending(current)) task_work_run(); return count; } static bool io_sq_tw_pending(void) { struct io_uring_task *tctx = current->io_uring; return !mpscq_empty(&tctx->task_list); } static int io_sq_thread(void *data) { struct io_sq_data *sqd = data; struct io_ring_ctx *ctx; unsigned long timeout = 0; char buf[TASK_COMM_LEN] = {}; DEFINE_WAIT(wait); /* offload context creation failed, just exit */ if (!current->io_uring) { mutex_lock(&sqd->lock); rcu_assign_pointer(sqd->thread, NULL); put_task_struct(current); mutex_unlock(&sqd->lock); goto err_out; } snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); /* reset to our pid after we've set task_comm, for fdinfo */ sqd->task_pid = current->pid; if (sqd->sq_cpu != -1) { set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); } else { set_cpus_allowed_ptr(current, cpu_online_mask); sqd->sq_cpu = raw_smp_processor_id(); } /* * Force audit context to get setup, in case we do prep side async * operations that would trigger an audit call before any issue side * audit has been done. */ audit_uring_entry(IORING_OP_NOP); audit_uring_exit(true, 0); mutex_lock(&sqd->lock); while (1) { bool cap_entries, sqt_spin = false; struct io_sq_time ist = { }; if (io_sqd_events_pending(sqd) || signal_pending(current)) { if (io_sqd_handle_event(sqd)) break; timeout = jiffies + sqd->sq_thread_idle; } cap_entries = !list_is_singular(&sqd->ctx_list); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { int ret = __io_sq_thread(ctx, sqd, cap_entries, &ist); if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) sqt_spin = true; } if (io_sq_tw(IORING_TW_CAP_ENTRIES_VALUE)) sqt_spin = true; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { if (io_napi(ctx)) { io_sq_start_worktime(&ist); io_napi_sqpoll_busy_poll(ctx); } } io_sq_update_worktime(sqd, &ist); if (sqt_spin || !time_after(jiffies, timeout)) { if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; if (unlikely(need_resched())) { mutex_unlock(&sqd->lock); cond_resched(); mutex_lock(&sqd->lock); sqd->sq_cpu = raw_smp_processor_id(); } continue; } prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); if (!io_sqd_events_pending(sqd) && !io_sq_tw_pending()) { bool needs_sched = true; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags); if ((ctx->flags & IORING_SETUP_IOPOLL) && !list_empty(&ctx->iopoll_list)) { needs_sched = false; break; } /* * Ensure the store of the wakeup flag is not * reordered with the load of the SQ tail */ smp_mb__after_atomic(); if (io_sqring_entries(ctx)) { needs_sched = false; break; } } if (needs_sched) { mutex_unlock(&sqd->lock); schedule(); mutex_lock(&sqd->lock); sqd->sq_cpu = raw_smp_processor_id(); } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) atomic_andnot(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags); } finish_wait(&sqd->wait, &wait); timeout = jiffies + sqd->sq_thread_idle; } if (io_sq_tw_pending()) io_sq_tw(UINT_MAX); io_uring_cancel_generic(true, sqd); rcu_assign_pointer(sqd->thread, NULL); put_task_struct(current); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags); io_run_task_work(); mutex_unlock(&sqd->lock); err_out: complete(&sqd->exited); do_exit(0); } void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) { DEFINE_WAIT(wait); do { if (!io_sqring_full(ctx)) break; prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); if (!io_sqring_full(ctx)) break; schedule(); } while (!signal_pending(current)); finish_wait(&ctx->sqo_sq_wait, &wait); } __cold int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p) { int ret; /* Retain compatibility with failing for an invalid attach attempt */ if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) == IORING_SETUP_ATTACH_WQ) { CLASS(fd, f)(p->wq_fd); if (fd_empty(f)) return -ENXIO; if (!io_is_uring_fops(fd_file(f))) return -EINVAL; } if (ctx->flags & IORING_SETUP_SQPOLL) { struct io_uring_task *tctx; struct task_struct *tsk; struct io_sq_data *sqd; bool attached; ret = security_uring_sqpoll(); if (ret) return ret; sqd = io_get_sq_data(p, &attached); if (IS_ERR(sqd)) { ret = PTR_ERR(sqd); goto err; } ctx->sq_creds = get_current_cred(); ctx->sq_data = sqd; ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); if (!ctx->sq_thread_idle) ctx->sq_thread_idle = HZ; io_sq_thread_park(sqd); list_add(&ctx->sqd_list, &sqd->ctx_list); io_sqd_update_thread_idle(sqd); /* don't attach to a dying SQPOLL thread, would be racy */ ret = (attached && !sqd->thread) ? -ENXIO : 0; io_sq_thread_unpark(sqd); if (ret < 0) goto err; if (attached) return 0; if (p->flags & IORING_SETUP_SQ_AFF) { cpumask_var_t allowed_mask; int cpu = p->sq_thread_cpu; ret = -EINVAL; if (cpu >= nr_cpu_ids || !cpu_online(cpu)) goto err_sqpoll; ret = -ENOMEM; if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL)) goto err_sqpoll; ret = -EINVAL; cpuset_cpus_allowed(current, allowed_mask); if (!cpumask_test_cpu(cpu, allowed_mask)) { free_cpumask_var(allowed_mask); goto err_sqpoll; } free_cpumask_var(allowed_mask); sqd->sq_cpu = cpu; } else { sqd->sq_cpu = -1; } sqd->task_pid = current->pid; sqd->task_tgid = current->tgid; tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE); if (IS_ERR(tsk)) { ret = PTR_ERR(tsk); goto err_sqpoll; } mutex_lock(&sqd->lock); rcu_assign_pointer(sqd->thread, tsk); mutex_unlock(&sqd->lock); ret = 0; get_task_struct(tsk); tctx = io_uring_alloc_task_context(tsk, ctx); if (!IS_ERR(tctx)) tsk->io_uring = tctx; else ret = PTR_ERR(tctx); wake_up_new_task(tsk); if (ret) goto err; } else if (p->flags & IORING_SETUP_SQ_AFF) { /* Can't have SQ_AFF without SQPOLL */ ret = -EINVAL; goto err; } return 0; err_sqpoll: complete(&ctx->sq_data->exited); err: io_sq_thread_finish(ctx); return ret; } __cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask) { struct io_sq_data *sqd = ctx->sq_data; int ret = -EINVAL; if (sqd) { struct task_struct *tsk; io_sq_thread_park(sqd); /* Don't set affinity for a dying thread */ tsk = sqpoll_task_locked(sqd); if (tsk) ret = io_wq_cpu_affinity(tsk->io_uring, mask); io_sq_thread_unpark(sqd); } return ret; } |
| 4 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | // SPDX-License-Identifier: GPL-2.0-or-later #include "linux/virtio_pci.h" #include <linux/virtio_pci_legacy.h> #include <linux/module.h> #include <linux/pci.h> /* * vp_legacy_probe: probe the legacy virtio pci device, note that the * caller is required to enable PCI device before calling this function. * @ldev: the legacy virtio-pci device * * Return 0 on succeed otherwise fail */ int vp_legacy_probe(struct virtio_pci_legacy_device *ldev) { struct pci_dev *pci_dev = ldev->pci_dev; int rc; /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */ if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f) return -ENODEV; if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) return -ENODEV; rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64)); if (rc) { rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); } else { /* * The virtio ring base address is expressed as a 32-bit PFN, * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT. */ dma_set_coherent_mask(&pci_dev->dev, DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT)); } if (rc) dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy"); if (rc) return rc; ldev->ioaddr = pci_iomap(pci_dev, 0, 0); if (!ldev->ioaddr) { rc = -EIO; goto err_iomap; } ldev->isr = ldev->ioaddr + VIRTIO_PCI_ISR; ldev->id.vendor = pci_dev->subsystem_vendor; ldev->id.device = pci_dev->subsystem_device; return 0; err_iomap: pci_release_region(pci_dev, 0); return rc; } EXPORT_SYMBOL_GPL(vp_legacy_probe); /* * vp_legacy_probe: remove and cleanup the legacy virtio pci device * @ldev: the legacy virtio-pci device */ void vp_legacy_remove(struct virtio_pci_legacy_device *ldev) { struct pci_dev *pci_dev = ldev->pci_dev; pci_iounmap(pci_dev, ldev->ioaddr); pci_release_region(pci_dev, 0); } EXPORT_SYMBOL_GPL(vp_legacy_remove); /* * vp_legacy_get_features - get features from device * @ldev: the legacy virtio-pci device * * Returns the features read from the device */ u64 vp_legacy_get_features(struct virtio_pci_legacy_device *ldev) { return ioread32(ldev->ioaddr + VIRTIO_PCI_HOST_FEATURES); } EXPORT_SYMBOL_GPL(vp_legacy_get_features); /* * vp_legacy_get_driver_features - get driver features from device * @ldev: the legacy virtio-pci device * * Returns the driver features read from the device */ u64 vp_legacy_get_driver_features(struct virtio_pci_legacy_device *ldev) { return ioread32(ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES); } EXPORT_SYMBOL_GPL(vp_legacy_get_driver_features); /* * vp_legacy_set_features - set features to device * @ldev: the legacy virtio-pci device * @features: the features set to device */ void vp_legacy_set_features(struct virtio_pci_legacy_device *ldev, u32 features) { iowrite32(features, ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES); } EXPORT_SYMBOL_GPL(vp_legacy_set_features); /* * vp_legacy_get_status - get the device status * @ldev: the legacy virtio-pci device * * Returns the status read from device */ u8 vp_legacy_get_status(struct virtio_pci_legacy_device *ldev) { return ioread8(ldev->ioaddr + VIRTIO_PCI_STATUS); } EXPORT_SYMBOL_GPL(vp_legacy_get_status); /* * vp_legacy_set_status - set status to device * @ldev: the legacy virtio-pci device * @status: the status set to device */ void vp_legacy_set_status(struct virtio_pci_legacy_device *ldev, u8 status) { iowrite8(status, ldev->ioaddr + VIRTIO_PCI_STATUS); } EXPORT_SYMBOL_GPL(vp_legacy_set_status); /* * vp_legacy_queue_vector - set the MSIX vector for a specific virtqueue * @ldev: the legacy virtio-pci device * @index: queue index * @vector: the queue vector * * Returns the queue vector read from the device */ u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev, u16 index, u16 vector) { iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); /* Flush the write out to device */ return ioread16(ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); } EXPORT_SYMBOL_GPL(vp_legacy_queue_vector); /* * vp_legacy_config_vector - set the vector for config interrupt * @ldev: the legacy virtio-pci device * @vector: the config vector * * Returns the config vector read from the device */ u16 vp_legacy_config_vector(struct virtio_pci_legacy_device *ldev, u16 vector) { /* Setup the vector used for configuration events */ iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR); /* Verify we had enough resources to assign the vector */ /* Will also flush the write out to device */ return ioread16(ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR); } EXPORT_SYMBOL_GPL(vp_legacy_config_vector); /* * vp_legacy_set_queue_address - set the virtqueue address * @ldev: the legacy virtio-pci device * @index: the queue index * @queue_pfn: pfn of the virtqueue */ void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev, u16 index, u32 queue_pfn) { iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); iowrite32(queue_pfn, ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN); } EXPORT_SYMBOL_GPL(vp_legacy_set_queue_address); /* * vp_legacy_get_queue_enable - enable a virtqueue * @ldev: the legacy virtio-pci device * @index: the queue index * * Returns whether a virtqueue is enabled or not */ bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev, u16 index) { iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); return ioread32(ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN); } EXPORT_SYMBOL_GPL(vp_legacy_get_queue_enable); /* * vp_legacy_get_queue_size - get size for a virtqueue * @ldev: the legacy virtio-pci device * @index: the queue index * * Returns the size of the virtqueue */ u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev, u16 index) { iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); return ioread16(ldev->ioaddr + VIRTIO_PCI_QUEUE_NUM); } EXPORT_SYMBOL_GPL(vp_legacy_get_queue_size); MODULE_VERSION("0.1"); MODULE_DESCRIPTION("Legacy Virtio PCI Device"); MODULE_AUTHOR("Wu Zongyong <wuzongyong@linux.alibaba.com>"); MODULE_LICENSE("GPL"); |
| 1932 4 4 1891 107 1792 1796 777 40 749 24 24 2094 33 79 2121 2123 91 2089 2095 2090 2096 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/main.c - Where the driver meets power management. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * * The driver model core calls device_pm_add() when a device is registered. * This will initialize the embedded device_pm_info object in the device * and add it to the list of power-controlled devices. sysfs entries for * controlling device power management will also be added. * * A separate list is used for keeping track of power info, because the power * domain dependencies may differ from the ancestral dependencies that the * subsystem list maintains. */ #define pr_fmt(fmt) "PM: " fmt #define dev_fmt pr_fmt #include <linux/device.h> #include <linux/export.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/pm_runtime.h> #include <linux/pm-trace.h> #include <linux/pm_wakeirq.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sysctl.h> #include <linux/async.h> #include <linux/suspend.h> #include <trace/events/power.h> #include <linux/cpufreq.h> #include <linux/devfreq.h> #include <linux/thermal.h> #include <linux/timer.h> #include <linux/nmi.h> #include "../base.h" #include "power.h" #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "pm." typedef int (*pm_callback_t)(struct device *); /* * The entries in the dpm_list list are in a depth first order, simply * because children are guaranteed to be discovered after parents, and * are inserted at the back of the list on discovery. * * Since device_pm_add() may be called with a device lock held, * we must never try to acquire a device lock while holding * dpm_list_mutex. */ LIST_HEAD(dpm_list); static LIST_HEAD(dpm_prepared_list); static LIST_HEAD(dpm_suspended_list); static LIST_HEAD(dpm_late_early_list); static LIST_HEAD(dpm_noirq_list); static DEFINE_MUTEX(dpm_list_mtx); static pm_message_t pm_transition; static DEFINE_MUTEX(async_wip_mtx); static int async_error; /** * pm_hibernate_is_recovering - if recovering from hibernate due to error. * * Used to query if dev_pm_ops.thaw() is called for normal hibernation case or * recovering from some error. * * Return: true for error case, false for normal case. */ bool pm_hibernate_is_recovering(void) { return pm_transition.event == PM_EVENT_RECOVER; } EXPORT_SYMBOL_GPL(pm_hibernate_is_recovering); static const char *pm_verb(int event) { switch (event) { case PM_EVENT_SUSPEND: return "suspend"; case PM_EVENT_RESUME: return "resume"; case PM_EVENT_FREEZE: return "freeze"; case PM_EVENT_QUIESCE: return "quiesce"; case PM_EVENT_HIBERNATE: return "hibernate"; case PM_EVENT_THAW: return "thaw"; case PM_EVENT_RESTORE: return "restore"; case PM_EVENT_RECOVER: return "recover"; case PM_EVENT_POWEROFF: return "poweroff"; default: return "(unknown PM event)"; } } /** * device_pm_sleep_init - Initialize system suspend-related device fields. * @dev: Device object being initialized. */ void device_pm_sleep_init(struct device *dev) { dev->power.is_prepared = false; dev->power.is_suspended = false; dev->power.is_noirq_suspended = false; dev->power.is_late_suspended = false; init_completion(&dev->power.completion); complete(&dev->power.completion); dev->power.wakeup = NULL; INIT_LIST_HEAD(&dev->power.entry); } /** * device_pm_lock - Lock the list of active devices used by the PM core. */ void device_pm_lock(void) { mutex_lock(&dpm_list_mtx); } /** * device_pm_unlock - Unlock the list of active devices used by the PM core. */ void device_pm_unlock(void) { mutex_unlock(&dpm_list_mtx); } /** * device_pm_add - Add a device to the PM core's list of active devices. * @dev: Device to add to the list. */ void device_pm_add(struct device *dev) { /* Skip PM setup/initialization. */ if (device_pm_not_required(dev)) return; pr_debug("Adding info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); device_pm_check_callbacks(dev); mutex_lock(&dpm_list_mtx); if (dev->parent && dev->parent->power.is_prepared) dev_warn(dev, "parent %s should not be sleeping\n", dev_name(dev->parent)); list_add_tail(&dev->power.entry, &dpm_list); dev->power.in_dpm_list = true; mutex_unlock(&dpm_list_mtx); } /** * device_pm_remove - Remove a device from the PM core's list of active devices. * @dev: Device to be removed from the list. */ void device_pm_remove(struct device *dev) { if (device_pm_not_required(dev)) return; pr_debug("Removing info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); complete_all(&dev->power.completion); mutex_lock(&dpm_list_mtx); list_del_init(&dev->power.entry); dev->power.in_dpm_list = false; mutex_unlock(&dpm_list_mtx); device_wakeup_disable(dev); pm_runtime_remove(dev); device_pm_check_callbacks(dev); } /** * device_pm_move_before - Move device in the PM core's list of active devices. * @deva: Device to move in dpm_list. * @devb: Device @deva should come before. */ void device_pm_move_before(struct device *deva, struct device *devb) { pr_debug("Moving %s:%s before %s:%s\n", deva->bus ? deva->bus->name : "No Bus", dev_name(deva), devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); /* Delete deva from dpm_list and reinsert before devb. */ list_move_tail(&deva->power.entry, &devb->power.entry); } /** * device_pm_move_after - Move device in the PM core's list of active devices. * @deva: Device to move in dpm_list. * @devb: Device @deva should come after. */ void device_pm_move_after(struct device *deva, struct device *devb) { pr_debug("Moving %s:%s after %s:%s\n", deva->bus ? deva->bus->name : "No Bus", dev_name(deva), devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); /* Delete deva from dpm_list and reinsert after devb. */ list_move(&deva->power.entry, &devb->power.entry); } /** * device_pm_move_last - Move device to end of the PM core's list of devices. * @dev: Device to move in dpm_list. */ void device_pm_move_last(struct device *dev) { pr_debug("Moving %s:%s to end of list\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); list_move_tail(&dev->power.entry, &dpm_list); } static ktime_t initcall_debug_start(struct device *dev, void *cb) { if (!pm_print_times_enabled) return 0; dev_info(dev, "calling %ps @ %i, parent: %s\n", cb, task_pid_nr(current), dev->parent ? dev_name(dev->parent) : "none"); return ktime_get(); } static void initcall_debug_report(struct device *dev, ktime_t calltime, void *cb, int error) { ktime_t rettime; if (!pm_print_times_enabled) return; rettime = ktime_get(); dev_info(dev, "%ps returned %d after %Ld usecs\n", cb, error, (unsigned long long)ktime_us_delta(rettime, calltime)); } /** * dpm_wait - Wait for a PM operation to complete. * @dev: Device to wait for. * @async: If unset, wait only if the device's power.async_suspend flag is set. */ static void dpm_wait(struct device *dev, bool async) { if (!dev) return; /* Devices with no PM support don't use the completion. */ if (dev->power.no_pm) return; if (async || (pm_async_enabled && dev->power.async_suspend)) wait_for_completion(&dev->power.completion); } static int dpm_wait_fn(struct device *dev, void *async_ptr) { dpm_wait(dev, *((bool *)async_ptr)); return 0; } static void dpm_wait_for_children(struct device *dev, bool async) { device_for_each_child(dev, &async, dpm_wait_fn); } static void dpm_wait_for_suppliers(struct device *dev, bool async) { struct device_link *link; int idx; idx = device_links_read_lock(); /* * If the supplier goes away right after we've checked the link to it, * we'll wait for its completion to change the state, but that's fine, * because the only things that will block as a result are the SRCU * callbacks freeing the link objects for the links in the list we're * walking. */ dev_for_each_link_to_supplier(link, dev) if (READ_ONCE(link->status) != DL_STATE_DORMANT && !device_link_flag_is_sync_state_only(link->flags)) dpm_wait(link->supplier, async); device_links_read_unlock(idx); } static bool dpm_wait_for_superior(struct device *dev, bool async) { struct device *parent; /* * If the device is resumed asynchronously and the parent's callback * deletes both the device and the parent itself, the parent object may * be freed while this function is running, so avoid that by reference * counting the parent once more unless the device has been deleted * already (in which case return right away). */ mutex_lock(&dpm_list_mtx); if (!device_pm_initialized(dev)) { mutex_unlock(&dpm_list_mtx); return false; } parent = get_device(dev->parent); mutex_unlock(&dpm_list_mtx); dpm_wait(parent, async); put_device(parent); dpm_wait_for_suppliers(dev, async); /* * If the parent's callback has deleted the device, attempting to resume * it would be invalid, so avoid doing that then. */ return device_pm_initialized(dev); } static void dpm_wait_for_consumers(struct device *dev, bool async) { struct device_link *link; int idx; idx = device_links_read_lock(); /* * The status of a device link can only be changed from "dormant" by a * probe, but that cannot happen during system suspend/resume. In * theory it can change to "dormant" at that time, but then it is * reasonable to wait for the target device anyway (eg. if it goes * away, it's better to wait for it to go away completely and then * continue instead of trying to continue in parallel with its * unregistration). */ dev_for_each_link_to_consumer(link, dev) if (READ_ONCE(link->status) != DL_STATE_DORMANT && !device_link_flag_is_sync_state_only(link->flags)) dpm_wait(link->consumer, async); device_links_read_unlock(idx); } static void dpm_wait_for_subordinate(struct device *dev, bool async) { dpm_wait_for_children(dev, async); dpm_wait_for_consumers(dev, async); } /** * pm_op - Return the PM operation appropriate for given PM event. * @ops: PM operations to choose from. * @state: PM transition of the system being carried out. */ static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state) { switch (state.event) { #ifdef CONFIG_SUSPEND case PM_EVENT_SUSPEND: return ops->suspend; case PM_EVENT_RESUME: return ops->resume; #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze; case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff; case PM_EVENT_THAW: case PM_EVENT_RECOVER: return ops->thaw; case PM_EVENT_RESTORE: return ops->restore; #endif /* CONFIG_HIBERNATE_CALLBACKS */ } return NULL; } /** * pm_late_early_op - Return the PM operation appropriate for given PM event. * @ops: PM operations to choose from. * @state: PM transition of the system being carried out. * * Runtime PM is disabled for @dev while this function is being executed. */ static pm_callback_t pm_late_early_op(const struct dev_pm_ops *ops, pm_message_t state) { switch (state.event) { #ifdef CONFIG_SUSPEND case PM_EVENT_SUSPEND: return ops->suspend_late; case PM_EVENT_RESUME: return ops->resume_early; #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_late; case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff_late; case PM_EVENT_THAW: case PM_EVENT_RECOVER: return ops->thaw_early; case PM_EVENT_RESTORE: return ops->restore_early; #endif /* CONFIG_HIBERNATE_CALLBACKS */ } return NULL; } /** * pm_noirq_op - Return the PM operation appropriate for given PM event. * @ops: PM operations to choose from. * @state: PM transition of the system being carried out. * * The driver of @dev will not receive interrupts while this function is being * executed. */ static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t state) { switch (state.event) { #ifdef CONFIG_SUSPEND case PM_EVENT_SUSPEND: return ops->suspend_noirq; case PM_EVENT_RESUME: return ops->resume_noirq; #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_noirq; case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff_noirq; case PM_EVENT_THAW: case PM_EVENT_RECOVER: return ops->thaw_noirq; case PM_EVENT_RESTORE: return ops->restore_noirq; #endif /* CONFIG_HIBERNATE_CALLBACKS */ } return NULL; } static void pm_dev_dbg(struct device *dev, pm_message_t state, const char *info) { dev_dbg(dev, "%s%s%s driver flags: %x\n", info, pm_verb(state.event), ((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ? ", may wakeup" : "", dev->power.driver_flags); } static void pm_dev_err(struct device *dev, pm_message_t state, const char *info, int error) { dev_err(dev, "failed to %s%s: error %d\n", pm_verb(state.event), info, error); } static void dpm_show_time(ktime_t starttime, pm_message_t state, int error, const char *info) { ktime_t calltime; u64 usecs64; int usecs; calltime = ktime_get(); usecs64 = ktime_to_ns(ktime_sub(calltime, starttime)); do_div(usecs64, NSEC_PER_USEC); usecs = usecs64; if (usecs == 0) usecs = 1; pm_pr_dbg("%s%s%s of devices %s after %ld.%03ld msecs\n", info ?: "", info ? " " : "", pm_verb(state.event), error ? "aborted" : "complete", usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC); } static int dpm_run_callback(pm_callback_t cb, struct device *dev, pm_message_t state, const char *info) { ktime_t calltime; int error; if (!cb) return 0; calltime = initcall_debug_start(dev, cb); pm_dev_dbg(dev, state, info); trace_device_pm_callback_start(dev, info, state.event); error = cb(dev); trace_device_pm_callback_end(dev, error); suspend_report_result(dev, cb, error); initcall_debug_report(dev, calltime, cb, error); return error; } #ifdef CONFIG_DPM_WATCHDOG struct dpm_watchdog { struct device *dev; struct task_struct *tsk; struct timer_list timer; bool fatal; }; #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \ struct dpm_watchdog wd static bool __read_mostly dpm_watchdog_all_cpu_backtrace; module_param(dpm_watchdog_all_cpu_backtrace, bool, 0644); MODULE_PARM_DESC(dpm_watchdog_all_cpu_backtrace, "Backtrace all CPUs on DPM watchdog timeout"); static bool __read_mostly dpm_watchdog_enabled = IS_ENABLED(CONFIG_DPM_WATCHDOG_ENABLED); module_param(dpm_watchdog_enabled, bool, 0644); MODULE_PARM_DESC(dpm_watchdog_enabled, "Enable DPM watchdog"); static unsigned int __read_mostly dpm_watchdog_timeout = CONFIG_DPM_WATCHDOG_TIMEOUT; static unsigned int __read_mostly dpm_watchdog_warning_timeout = CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; static const unsigned int dpm_watchdog_timeout_max = CONFIG_DPM_WATCHDOG_TIMEOUT; static int proc_dodpm_watchdog_timeout_secs(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ctl = *table; unsigned int val = dpm_watchdog_timeout; int ret; ctl.data = &val; ret = proc_douintvec_minmax(&ctl, write, buffer, lenp, ppos); if (ret || !write) return ret; if (val < dpm_watchdog_warning_timeout) dpm_watchdog_warning_timeout = val; dpm_watchdog_timeout = val; return 0; } static const struct ctl_table dpm_watchdog_sysctls[] = { { .procname = "dpm_watchdog_timeout_secs", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dodpm_watchdog_timeout_secs, .extra1 = SYSCTL_ONE, .extra2 = (void *)&dpm_watchdog_timeout_max, }, { .procname = "dpm_watchdog_warning_timeout_secs", .data = &dpm_watchdog_warning_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = (void *)&dpm_watchdog_timeout, }, }; static int __init dpm_watchdog_sysctl_init(void) { register_sysctl_init("kernel", dpm_watchdog_sysctls); return 0; } subsys_initcall(dpm_watchdog_sysctl_init); /** * dpm_watchdog_handler - Driver suspend / resume watchdog handler. * @t: The timer that PM watchdog depends on. * * Called when a driver has timed out suspending or resuming. * There's not much we can do here to recover so panic() to * capture a crash-dump in pstore. */ static void dpm_watchdog_handler(struct timer_list *t) { struct dpm_watchdog *wd = timer_container_of(wd, t, timer); struct timer_list *timer = &wd->timer; unsigned int time_left; if (wd->fatal) { unsigned int this_cpu = smp_processor_id(); dev_emerg(wd->dev, "**** DPM device timeout ****\n"); show_stack(wd->tsk, NULL, KERN_EMERG); if (dpm_watchdog_all_cpu_backtrace) trigger_allbutcpu_cpu_backtrace(this_cpu); panic("%s %s: unrecoverable failure\n", dev_driver_string(wd->dev), dev_name(wd->dev)); } time_left = dpm_watchdog_timeout - dpm_watchdog_warning_timeout; dev_warn(wd->dev, "**** DPM device timeout after %u seconds; %u seconds until panic ****\n", dpm_watchdog_warning_timeout, time_left); show_stack(wd->tsk, NULL, KERN_WARNING); wd->fatal = true; mod_timer(timer, jiffies + HZ * time_left); } /** * dpm_watchdog_set - Enable pm watchdog for given device. * @wd: Watchdog. Must be allocated on the stack. * @dev: Device to handle. */ static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev) { struct timer_list *timer = &wd->timer; if (!dpm_watchdog_enabled) return; wd->dev = dev; wd->tsk = current; wd->fatal = dpm_watchdog_timeout == dpm_watchdog_warning_timeout; timer_setup_on_stack(timer, dpm_watchdog_handler, 0); /* use same timeout value for both suspend and resume */ timer->expires = jiffies + HZ * dpm_watchdog_warning_timeout; add_timer(timer); } /** * dpm_watchdog_clear - Disable suspend/resume watchdog. * @wd: Watchdog to disable. */ static void dpm_watchdog_clear(struct dpm_watchdog *wd) { struct timer_list *timer = &wd->timer; if (!dpm_watchdog_enabled) return; timer_delete_sync(timer); timer_destroy_on_stack(timer); } #else #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) #define dpm_watchdog_set(x, y) #define dpm_watchdog_clear(x) #endif /*------------------------- Resume routines -------------------------*/ /** * dev_pm_skip_resume - System-wide device resume optimization check. * @dev: Target device. * * Return: * - %false if the transition under way is RESTORE. * - Return value of dev_pm_skip_suspend() if the transition under way is THAW. * - The logical negation of %power.must_resume otherwise (that is, when the * transition under way is RESUME). */ bool dev_pm_skip_resume(struct device *dev) { if (pm_transition.event == PM_EVENT_RESTORE) return false; if (pm_transition.event == PM_EVENT_THAW) return dev_pm_skip_suspend(dev); return !dev->power.must_resume; } static bool is_async(struct device *dev) { return dev->power.async_suspend && pm_async_enabled && !pm_trace_is_enabled(); } static bool __dpm_async(struct device *dev, async_func_t func) { if (dev->power.work_in_progress) return true; if (!is_async(dev)) return false; dev->power.work_in_progress = true; get_device(dev); if (async_schedule_dev_nocall(func, dev)) return true; put_device(dev); return false; } static bool dpm_async_fn(struct device *dev, async_func_t func) { guard(mutex)(&async_wip_mtx); return __dpm_async(dev, func); } static int dpm_async_with_cleanup(struct device *dev, void *fn) { guard(mutex)(&async_wip_mtx); if (!__dpm_async(dev, fn)) dev->power.work_in_progress = false; return 0; } static void dpm_async_resume_children(struct device *dev, async_func_t func) { /* * Prevent racing with dpm_clear_async_state() during initial list * walks in dpm_noirq_resume_devices(), dpm_resume_early(), and * dpm_resume(). */ guard(mutex)(&dpm_list_mtx); /* * Start processing "async" children of the device unless it's been * started already for them. */ device_for_each_child(dev, func, dpm_async_with_cleanup); } static void dpm_async_resume_subordinate(struct device *dev, async_func_t func) { struct device_link *link; int idx; dpm_async_resume_children(dev, func); idx = device_links_read_lock(); /* Start processing the device's "async" consumers. */ dev_for_each_link_to_consumer(link, dev) if (READ_ONCE(link->status) != DL_STATE_DORMANT) dpm_async_with_cleanup(link->consumer, func); device_links_read_unlock(idx); } static void dpm_clear_async_state(struct device *dev) { reinit_completion(&dev->power.completion); dev->power.work_in_progress = false; } static bool dpm_root_device(struct device *dev) { lockdep_assert_held(&dpm_list_mtx); /* * Since this function is required to run under dpm_list_mtx, the * list_empty() below will only return true if the device's list of * consumers is actually empty before calling it. */ return !dev->parent && list_empty(&dev->links.suppliers); } static void async_resume_noirq(void *data, async_cookie_t cookie); /** * device_resume_noirq - Execute a "noirq resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * The driver of @dev will not receive interrupts while this function is being * executed. */ static void device_resume_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; bool skip_resume; int error = 0; TRACE_DEVICE(dev); TRACE_RESUME(0); if (dev->power.syscore || dev->power.direct_complete) goto Out; if (!dev->power.is_noirq_suspended) { /* * This means that system suspend has been aborted in the noirq * phase before invoking the noirq suspend callback for the * device, so if device_suspend_late() has left it in suspend, * device_resume_early() should leave it in suspend either in * case the early resume of it depends on the noirq resume that * has not run. */ if (dev_pm_skip_suspend(dev)) dev->power.must_resume = false; goto Out; } if (!dpm_wait_for_superior(dev, async)) goto Out; skip_resume = dev_pm_skip_resume(dev); /* * If the driver callback is skipped below or by the middle layer * callback and device_resume_early() also skips the driver callback for * this device later, it needs to appear as "suspended" to PM-runtime, * so change its status accordingly. * * Otherwise, the device is going to be resumed, so set its PM-runtime * status to "active" unless its power.smart_suspend flag is clear, in * which case it is not necessary to update its PM-runtime status. */ if (skip_resume) pm_runtime_set_suspended(dev); else if (dev_pm_smart_suspend(dev)) pm_runtime_set_active(dev); if (dev->pm_domain) { info = "noirq power domain "; callback = pm_noirq_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "noirq type "; callback = pm_noirq_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "noirq class "; callback = pm_noirq_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "noirq bus "; callback = pm_noirq_op(dev->bus->pm, state); } if (callback) goto Run; if (skip_resume) goto Skip; if (dev->driver && dev->driver->pm) { info = "noirq driver "; callback = pm_noirq_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); Skip: dev->power.is_noirq_suspended = false; Out: complete_all(&dev->power.completion); TRACE_RESUME(error); if (error) { WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); } dpm_async_resume_subordinate(dev, async_resume_noirq); } static void async_resume_noirq(void *data, async_cookie_t cookie) { struct device *dev = data; device_resume_noirq(dev, pm_transition, true); put_device(dev); } static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true); async_error = 0; pm_transition = state; mutex_lock(&dpm_list_mtx); /* * Start processing "async" root devices upfront so they don't wait for * the "sync" devices they don't depend on. */ list_for_each_entry(dev, &dpm_noirq_list, power.entry) { dpm_clear_async_state(dev); if (dpm_root_device(dev)) dpm_async_with_cleanup(dev, async_resume_noirq); } while (!list_empty(&dpm_noirq_list)) { dev = to_device(dpm_noirq_list.next); list_move_tail(&dev->power.entry, &dpm_late_early_list); if (!dpm_async_fn(dev, async_resume_noirq)) { get_device(dev); mutex_unlock(&dpm_list_mtx); device_resume_noirq(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "noirq"); if (READ_ONCE(async_error)) dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false); } /** * dpm_resume_noirq - Execute "noirq resume" callbacks for all devices. * @state: PM transition of the system being carried out. * * Invoke the "noirq" resume callbacks for all devices in dpm_noirq_list and * allow device drivers' interrupt handlers to be called. */ void dpm_resume_noirq(pm_message_t state) { dpm_noirq_resume_devices(state); resume_device_irqs(); device_wakeup_disarm_wake_irqs(); } static void async_resume_early(void *data, async_cookie_t cookie); /** * device_resume_early - Execute an "early resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ static void device_resume_early(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_RESUME(0); if (dev->power.direct_complete) goto Out; if (!dev->power.is_late_suspended) goto Out; if (dev->power.syscore) goto Skip; if (!dpm_wait_for_superior(dev, async)) goto Out; if (dev->pm_domain) { info = "early power domain "; callback = pm_late_early_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "early type "; callback = pm_late_early_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "early class "; callback = pm_late_early_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "early bus "; callback = pm_late_early_op(dev->bus->pm, state); } if (callback) goto Run; if (dev_pm_skip_resume(dev)) goto Skip; if (dev->driver && dev->driver->pm) { info = "early driver "; callback = pm_late_early_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); Skip: dev->power.is_late_suspended = false; pm_runtime_enable(dev); Out: TRACE_RESUME(error); complete_all(&dev->power.completion); if (error) { WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async early" : " early", error); } dpm_async_resume_subordinate(dev, async_resume_early); } static void async_resume_early(void *data, async_cookie_t cookie) { struct device *dev = data; device_resume_early(dev, pm_transition, true); put_device(dev); } /** * dpm_resume_early - Execute "early resume" callbacks for all devices. * @state: PM transition of the system being carried out. */ void dpm_resume_early(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume_early"), state.event, true); async_error = 0; pm_transition = state; mutex_lock(&dpm_list_mtx); /* * Start processing "async" root devices upfront so they don't wait for * the "sync" devices they don't depend on. */ list_for_each_entry(dev, &dpm_late_early_list, power.entry) { dpm_clear_async_state(dev); if (dpm_root_device(dev)) dpm_async_with_cleanup(dev, async_resume_early); } while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.next); list_move_tail(&dev->power.entry, &dpm_suspended_list); if (!dpm_async_fn(dev, async_resume_early)) { get_device(dev); mutex_unlock(&dpm_list_mtx); device_resume_early(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "early"); if (READ_ONCE(async_error)) dpm_save_failed_step(SUSPEND_RESUME_EARLY); trace_suspend_resume(TPS("dpm_resume_early"), state.event, false); } /** * dpm_resume_start - Execute "noirq" and "early" device callbacks. * @state: PM transition of the system being carried out. */ void dpm_resume_start(pm_message_t state) { dpm_resume_noirq(state); dpm_resume_early(state); } EXPORT_SYMBOL_GPL(dpm_resume_start); static void async_resume(void *data, async_cookie_t cookie); /** * device_resume - Execute "resume" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. */ static void device_resume(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; DECLARE_DPM_WATCHDOG_ON_STACK(wd); TRACE_DEVICE(dev); TRACE_RESUME(0); if (dev->power.syscore) goto Complete; if (!dev->power.is_suspended) goto Complete; dev->power.is_suspended = false; if (dev->power.direct_complete) { /* * Allow new children to be added under the device after this * point if it has no PM callbacks. */ if (dev->power.no_pm_callbacks) dev->power.is_prepared = false; /* Match the pm_runtime_disable() in device_suspend(). */ pm_runtime_enable(dev); goto Complete; } if (!dpm_wait_for_superior(dev, async)) goto Complete; dpm_watchdog_set(&wd, dev); device_lock(dev); /* * This is a fib. But we'll allow new children to be added below * a resumed device, even if the device hasn't been completed yet. */ dev->power.is_prepared = false; if (dev->pm_domain) { info = "power domain "; callback = pm_op(&dev->pm_domain->ops, state); goto Driver; } if (dev->type && dev->type->pm) { info = "type "; callback = pm_op(dev->type->pm, state); goto Driver; } if (dev->class && dev->class->pm) { info = "class "; callback = pm_op(dev->class->pm, state); goto Driver; } if (dev->bus) { if (dev->bus->pm) { info = "bus "; callback = pm_op(dev->bus->pm, state); } else if (dev->bus->resume) { info = "legacy bus "; callback = dev->bus->resume; goto End; } } Driver: if (!callback && dev->driver && dev->driver->pm) { info = "driver "; callback = pm_op(dev->driver->pm, state); } End: error = dpm_run_callback(callback, dev, state, info); device_unlock(dev); dpm_watchdog_clear(&wd); Complete: complete_all(&dev->power.completion); TRACE_RESUME(error); if (error) { WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async" : "", error); } dpm_async_resume_subordinate(dev, async_resume); } static void async_resume(void *data, async_cookie_t cookie) { struct device *dev = data; device_resume(dev, pm_transition, true); put_device(dev); } /** * dpm_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. * * Execute the appropriate "resume" callback for all devices whose status * indicates that they are suspended. */ void dpm_resume(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume"), state.event, true); pm_transition = state; async_error = 0; mutex_lock(&dpm_list_mtx); /* * Start processing "async" root devices upfront so they don't wait for * the "sync" devices they don't depend on. */ list_for_each_entry(dev, &dpm_suspended_list, power.entry) { dpm_clear_async_state(dev); if (dpm_root_device(dev)) dpm_async_with_cleanup(dev, async_resume); } while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.next); list_move_tail(&dev->power.entry, &dpm_prepared_list); if (!dpm_async_fn(dev, async_resume)) { get_device(dev); mutex_unlock(&dpm_list_mtx); device_resume(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, NULL); if (READ_ONCE(async_error)) dpm_save_failed_step(SUSPEND_RESUME); cpufreq_resume(); devfreq_resume(); trace_suspend_resume(TPS("dpm_resume"), state.event, false); } /** * device_complete - Complete a PM transition for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. */ static void device_complete(struct device *dev, pm_message_t state) { void (*callback)(struct device *) = NULL; const char *info = NULL; if (dev->power.syscore) goto out; device_lock(dev); if (dev->pm_domain) { info = "completing power domain "; callback = dev->pm_domain->ops.complete; } else if (dev->type && dev->type->pm) { info = "completing type "; callback = dev->type->pm->complete; } else if (dev->class && dev->class->pm) { info = "completing class "; callback = dev->class->pm->complete; } else if (dev->bus && dev->bus->pm) { info = "completing bus "; callback = dev->bus->pm->complete; } if (!callback && dev->driver && dev->driver->pm) { info = "completing driver "; callback = dev->driver->pm->complete; } if (callback) { pm_dev_dbg(dev, state, info); callback(dev); } device_unlock(dev); out: /* If enabling runtime PM for the device is blocked, unblock it. */ pm_runtime_unblock(dev); pm_runtime_put(dev); } /** * dpm_complete - Complete a PM transition for all non-sysdev devices. * @state: PM transition of the system being carried out. * * Execute the ->complete() callbacks for all devices whose PM status is not * DPM_ON (this allows new devices to be registered). */ void dpm_complete(pm_message_t state) { struct list_head list; trace_suspend_resume(TPS("dpm_complete"), state.event, true); INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_prepared_list)) { struct device *dev = to_device(dpm_prepared_list.prev); get_device(dev); dev->power.is_prepared = false; list_move(&dev->power.entry, &list); mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); device_complete(dev, state); trace_device_pm_callback_end(dev, 0); put_device(dev); mutex_lock(&dpm_list_mtx); } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); /* Start resuming thermal control */ thermal_pm_complete(); /* Allow device probing and trigger re-probing of deferred devices */ device_unblock_probing(); trace_suspend_resume(TPS("dpm_complete"), state.event, false); } /** * dpm_resume_end - Execute "resume" callbacks and complete system transition. * @state: PM transition of the system being carried out. * * Execute "resume" callbacks for all devices and complete the PM transition of * the system. */ void dpm_resume_end(pm_message_t state) { dpm_resume(state); pm_restore_gfp_mask(); dpm_complete(state); } EXPORT_SYMBOL_GPL(dpm_resume_end); /*------------------------- Suspend routines -------------------------*/ static bool dpm_leaf_device(struct device *dev) { struct device *child; lockdep_assert_held(&dpm_list_mtx); child = device_find_any_child(dev); if (child) { put_device(child); return false; } /* * Since this function is required to run under dpm_list_mtx, the * list_empty() below will only return true if the device's list of * consumers is actually empty before calling it. */ return list_empty(&dev->links.consumers); } static bool dpm_async_suspend_parent(struct device *dev, async_func_t func) { guard(mutex)(&dpm_list_mtx); /* * If the device is suspended asynchronously and the parent's callback * deletes both the device and the parent itself, the parent object may * be freed while this function is running, so avoid that by checking * if the device has been deleted already as the parent cannot be * deleted before it. */ if (!device_pm_initialized(dev)) return false; /* Start processing the device's parent if it is "async". */ if (dev->parent) dpm_async_with_cleanup(dev->parent, func); return true; } static void dpm_async_suspend_superior(struct device *dev, async_func_t func) { struct device_link *link; int idx; if (!dpm_async_suspend_parent(dev, func)) return; idx = device_links_read_lock(); /* Start processing the device's "async" suppliers. */ dev_for_each_link_to_supplier(link, dev) if (READ_ONCE(link->status) != DL_STATE_DORMANT) dpm_async_with_cleanup(link->supplier, func); device_links_read_unlock(idx); } static void dpm_async_suspend_complete_all(struct list_head *device_list) { struct device *dev; guard(mutex)(&async_wip_mtx); list_for_each_entry_reverse(dev, device_list, power.entry) { /* * In case the device is being waited for and async processing * has not started for it yet, let the waiters make progress. */ if (!dev->power.work_in_progress) complete_all(&dev->power.completion); } } /** * resume_event - Return a "resume" message for given "suspend" sleep state. * @sleep_state: PM message representing a sleep state. * * Return a PM message representing the resume event corresponding to given * sleep state. */ static pm_message_t resume_event(pm_message_t sleep_state) { switch (sleep_state.event) { case PM_EVENT_SUSPEND: return PMSG_RESUME; case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return PMSG_RECOVER; case PM_EVENT_HIBERNATE: return PMSG_RESTORE; } return PMSG_ON; } static void dpm_superior_set_must_resume(struct device *dev) { struct device_link *link; int idx; if (dev->parent) dev->parent->power.must_resume = true; idx = device_links_read_lock(); dev_for_each_link_to_supplier(link, dev) link->supplier->power.must_resume = true; device_links_read_unlock(idx); } static void async_suspend_noirq(void *data, async_cookie_t cookie); /** * device_suspend_noirq - Execute a "noirq suspend" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. * * The driver of @dev will not receive interrupts while this function is being * executed. */ static void device_suspend_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_SUSPEND(0); dpm_wait_for_subordinate(dev, async); if (READ_ONCE(async_error)) goto Complete; if (dev->power.syscore || dev->power.direct_complete) goto Complete; if (dev->pm_domain) { info = "noirq power domain "; callback = pm_noirq_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "noirq type "; callback = pm_noirq_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "noirq class "; callback = pm_noirq_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "noirq bus "; callback = pm_noirq_op(dev->bus->pm, state); } if (callback) goto Run; if (dev_pm_skip_suspend(dev)) goto Skip; if (dev->driver && dev->driver->pm) { info = "noirq driver "; callback = pm_noirq_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); if (error) { WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); goto Complete; } Skip: dev->power.is_noirq_suspended = true; /* * Devices must be resumed unless they are explicitly allowed to be left * in suspend, but even in that case skipping the resume of devices that * were in use right before the system suspend (as indicated by their * runtime PM usage counters and child counters) would be suboptimal. */ if (!(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) && dev->power.may_skip_resume) || !pm_runtime_need_not_resume(dev)) dev->power.must_resume = true; if (dev->power.must_resume) dpm_superior_set_must_resume(dev); Complete: complete_all(&dev->power.completion); TRACE_SUSPEND(error); if (error || READ_ONCE(async_error)) return; dpm_async_suspend_superior(dev, async_suspend_noirq); } static void async_suspend_noirq(void *data, async_cookie_t cookie) { struct device *dev = data; device_suspend_noirq(dev, pm_transition, true); put_device(dev); } static int dpm_noirq_suspend_devices(pm_message_t state) { ktime_t starttime = ktime_get(); struct device *dev; int error; trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true); pm_transition = state; async_error = 0; mutex_lock(&dpm_list_mtx); /* * Start processing "async" leaf devices upfront so they don't need to * wait for the "sync" devices they don't depend on. */ list_for_each_entry_reverse(dev, &dpm_late_early_list, power.entry) { dpm_clear_async_state(dev); if (dpm_leaf_device(dev)) dpm_async_with_cleanup(dev, async_suspend_noirq); } while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.prev); list_move(&dev->power.entry, &dpm_noirq_list); if (dpm_async_fn(dev, async_suspend_noirq)) continue; get_device(dev); mutex_unlock(&dpm_list_mtx); device_suspend_noirq(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); if (READ_ONCE(async_error)) { dpm_async_suspend_complete_all(&dpm_late_early_list); /* * Move all devices to the target list to resume them * properly. */ list_splice_init(&dpm_late_early_list, &dpm_noirq_list); break; } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); error = READ_ONCE(async_error); if (error) dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ); dpm_show_time(starttime, state, error, "noirq"); trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false); return error; } /** * dpm_suspend_noirq - Execute "noirq suspend" callbacks for all devices. * @state: PM transition of the system being carried out. * * Prevent device drivers' interrupt handlers from being called and invoke * "noirq" suspend callbacks for all non-sysdev devices. */ int dpm_suspend_noirq(pm_message_t state) { int ret; device_wakeup_arm_wake_irqs(); suspend_device_irqs(); ret = dpm_noirq_suspend_devices(state); if (ret) dpm_resume_noirq(resume_event(state)); return ret; } static void dpm_propagate_wakeup_to_parent(struct device *dev) { struct device *parent = dev->parent; if (!parent) return; spin_lock_irq(&parent->power.lock); if (device_wakeup_path(dev) && !parent->power.ignore_children) parent->power.wakeup_path = true; spin_unlock_irq(&parent->power.lock); } static void async_suspend_late(void *data, async_cookie_t cookie); /** * device_suspend_late - Execute a "late suspend" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ static void device_suspend_late(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_SUSPEND(0); dpm_wait_for_subordinate(dev, async); if (READ_ONCE(async_error)) goto Complete; if (pm_wakeup_pending()) { WRITE_ONCE(async_error, -EBUSY); goto Complete; } if (dev->power.direct_complete) goto Complete; /* * After this point, any runtime PM operations targeting the device * will fail until the corresponding pm_runtime_enable() call in * device_resume_early(). */ pm_runtime_disable(dev); if (dev->power.syscore) goto Skip; if (dev->pm_domain) { info = "late power domain "; callback = pm_late_early_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "late type "; callback = pm_late_early_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "late class "; callback = pm_late_early_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "late bus "; callback = pm_late_early_op(dev->bus->pm, state); } if (callback) goto Run; if (dev_pm_skip_suspend(dev)) goto Skip; if (dev->driver && dev->driver->pm) { info = "late driver "; callback = pm_late_early_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); if (error) { WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async late" : " late", error); pm_runtime_enable(dev); goto Complete; } dpm_propagate_wakeup_to_parent(dev); Skip: dev->power.is_late_suspended = true; Complete: TRACE_SUSPEND(error); complete_all(&dev->power.completion); if (error || READ_ONCE(async_error)) return; dpm_async_suspend_superior(dev, async_suspend_late); } static void async_suspend_late(void *data, async_cookie_t cookie) { struct device *dev = data; device_suspend_late(dev, pm_transition, true); put_device(dev); } /** * dpm_suspend_late - Execute "late suspend" callbacks for all devices. * @state: PM transition of the system being carried out. */ int dpm_suspend_late(pm_message_t state) { ktime_t starttime = ktime_get(); struct device *dev; int error; trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true); pm_transition = state; async_error = 0; wake_up_all_idle_cpus(); mutex_lock(&dpm_list_mtx); /* * Start processing "async" leaf devices upfront so they don't need to * wait for the "sync" devices they don't depend on. */ list_for_each_entry_reverse(dev, &dpm_suspended_list, power.entry) { dpm_clear_async_state(dev); if (dpm_leaf_device(dev)) dpm_async_with_cleanup(dev, async_suspend_late); } while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.prev); list_move(&dev->power.entry, &dpm_late_early_list); if (dpm_async_fn(dev, async_suspend_late)) continue; get_device(dev); mutex_unlock(&dpm_list_mtx); device_suspend_late(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); if (READ_ONCE(async_error)) { dpm_async_suspend_complete_all(&dpm_suspended_list); /* * Move all devices to the target list to resume them * properly. */ list_splice_init(&dpm_suspended_list, &dpm_late_early_list); break; } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); error = READ_ONCE(async_error); if (error) { dpm_save_failed_step(SUSPEND_SUSPEND_LATE); dpm_resume_early(resume_event(state)); } dpm_show_time(starttime, state, error, "late"); trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false); return error; } /** * dpm_suspend_end - Execute "late" and "noirq" device suspend callbacks. * @state: PM transition of the system being carried out. */ int dpm_suspend_end(pm_message_t state) { ktime_t starttime = ktime_get(); int error; error = dpm_suspend_late(state); if (error) goto out; error = dpm_suspend_noirq(state); if (error) dpm_resume_early(resume_event(state)); out: dpm_show_time(starttime, state, error, "end"); return error; } EXPORT_SYMBOL_GPL(dpm_suspend_end); /** * legacy_suspend - Execute a legacy (bus or class) suspend callback for device. * @dev: Device to suspend. * @state: PM transition of the system being carried out. * @cb: Suspend callback to execute. * @info: string description of caller. */ static int legacy_suspend(struct device *dev, pm_message_t state, int (*cb)(struct device *dev, pm_message_t state), const char *info) { int error; ktime_t calltime; calltime = initcall_debug_start(dev, cb); trace_device_pm_callback_start(dev, info, state.event); error = cb(dev, state); trace_device_pm_callback_end(dev, error); suspend_report_result(dev, cb, error); initcall_debug_report(dev, calltime, cb, error); return error; } static void dpm_clear_superiors_direct_complete(struct device *dev) { struct device_link *link; int idx; if (dev->parent) { spin_lock_irq(&dev->parent->power.lock); dev->parent->power.direct_complete = false; spin_unlock_irq(&dev->parent->power.lock); } idx = device_links_read_lock(); dev_for_each_link_to_supplier(link, dev) { spin_lock_irq(&link->supplier->power.lock); link->supplier->power.direct_complete = false; spin_unlock_irq(&link->supplier->power.lock); } device_links_read_unlock(idx); } static void async_suspend(void *data, async_cookie_t cookie); /** * device_suspend - Execute "suspend" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. */ static void device_suspend(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; DECLARE_DPM_WATCHDOG_ON_STACK(wd); TRACE_DEVICE(dev); TRACE_SUSPEND(0); dpm_wait_for_subordinate(dev, async); if (READ_ONCE(async_error)) { dev->power.direct_complete = false; goto Complete; } /* * Wait for possible runtime PM transitions of the device in progress * to complete and if there's a runtime resume request pending for it, * resume it before proceeding with invoking the system-wide suspend * callbacks for it. * * If the system-wide suspend callbacks below change the configuration * of the device, they must disable runtime PM for it or otherwise * ensure that its runtime-resume callbacks will not be confused by that * change in case they are invoked going forward. */ pm_runtime_barrier(dev); if (pm_wakeup_pending()) { dev->power.direct_complete = false; WRITE_ONCE(async_error, -EBUSY); goto Complete; } if (dev->power.syscore) goto Complete; /* Avoid direct_complete to let wakeup_path propagate. */ if (device_may_wakeup(dev) || device_wakeup_path(dev)) dev->power.direct_complete = false; if (dev->power.direct_complete) { if (pm_runtime_status_suspended(dev)) { pm_runtime_disable(dev); if (pm_runtime_status_suspended(dev)) { pm_dev_dbg(dev, state, "direct-complete "); dev->power.is_suspended = true; goto Complete; } pm_runtime_enable(dev); } dev->power.direct_complete = false; } dev->power.may_skip_resume = true; dev->power.must_resume = !dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME); dpm_watchdog_set(&wd, dev); device_lock(dev); if (dev->pm_domain) { info = "power domain "; callback = pm_op(&dev->pm_domain->ops, state); goto Run; } if (dev->type && dev->type->pm) { info = "type "; callback = pm_op(dev->type->pm, state); goto Run; } if (dev->class && dev->class->pm) { info = "class "; callback = pm_op(dev->class->pm, state); goto Run; } if (dev->bus) { if (dev->bus->pm) { info = "bus "; callback = pm_op(dev->bus->pm, state); } else if (dev->bus->suspend) { pm_dev_dbg(dev, state, "legacy bus "); error = legacy_suspend(dev, state, dev->bus->suspend, "legacy bus "); goto End; } } Run: if (!callback && dev->driver && dev->driver->pm) { info = "driver "; callback = pm_op(dev->driver->pm, state); } error = dpm_run_callback(callback, dev, state, info); End: if (!error) { dev->power.is_suspended = true; if (device_may_wakeup(dev)) dev->power.wakeup_path = true; dpm_propagate_wakeup_to_parent(dev); dpm_clear_superiors_direct_complete(dev); } device_unlock(dev); dpm_watchdog_clear(&wd); Complete: if (error) { WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async" : "", error); } complete_all(&dev->power.completion); TRACE_SUSPEND(error); if (error || READ_ONCE(async_error)) return; dpm_async_suspend_superior(dev, async_suspend); } static void async_suspend(void *data, async_cookie_t cookie) { struct device *dev = data; device_suspend(dev, pm_transition, true); put_device(dev); } /** * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices. * @state: PM transition of the system being carried out. */ int dpm_suspend(pm_message_t state) { ktime_t starttime = ktime_get(); struct device *dev; int error; trace_suspend_resume(TPS("dpm_suspend"), state.event, true); might_sleep(); devfreq_suspend(); cpufreq_suspend(); pm_transition = state; async_error = 0; mutex_lock(&dpm_list_mtx); /* * Start processing "async" leaf devices upfront so they don't need to * wait for the "sync" devices they don't depend on. */ list_for_each_entry_reverse(dev, &dpm_prepared_list, power.entry) { dpm_clear_async_state(dev); if (dpm_leaf_device(dev)) dpm_async_with_cleanup(dev, async_suspend); } while (!list_empty(&dpm_prepared_list)) { dev = to_device(dpm_prepared_list.prev); list_move(&dev->power.entry, &dpm_suspended_list); if (dpm_async_fn(dev, async_suspend)) continue; get_device(dev); mutex_unlock(&dpm_list_mtx); device_suspend(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); if (READ_ONCE(async_error)) { dpm_async_suspend_complete_all(&dpm_prepared_list); /* * Move all devices to the target list to resume them * properly. */ list_splice_init(&dpm_prepared_list, &dpm_suspended_list); break; } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); error = READ_ONCE(async_error); if (error) dpm_save_failed_step(SUSPEND_SUSPEND); dpm_show_time(starttime, state, error, NULL); trace_suspend_resume(TPS("dpm_suspend"), state.event, false); return error; } static bool device_prepare_smart_suspend(struct device *dev) { struct device_link *link; bool ret = true; int idx; /* * The "smart suspend" feature is enabled for devices whose drivers ask * for it and for devices without PM callbacks. * * However, if "smart suspend" is not enabled for the device's parent * or any of its suppliers that take runtime PM into account, it cannot * be enabled for the device either. */ if (!dev->power.no_pm_callbacks && !dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) return false; if (dev->parent && !dev_pm_smart_suspend(dev->parent) && !dev->parent->power.ignore_children && !pm_runtime_blocked(dev->parent)) return false; idx = device_links_read_lock(); dev_for_each_link_to_supplier(link, dev) { if (!device_link_test(link, DL_FLAG_PM_RUNTIME)) continue; if (!dev_pm_smart_suspend(link->supplier) && !pm_runtime_blocked(link->supplier)) { ret = false; break; } } device_links_read_unlock(idx); return ret; } /** * device_prepare - Prepare a device for system power transition. * @dev: Device to handle. * @state: PM transition of the system being carried out. * * Execute the ->prepare() callback(s) for given device. No new children of the * device may be registered after this function has returned. */ static int device_prepare(struct device *dev, pm_message_t state) { int (*callback)(struct device *) = NULL; bool smart_suspend; int ret = 0; /* * If a device's parent goes into runtime suspend at the wrong time, * it won't be possible to resume the device. To prevent this we * block runtime suspend here, during the prepare phase, and allow * it again during the complete phase. */ pm_runtime_get_noresume(dev); /* * If runtime PM is disabled for the device at this point and it has * never been enabled so far, it should not be enabled until this system * suspend-resume cycle is complete, so prepare to trigger a warning on * subsequent attempts to enable it. */ smart_suspend = !pm_runtime_block_if_disabled(dev); if (dev->power.syscore) return 0; device_lock(dev); dev->power.wakeup_path = false; dev->power.out_band_wakeup = false; if (dev->power.no_pm_callbacks) goto unlock; if (dev->pm_domain) callback = dev->pm_domain->ops.prepare; else if (dev->type && dev->type->pm) callback = dev->type->pm->prepare; else if (dev->class && dev->class->pm) callback = dev->class->pm->prepare; else if (dev->bus && dev->bus->pm) callback = dev->bus->pm->prepare; if (!callback && dev->driver && dev->driver->pm) callback = dev->driver->pm->prepare; if (callback) ret = callback(dev); unlock: device_unlock(dev); if (ret < 0) { suspend_report_result(dev, callback, ret); pm_runtime_put(dev); return ret; } /* Do not enable "smart suspend" for devices with disabled runtime PM. */ if (smart_suspend) smart_suspend = device_prepare_smart_suspend(dev); spin_lock_irq(&dev->power.lock); dev->power.smart_suspend = smart_suspend; /* * A positive return value from ->prepare() means "this device appears * to be runtime-suspended and its state is fine, so if it really is * runtime-suspended, you can leave it in that state provided that you * will do the same thing with all of its descendants". This only * applies to suspend transitions, however. */ dev->power.direct_complete = state.event == PM_EVENT_SUSPEND && (ret > 0 || dev->power.no_pm_callbacks) && !dev_pm_test_driver_flags(dev, DPM_FLAG_NO_DIRECT_COMPLETE); spin_unlock_irq(&dev->power.lock); return 0; } /** * dpm_prepare - Prepare all non-sysdev devices for a system PM transition. * @state: PM transition of the system being carried out. * * Execute the ->prepare() callback(s) for all devices. */ int dpm_prepare(pm_message_t state) { int error = 0; trace_suspend_resume(TPS("dpm_prepare"), state.event, true); /* * Give a chance for the known devices to complete their probes, before * disable probing of devices. This sync point is important at least * at boot time + hibernation restore. */ wait_for_device_probe(); /* * It is unsafe if probing of devices will happen during suspend or * hibernation and system behavior will be unpredictable in this case. * So, let's prohibit device's probing here and defer their probes * instead. The normal behavior will be restored in dpm_complete(). */ device_block_probing(); /* Suspend thermal control. */ thermal_pm_prepare(); mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_list) && !error) { struct device *dev = to_device(dpm_list.next); get_device(dev); mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); error = device_prepare(dev, state); trace_device_pm_callback_end(dev, error); mutex_lock(&dpm_list_mtx); if (!error) { dev->power.is_prepared = true; if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); } else if (error == -EAGAIN) { error = 0; } else { dev_info(dev, "not prepared for power transition: code %d\n", error); } mutex_unlock(&dpm_list_mtx); put_device(dev); mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); trace_suspend_resume(TPS("dpm_prepare"), state.event, false); return error; } /** * dpm_suspend_start - Prepare devices for PM transition and suspend them. * @state: PM transition of the system being carried out. * * Prepare all non-sysdev devices for system PM transition and execute "suspend" * callbacks for them. */ int dpm_suspend_start(pm_message_t state) { ktime_t starttime = ktime_get(); int error; error = dpm_prepare(state); if (error) dpm_save_failed_step(SUSPEND_PREPARE); else { pm_restrict_gfp_mask(); error = dpm_suspend(state); } dpm_show_time(starttime, state, error, "start"); return error; } EXPORT_SYMBOL_GPL(dpm_suspend_start); void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret) { if (ret) dev_err(dev, "%s(): %ps returns %d\n", function, fn, ret); } EXPORT_SYMBOL_GPL(__suspend_report_result); /** * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete. * @subordinate: Device that needs to wait for @dev. * @dev: Device to wait for. */ int device_pm_wait_for_dev(struct device *subordinate, struct device *dev) { dpm_wait(dev, subordinate->power.async_suspend); return async_error; } EXPORT_SYMBOL_GPL(device_pm_wait_for_dev); /** * dpm_for_each_dev - device iterator. * @data: data for the callback. * @fn: function to be called for each device. * * Iterate over devices in dpm_list, and call @fn for each device, * passing it @data. */ void dpm_for_each_dev(void *data, void (*fn)(struct device *, void *)) { struct device *dev; if (!fn) return; device_pm_lock(); list_for_each_entry(dev, &dpm_list, power.entry) fn(dev, data); device_pm_unlock(); } EXPORT_SYMBOL_GPL(dpm_for_each_dev); static bool pm_ops_is_empty(const struct dev_pm_ops *ops) { if (!ops) return true; return !ops->prepare && !ops->suspend && !ops->suspend_late && !ops->suspend_noirq && !ops->resume_noirq && !ops->resume_early && !ops->resume && !ops->complete; } void device_pm_check_callbacks(struct device *dev) { unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); dev->power.no_pm_callbacks = (!dev->bus || (pm_ops_is_empty(dev->bus->pm) && !dev->bus->suspend && !dev->bus->resume)) && (!dev->class || pm_ops_is_empty(dev->class->pm)) && (!dev->type || pm_ops_is_empty(dev->type->pm)) && (!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) && (!dev->driver || (pm_ops_is_empty(dev->driver->pm) && !dev->driver->suspend && !dev->driver->resume)); spin_unlock_irqrestore(&dev->power.lock, flags); } bool dev_pm_skip_suspend(struct device *dev) { return dev_pm_smart_suspend(dev) && pm_runtime_status_suspended(dev); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool.h> #include <linux/phy.h> #include <linux/slab.h> #include "common.h" #include "netlink.h" /* Channels A-D only; WORST and LINK are exclusive alternatives */ #define PHY_MSE_CHANNEL_COUNT 4 struct mse_req_info { struct ethnl_req_info base; }; struct mse_snapshot_entry { struct phy_mse_snapshot snapshot; int channel; }; struct mse_reply_data { struct ethnl_reply_data base; struct phy_mse_capability capability; struct mse_snapshot_entry *snapshots; unsigned int num_snapshots; }; static struct mse_reply_data * mse_repdata(const struct ethnl_reply_data *reply_base) { return container_of(reply_base, struct mse_reply_data, base); } const struct nla_policy ethnl_mse_get_policy[] = { [ETHTOOL_A_MSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int get_snapshot_if_supported(struct phy_device *phydev, struct mse_reply_data *data, unsigned int *idx, u32 cap_bit, enum phy_mse_channel channel) { int ret; if (data->capability.supported_caps & cap_bit) { ret = phydev->drv->get_mse_snapshot(phydev, channel, &data->snapshots[*idx].snapshot); if (ret) return ret; data->snapshots[*idx].channel = channel; (*idx)++; } return 0; } static int mse_get_channels(struct phy_device *phydev, struct mse_reply_data *data) { unsigned int i = 0; int ret; if (!data->capability.supported_caps) return 0; data->snapshots = kzalloc_objs(*data->snapshots, PHY_MSE_CHANNEL_COUNT); if (!data->snapshots) return -ENOMEM; /* Priority 1: Individual channels */ ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_A, PHY_MSE_CHANNEL_A); if (ret) return ret; ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_B, PHY_MSE_CHANNEL_B); if (ret) return ret; ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_C, PHY_MSE_CHANNEL_C); if (ret) return ret; ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_D, PHY_MSE_CHANNEL_D); if (ret) return ret; /* If any individual channels were found, we are done. */ if (i > 0) { data->num_snapshots = i; return 0; } /* Priority 2: Worst channel, if no individual channels supported. */ ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_WORST_CHANNEL, PHY_MSE_CHANNEL_WORST); if (ret) return ret; /* If worst channel was found, we are done. */ if (i > 0) { data->num_snapshots = i; return 0; } /* Priority 3: Link-wide, if nothing else is supported. */ ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_LINK, PHY_MSE_CHANNEL_LINK); if (ret) return ret; data->num_snapshots = i; return 0; } static int mse_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct mse_reply_data *data = mse_repdata(reply_base); struct net_device *dev = reply_base->dev; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, info->attrs, ETHTOOL_A_MSE_HEADER, info->extack); if (IS_ERR(phydev)) return PTR_ERR(phydev); if (!phydev) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret) return ret; mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_mse_capability || !phydev->drv->get_mse_snapshot) { ret = -EOPNOTSUPP; goto out_unlock; } if (!phydev->link) { ret = -ENETDOWN; goto out_unlock; } ret = phydev->drv->get_mse_capability(phydev, &data->capability); if (ret) goto out_unlock; ret = mse_get_channels(phydev, data); out_unlock: mutex_unlock(&phydev->lock); ethnl_ops_complete(dev); if (ret) kfree(data->snapshots); return ret; } static void mse_cleanup_data(struct ethnl_reply_data *reply_base) { struct mse_reply_data *data = mse_repdata(reply_base); kfree(data->snapshots); } static int mse_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct mse_reply_data *data = mse_repdata(reply_base); size_t len = 0; unsigned int i; /* ETHTOOL_A_MSE_CAPABILITIES */ len += nla_total_size(0); if (data->capability.supported_caps & PHY_MSE_CAP_AVG) /* ETHTOOL_A_MSE_CAPABILITIES_MAX_AVERAGE_MSE */ len += nla_total_size(sizeof(u64)); if (data->capability.supported_caps & (PHY_MSE_CAP_PEAK | PHY_MSE_CAP_WORST_PEAK)) /* ETHTOOL_A_MSE_CAPABILITIES_MAX_PEAK_MSE */ len += nla_total_size(sizeof(u64)); /* ETHTOOL_A_MSE_CAPABILITIES_REFRESH_RATE_PS */ len += nla_total_size(sizeof(u64)); /* ETHTOOL_A_MSE_CAPABILITIES_NUM_SYMBOLS */ len += nla_total_size(sizeof(u64)); for (i = 0; i < data->num_snapshots; i++) { size_t snapshot_len = 0; /* Per-channel nest (e.g., ETHTOOL_A_MSE_CHANNEL_A / _B / _C / * _D / _WORST_CHANNEL / _LINK) */ snapshot_len += nla_total_size(0); if (data->capability.supported_caps & PHY_MSE_CAP_AVG) snapshot_len += nla_total_size(sizeof(u64)); if (data->capability.supported_caps & PHY_MSE_CAP_PEAK) snapshot_len += nla_total_size(sizeof(u64)); if (data->capability.supported_caps & PHY_MSE_CAP_WORST_PEAK) snapshot_len += nla_total_size(sizeof(u64)); len += snapshot_len; } return len; } static int mse_channel_to_attr(int ch) { switch (ch) { case PHY_MSE_CHANNEL_A: return ETHTOOL_A_MSE_CHANNEL_A; case PHY_MSE_CHANNEL_B: return ETHTOOL_A_MSE_CHANNEL_B; case PHY_MSE_CHANNEL_C: return ETHTOOL_A_MSE_CHANNEL_C; case PHY_MSE_CHANNEL_D: return ETHTOOL_A_MSE_CHANNEL_D; case PHY_MSE_CHANNEL_WORST: return ETHTOOL_A_MSE_WORST_CHANNEL; case PHY_MSE_CHANNEL_LINK: return ETHTOOL_A_MSE_LINK; default: return -EINVAL; } } static int mse_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct mse_reply_data *data = mse_repdata(reply_base); struct nlattr *nest; unsigned int i; int ret; nest = nla_nest_start(skb, ETHTOOL_A_MSE_CAPABILITIES); if (!nest) return -EMSGSIZE; if (data->capability.supported_caps & PHY_MSE_CAP_AVG) { ret = nla_put_uint(skb, ETHTOOL_A_MSE_CAPABILITIES_MAX_AVERAGE_MSE, data->capability.max_average_mse); if (ret < 0) goto nla_put_nest_failure; } if (data->capability.supported_caps & (PHY_MSE_CAP_PEAK | PHY_MSE_CAP_WORST_PEAK)) { ret = nla_put_uint(skb, ETHTOOL_A_MSE_CAPABILITIES_MAX_PEAK_MSE, data->capability.max_peak_mse); if (ret < 0) goto nla_put_nest_failure; } ret = nla_put_uint(skb, ETHTOOL_A_MSE_CAPABILITIES_REFRESH_RATE_PS, data->capability.refresh_rate_ps); if (ret < 0) goto nla_put_nest_failure; ret = nla_put_uint(skb, ETHTOOL_A_MSE_CAPABILITIES_NUM_SYMBOLS, data->capability.num_symbols); if (ret < 0) goto nla_put_nest_failure; nla_nest_end(skb, nest); for (i = 0; i < data->num_snapshots; i++) { const struct mse_snapshot_entry *s = &data->snapshots[i]; int chan_attr; chan_attr = mse_channel_to_attr(s->channel); if (chan_attr < 0) return chan_attr; nest = nla_nest_start(skb, chan_attr); if (!nest) return -EMSGSIZE; if (data->capability.supported_caps & PHY_MSE_CAP_AVG) { ret = nla_put_uint(skb, ETHTOOL_A_MSE_SNAPSHOT_AVERAGE_MSE, s->snapshot.average_mse); if (ret) goto nla_put_nest_failure; } if (data->capability.supported_caps & PHY_MSE_CAP_PEAK) { ret = nla_put_uint(skb, ETHTOOL_A_MSE_SNAPSHOT_PEAK_MSE, s->snapshot.peak_mse); if (ret) goto nla_put_nest_failure; } if (data->capability.supported_caps & PHY_MSE_CAP_WORST_PEAK) { ret = nla_put_uint(skb, ETHTOOL_A_MSE_SNAPSHOT_WORST_PEAK_MSE, s->snapshot.worst_peak_mse); if (ret) goto nla_put_nest_failure; } nla_nest_end(skb, nest); } return 0; nla_put_nest_failure: nla_nest_cancel(skb, nest); return ret; } const struct ethnl_request_ops ethnl_mse_request_ops = { .request_cmd = ETHTOOL_MSG_MSE_GET, .reply_cmd = ETHTOOL_MSG_MSE_GET_REPLY, .hdr_attr = ETHTOOL_A_MSE_HEADER, .req_info_size = sizeof(struct mse_req_info), .reply_data_size = sizeof(struct mse_reply_data), .prepare_data = mse_prepare_data, .cleanup_data = mse_cleanup_data, .reply_size = mse_reply_size, .fill_reply = mse_fill_reply, }; |
| 10 11 1 10 6 6 6 6 5 5 6 6 11 1 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /******************************************************************************* * * Module Name: utstate - state object support procedures * ******************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #define _COMPONENT ACPI_UTILITIES ACPI_MODULE_NAME("utstate") /******************************************************************************* * * FUNCTION: acpi_ut_push_generic_state * * PARAMETERS: list_head - Head of the state stack * state - State object to push * * RETURN: None * * DESCRIPTION: Push a state object onto a state stack * ******************************************************************************/ void acpi_ut_push_generic_state(union acpi_generic_state **list_head, union acpi_generic_state *state) { ACPI_FUNCTION_ENTRY(); /* Push the state object onto the front of the list (stack) */ state->common.next = *list_head; *list_head = state; return; } /******************************************************************************* * * FUNCTION: acpi_ut_pop_generic_state * * PARAMETERS: list_head - Head of the state stack * * RETURN: The popped state object * * DESCRIPTION: Pop a state object from a state stack * ******************************************************************************/ union acpi_generic_state *acpi_ut_pop_generic_state(union acpi_generic_state **list_head) { union acpi_generic_state *state; ACPI_FUNCTION_ENTRY(); /* Remove the state object at the head of the list (stack) */ state = *list_head; if (state) { /* Update the list head */ *list_head = state->common.next; } return (state); } /******************************************************************************* * * FUNCTION: acpi_ut_create_generic_state * * PARAMETERS: None * * RETURN: The new state object. NULL on failure. * * DESCRIPTION: Create a generic state object. Attempt to obtain one from * the global state cache; If none available, create a new one. * ******************************************************************************/ union acpi_generic_state *acpi_ut_create_generic_state(void) { union acpi_generic_state *state; ACPI_FUNCTION_ENTRY(); state = acpi_os_acquire_object(acpi_gbl_state_cache); if (state) { /* Initialize */ state->common.descriptor_type = ACPI_DESC_TYPE_STATE; } return (state); } /******************************************************************************* * * FUNCTION: acpi_ut_create_thread_state * * PARAMETERS: None * * RETURN: New Thread State. NULL on failure * * DESCRIPTION: Create a "Thread State" - a flavor of the generic state used * to track per-thread info during method execution * ******************************************************************************/ struct acpi_thread_state *acpi_ut_create_thread_state(void) { union acpi_generic_state *state; ACPI_FUNCTION_ENTRY(); /* Create the generic state object */ state = acpi_ut_create_generic_state(); if (!state) { return (NULL); } /* Init fields specific to the update struct */ state->common.descriptor_type = ACPI_DESC_TYPE_STATE_THREAD; state->thread.thread_id = acpi_os_get_thread_id(); /* Check for invalid thread ID - zero is very bad, it will break things */ if (!state->thread.thread_id) { ACPI_ERROR((AE_INFO, "Invalid zero ID from AcpiOsGetThreadId")); state->thread.thread_id = (acpi_thread_id) 1; } return ((struct acpi_thread_state *)state); } /******************************************************************************* * * FUNCTION: acpi_ut_create_update_state * * PARAMETERS: object - Initial Object to be installed in the state * action - Update action to be performed * * RETURN: New state object, null on failure * * DESCRIPTION: Create an "Update State" - a flavor of the generic state used * to update reference counts and delete complex objects such * as packages. * ******************************************************************************/ union acpi_generic_state *acpi_ut_create_update_state(union acpi_operand_object *object, u16 action) { union acpi_generic_state *state; ACPI_FUNCTION_ENTRY(); /* Create the generic state object */ state = acpi_ut_create_generic_state(); if (!state) { return (NULL); } /* Init fields specific to the update struct */ state->common.descriptor_type = ACPI_DESC_TYPE_STATE_UPDATE; state->update.object = object; state->update.value = action; return (state); } /******************************************************************************* * * FUNCTION: acpi_ut_create_pkg_state * * PARAMETERS: object - Initial Object to be installed in the state * action - Update action to be performed * * RETURN: New state object, null on failure * * DESCRIPTION: Create a "Package State" * ******************************************************************************/ union acpi_generic_state *acpi_ut_create_pkg_state(void *internal_object, void *external_object, u32 index) { union acpi_generic_state *state; ACPI_FUNCTION_ENTRY(); /* Create the generic state object */ state = acpi_ut_create_generic_state(); if (!state) { return (NULL); } /* Init fields specific to the update struct */ state->common.descriptor_type = ACPI_DESC_TYPE_STATE_PACKAGE; state->pkg.source_object = (union acpi_operand_object *)internal_object; state->pkg.dest_object = external_object; state->pkg.index = index; state->pkg.num_packages = 1; return (state); } /******************************************************************************* * * FUNCTION: acpi_ut_create_control_state * * PARAMETERS: None * * RETURN: New state object, null on failure * * DESCRIPTION: Create a "Control State" - a flavor of the generic state used * to support nested IF/WHILE constructs in the AML. * ******************************************************************************/ union acpi_generic_state *acpi_ut_create_control_state(void) { union acpi_generic_state *state; ACPI_FUNCTION_ENTRY(); /* Create the generic state object */ state = acpi_ut_create_generic_state(); if (!state) { return (NULL); } /* Init fields specific to the control struct */ state->common.descriptor_type = ACPI_DESC_TYPE_STATE_CONTROL; state->common.state = ACPI_CONTROL_CONDITIONAL_EXECUTING; return (state); } /******************************************************************************* * * FUNCTION: acpi_ut_delete_generic_state * * PARAMETERS: state - The state object to be deleted * * RETURN: None * * DESCRIPTION: Release a state object to the state cache. NULL state objects * are ignored. * ******************************************************************************/ void acpi_ut_delete_generic_state(union acpi_generic_state *state) { ACPI_FUNCTION_ENTRY(); /* Ignore null state */ if (state) { (void)acpi_os_release_object(acpi_gbl_state_cache, state); } return; } |
| 140 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_TABLES_IPV4_H_ #define _NF_TABLES_IPV4_H_ #include <net/netfilter/nf_tables.h> #include <net/ip.h> static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt) { struct iphdr *ip; ip = ip_hdr(pkt->skb); pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = ip->protocol; pkt->ethertype = pkt->skb->protocol; pkt->nhoff = 0; pkt->thoff = ip_hdrlen(pkt->skb); pkt->fragoff = ntohs(ip->frag_off) & IP_OFFSET; } static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, int nhoff) { struct iphdr *iph, _iph; u32 len, thoff, skb_len; iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb) + nhoff, sizeof(*iph), &_iph); if (!iph) return -1; if (iph->ihl < 5 || iph->version != 4) return -1; len = iph_totlen(pkt->skb, iph); thoff = iph->ihl * 4; skb_len = pkt->skb->len - skb_network_offset(pkt->skb) - nhoff; if (skb_len < len) return -1; else if (len < thoff) return -1; else if (thoff < sizeof(*iph)) return -1; pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = iph->protocol; pkt->ethertype = pkt->skb->protocol; pkt->nhoff = nhoff; pkt->thoff = skb_network_offset(pkt->skb) + nhoff + thoff; pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; } static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { if (__nft_set_pktinfo_ipv4_validate(pkt, 0) < 0) nft_set_pktinfo_unspec(pkt); } static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) { struct iphdr *iph; u32 len, thoff; if (!pskb_may_pull(pkt->skb, sizeof(*iph))) return -1; iph = ip_hdr(pkt->skb); if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; len = iph_totlen(pkt->skb, iph); thoff = iph->ihl * 4; if (pkt->skb->len < len) { __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); return -1; } else if (len < thoff) { goto inhdr_error; } else if (thoff < sizeof(*iph)) { return -1; } pkt->flags = NFT_PKTINFO_L4PROTO; pkt->ethertype = pkt->skb->protocol; pkt->nhoff = 0; pkt->tprot = iph->protocol; pkt->thoff = thoff; pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; inhdr_error: __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INHDRERRORS); return -1; } #endif |
| 5857 5859 1 23 23 25 25 25 153 12493 12243 1 12252 12249 12244 12250 12484 12493 12246 12286 12241 7098 12520 13362 13363 1 62 65 77 518 401 6 574 13104 13103 2 1 13096 14639 14656 1 1 1 1 683 684 27 26 27 25 189 5969 9001 13368 13421 11425 13360 10 68 68 57 11397 2 11393 11425 5 5 11395 473 425 464 10 10 211 283 614 626 1 1 614 11 11 613 625 11 614 476 3 473 206 278 87 399 6 7 213 282 77 414 462 2 17 462 11 11240 1182 11240 110 11164 2938 11246 1747 1745 9181 9191 65 59 65 4 14 49 78 13 69 5 5 6 5 1 64 3 5 8 49 48 17 38 50 8 12 41 19 40 6 18 27 40 5 44 39 39 39 10 17 4 3 1 9 2 3 6 23 4 19 19 233 13352 13356 8 14 3 2 2 9 12 13354 13025 373 2 9613 9608 9621 31 30 31 7 7 1 7 7 7 7 1144 12232 9590 9605 9601 2 2 15529 15532 15519 15490 2644 584 13393 13391 13293 13353 13374 13395 13393 18 32 9588 4246 4244 372 51 1442 1431 3 4328 1447 3982 3 1444 9 1197 296 296 1449 1450 2 1444 3 1451 51 1450 5420 3265 5051 5421 5042 35 5321 1419 33 2844 25 25 25 25 57 2 55 36 33 5 11 16 22 3 3 3 2 1 4 2 3 5 17 18 2 3 1 1 4 2 6 2 1 2 4 5 4 4 13376 1 232 13411 12 1 2 462 13159 11222 2884 1 13364 3 13301 63 13296 581 1 82 568 2 472 178 387 190 565 4 566 4 525 46 437 243 3 579 153 153 153 153 11 11 14249 10162 10141 3 10 2 5 6 11 1 10 11 1 3 7 4 6 9 1 10 1144 1146 1144 3 1584 1453 244 1 1396 256 1385 5 1587 1582 1591 1 1531 67 1 1575 672 1147 3 1144 595 551 1559 1565 1558 1 723 730 1440 113 115 9126 1433 8222 1428 8250 8229 9126 8 11724 11645 452 46 85 1387 10409 8374 3789 3285 893 3284 892 10 3 8 10 10 10 10 5 10 10 8 3 10 10 10 10 10 10 3 8 10 153 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NETLINK Kernel-user communication protocol. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Patrick McHardy <kaber@trash.net> * * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith * added netlink_proto_exit * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br> * use nlk_sk, as sk->protinfo is on a diet 8) * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org> * - inc module use count of module that owns * the kernel socket in case userspace opens * socket of same protocol * - remove all module support, since netlink is * mandatory if CONFIG_NET=y these days */ #include <linux/module.h> #include <linux/bpf.h> #include <linux/capability.h> #include <linux/kernel.h> #include <linux/filter.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/un.h> #include <linux/fcntl.h> #include <linux/termios.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/uio.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/security.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/bitops.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/audit.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> #include <linux/rhashtable.h> #include <asm/cacheflush.h> #include <linux/hash.h> #include <linux/net_namespace.h> #include <linux/nospec.h> #include <linux/btf_ids.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/scm.h> #include <net/netlink.h> #define CREATE_TRACE_POINTS #include <trace/events/netlink.h> #include "af_netlink.h" #include "genetlink.h" struct listeners { struct rcu_head rcu; unsigned long masks[]; }; /* state bits */ #define NETLINK_S_CONGESTED 0x0 static inline int netlink_is_kernel(struct sock *sk) { return nlk_test_bit(KERNEL_SOCKET, sk); } struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS]; static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { "nlk_cb_mutex-ROUTE", "nlk_cb_mutex-1", "nlk_cb_mutex-USERSOCK", "nlk_cb_mutex-FIREWALL", "nlk_cb_mutex-SOCK_DIAG", "nlk_cb_mutex-NFLOG", "nlk_cb_mutex-XFRM", "nlk_cb_mutex-SELINUX", "nlk_cb_mutex-ISCSI", "nlk_cb_mutex-AUDIT", "nlk_cb_mutex-FIB_LOOKUP", "nlk_cb_mutex-CONNECTOR", "nlk_cb_mutex-NETFILTER", "nlk_cb_mutex-IP6_FW", "nlk_cb_mutex-DNRTMSG", "nlk_cb_mutex-KOBJECT_UEVENT", "nlk_cb_mutex-GENERIC", "nlk_cb_mutex-17", "nlk_cb_mutex-SCSITRANSPORT", "nlk_cb_mutex-ECRYPTFS", "nlk_cb_mutex-RDMA", "nlk_cb_mutex-CRYPTO", "nlk_cb_mutex-SMC", "nlk_cb_mutex-23", "nlk_cb_mutex-24", "nlk_cb_mutex-25", "nlk_cb_mutex-26", "nlk_cb_mutex-27", "nlk_cb_mutex-28", "nlk_cb_mutex-29", "nlk_cb_mutex-30", "nlk_cb_mutex-31", "nlk_cb_mutex-MAX_LINKS" }; static int netlink_dump(struct sock *sk, bool lock_taken); /* nl_table locking explained: * Lookup and traversal are protected with an RCU read-side lock. Insertion * and removal are protected with per bucket lock while using RCU list * modification primitives and may run in parallel to RCU protected lookups. * Destruction of the Netlink socket may only occur *after* nl_table_lock has * been acquired * either during or after the socket has been removed from * the list and after an RCU grace period. */ DEFINE_RWLOCK(nl_table_lock); EXPORT_SYMBOL_GPL(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); static BLOCKING_NOTIFIER_HEAD(netlink_chain); static const struct rhashtable_params netlink_rhashtable_params; void do_trace_netlink_extack(const char *msg) { trace_netlink_extack(msg); } EXPORT_SYMBOL(do_trace_netlink_extack); static inline u32 netlink_group_mask(u32 group) { if (group > 32) return 0; return group ? 1 << (group - 1) : 0; } static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); if (new == NULL) return NULL; NETLINK_CB(new).portid = NETLINK_CB(skb).portid; NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; NETLINK_CB(new).creds = NETLINK_CB(skb).creds; skb_put_data(new, skb->data, len); return new; } static unsigned int netlink_tap_net_id; struct netlink_tap_net { struct list_head netlink_tap_all; struct mutex netlink_tap_lock; }; int netlink_add_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); if (unlikely(nt->dev->type != ARPHRD_NETLINK)) return -EINVAL; mutex_lock(&nn->netlink_tap_lock); list_add_rcu(&nt->list, &nn->netlink_tap_all); mutex_unlock(&nn->netlink_tap_lock); __module_get(nt->module); return 0; } EXPORT_SYMBOL_GPL(netlink_add_tap); static int __netlink_remove_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); bool found = false; struct netlink_tap *tmp; mutex_lock(&nn->netlink_tap_lock); list_for_each_entry(tmp, &nn->netlink_tap_all, list) { if (nt == tmp) { list_del_rcu(&nt->list); found = true; goto out; } } pr_warn("__netlink_remove_tap: %p not found\n", nt); out: mutex_unlock(&nn->netlink_tap_lock); if (found) module_put(nt->module); return found ? 0 : -ENODEV; } int netlink_remove_tap(struct netlink_tap *nt) { int ret; ret = __netlink_remove_tap(nt); synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(netlink_remove_tap); static __net_init int netlink_tap_init_net(struct net *net) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); INIT_LIST_HEAD(&nn->netlink_tap_all); mutex_init(&nn->netlink_tap_lock); return 0; } static struct pernet_operations netlink_tap_net_ops = { .init = netlink_tap_init_net, .id = &netlink_tap_net_id, .size = sizeof(struct netlink_tap_net), }; static bool netlink_filter_tap(const struct sk_buff *skb) { struct sock *sk = skb->sk; /* We take the more conservative approach and * whitelist socket protocols that may pass. */ switch (sk->sk_protocol) { case NETLINK_ROUTE: case NETLINK_USERSOCK: case NETLINK_SOCK_DIAG: case NETLINK_NFLOG: case NETLINK_XFRM: case NETLINK_FIB_LOOKUP: case NETLINK_NETFILTER: case NETLINK_GENERIC: return true; } return false; } static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *nskb; struct sock *sk = skb->sk; int ret = -ENOMEM; if (!net_eq(dev_net(dev), sock_net(sk))) return 0; dev_hold(dev); if (is_vmalloc_addr(skb->head)) nskb = netlink_to_full_skb(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); } dev_put(dev); return ret; } static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn) { int ret; struct netlink_tap *tmp; if (!netlink_filter_tap(skb)) return; list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) { ret = __netlink_deliver_tap_skb(skb, tmp->dev); if (unlikely(ret)) break; } } static void netlink_deliver_tap(struct net *net, struct sk_buff *skb) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); rcu_read_lock(); if (unlikely(!list_empty(&nn->netlink_tap_all))) __netlink_deliver_tap(skb, nn); rcu_read_unlock(); } static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, struct sk_buff *skb) { if (!(netlink_is_kernel(dst) && netlink_is_kernel(src))) netlink_deliver_tap(sock_net(dst), skb); } static void netlink_overrun(struct sock *sk) { if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { WRITE_ONCE(sk->sk_err, ENOBUFS); sk_error_report(sk); } } sk_drops_inc(sk); } static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); } static void netlink_skb_destructor(struct sk_buff *skb) { if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) vfree_atomic(skb->head); skb->head = NULL; } if (skb->sk != NULL) sock_rfree(skb); } static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; sk_mem_charge(sk, skb->truesize); } static void netlink_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(nlk_sk(sk)->groups); } /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves * this, _but_ remember, it adds useless work on UP machines. */ void netlink_table_grab(void) __acquires(nl_table_lock) { might_sleep(); write_lock_irq(&nl_table_lock); if (atomic_read(&nl_table_users)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&nl_table_wait, &wait); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&nl_table_users) == 0) break; write_unlock_irq(&nl_table_lock); schedule(); write_lock_irq(&nl_table_lock); } __set_current_state(TASK_RUNNING); remove_wait_queue(&nl_table_wait, &wait); } } void netlink_table_ungrab(void) __releases(nl_table_lock) { write_unlock_irq(&nl_table_lock); wake_up(&nl_table_wait); } static inline void netlink_lock_table(void) { unsigned long flags; /* read_lock() synchronizes us to netlink_table_grab */ read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); read_unlock_irqrestore(&nl_table_lock, flags); } static inline void netlink_unlock_table(void) { if (atomic_dec_and_test(&nl_table_users)) wake_up(&nl_table_wait); } struct netlink_compare_arg { possible_net_t pnet; u32 portid; }; /* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ #define netlink_compare_arg_len \ (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) static inline int netlink_compare(struct rhashtable_compare_arg *arg, const void *ptr) { const struct netlink_compare_arg *x = arg->key; const struct netlink_sock *nlk = ptr; return nlk->portid != x->portid || !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); } static void netlink_compare_arg_init(struct netlink_compare_arg *arg, struct net *net, u32 portid) { memset(arg, 0, sizeof(*arg)); write_pnet(&arg->pnet, net); arg->portid = portid; } static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, struct net *net) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, net, portid); return rhashtable_lookup_fast(&table->hash, &arg, netlink_rhashtable_params); } static int __netlink_insert(struct netlink_table *table, struct sock *sk) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); return rhashtable_lookup_insert_key(&table->hash, &arg, &nlk_sk(sk)->node, netlink_rhashtable_params); } static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { struct netlink_table *table = &nl_table[protocol]; struct sock *sk; rcu_read_lock(); sk = __netlink_lookup(table, portid, net); if (sk) sock_hold(sk); rcu_read_unlock(); return sk; } static const struct proto_ops netlink_ops; static void netlink_update_listeners(struct sock *sk) { struct netlink_table *tbl = &nl_table[sk->sk_protocol]; unsigned long mask; unsigned int i; struct listeners *listeners; listeners = nl_deref_protected(tbl->listeners); if (!listeners) return; for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; sk_for_each_bound(sk, &tbl->mc_list) { if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } listeners->masks[i] = mask; } /* this function is only called with the netlink table "grabbed", which * makes sure updates are visible before bind or setsockopt return. */ } static int netlink_insert(struct sock *sk, u32 portid) { struct netlink_table *table = &nl_table[sk->sk_protocol]; int err; lock_sock(sk); err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; if (nlk_sk(sk)->bound) goto err; /* portid can be read locklessly from netlink_getname(). */ WRITE_ONCE(nlk_sk(sk)->portid, portid); sock_hold(sk); err = __netlink_insert(table, sk); if (err) { /* In case the hashtable backend returns with -EBUSY * from here, it must not escape to the caller. */ if (unlikely(err == -EBUSY)) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; sock_put(sk); goto err; } /* We need to ensure that the socket is hashed and visible. */ smp_wmb(); /* Paired with lockless reads from netlink_bind(), * netlink_connect() and netlink_sendmsg(). */ WRITE_ONCE(nlk_sk(sk)->bound, portid); err: release_sock(sk); return err; } static void netlink_remove(struct sock *sk) { struct netlink_table *table; table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, netlink_rhashtable_params)) __sock_put(sk); netlink_table_grab(); if (nlk_sk(sk)->subscriptions) { __sk_del_bind_node(sk); netlink_update_listeners(sk); } if (sk->sk_protocol == NETLINK_GENERIC) atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } static struct proto netlink_proto = { .name = "NETLINK", .owner = THIS_MODULE, .obj_size = sizeof(struct netlink_sock), }; static int __netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct netlink_sock *nlk; sock->ops = &netlink_ops; sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); nlk = nlk_sk(sk); mutex_init(&nlk->nl_cb_mutex); lockdep_set_class_and_name(&nlk->nl_cb_mutex, nlk_cb_mutex_keys + protocol, nlk_cb_mutex_key_strings[protocol]); init_waitqueue_head(&nlk->wait); sk->sk_destruct = netlink_sock_destruct; sk->sk_protocol = protocol; return 0; } static int netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct module *module = NULL; struct netlink_sock *nlk; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); void (*release)(struct sock *sock, unsigned long *groups); int err = 0; sock->state = SS_UNCONNECTED; if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES if (!nl_table[protocol].registered) { netlink_unlock_table(); request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); netlink_lock_table(); } #endif if (nl_table[protocol].registered && try_module_get(nl_table[protocol].module)) module = nl_table[protocol].module; else err = -EPROTONOSUPPORT; bind = nl_table[protocol].bind; unbind = nl_table[protocol].unbind; release = nl_table[protocol].release; netlink_unlock_table(); if (err < 0) goto out; err = __netlink_create(net, sock, protocol, kern); if (err < 0) goto out_module; sock_prot_inuse_add(net, &netlink_proto, 1); nlk = nlk_sk(sock->sk); nlk->module = module; nlk->netlink_bind = bind; nlk->netlink_unbind = unbind; nlk->netlink_release = release; out: return err; out_module: module_put(module); goto out; } static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); struct sock *sk = &nlk->sk; kfree(nlk->groups); nlk->groups = NULL; if (!refcount_dec_and_test(&sk->sk_refcnt)) return; sk_free(sk); } static int netlink_release(struct socket *sock) { struct sock *sk = sock->sk; struct netlink_sock *nlk; if (!sk) return 0; netlink_remove(sk); sock_orphan(sk); nlk = nlk_sk(sk); /* * OK. Socket is unlinked, any packets that arrive now * will be purged. */ if (nlk->netlink_release) nlk->netlink_release(sk, nlk->groups); /* must not acquire netlink_table_lock in any way again before unbind * and notifying genetlink is done as otherwise it might deadlock */ if (nlk->netlink_unbind) { int i; for (i = 0; i < nlk->ngroups; i++) if (test_bit(i, nlk->groups)) nlk->netlink_unbind(sock_net(sk), i + 1); } if (sk->sk_protocol == NETLINK_GENERIC && atomic_dec_return(&genl_sk_destructing_cnt) == 0) wake_up(&genl_sk_destructing_waitq); sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); skb_queue_purge(&sk->sk_write_queue); if (nlk->portid && nlk->bound) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, .portid = nlk->portid, }; blocking_notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n); } /* Terminate any outstanding dump */ if (nlk->cb_running) { if (nlk->cb.done) nlk->cb.done(&nlk->cb); module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); WRITE_ONCE(nlk->cb_running, false); } module_put(nlk->module); if (netlink_is_kernel(sk)) { netlink_table_grab(); BUG_ON(nl_table[sk->sk_protocol].registered == 0); if (--nl_table[sk->sk_protocol].registered == 0) { struct listeners *old; old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; nl_table[sk->sk_protocol].unbind = NULL; nl_table[sk->sk_protocol].flags = 0; nl_table[sk->sk_protocol].registered = 0; } netlink_table_ungrab(); } sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_table *table = &nl_table[sk->sk_protocol]; s32 portid = task_tgid_vnr(current); int err; s32 rover = -4096; bool ok; retry: cond_resched(); rcu_read_lock(); ok = !__netlink_lookup(table, portid, net); rcu_read_unlock(); if (!ok) { /* Bind collision, search negative portid values. */ if (rover == -4096) /* rover will be in range [S32_MIN, -4097] */ rover = S32_MIN + get_random_u32_below(-4096 - S32_MIN); else if (rover >= -4096) rover = -4097; portid = rover--; goto retry; } err = netlink_insert(sk, portid); if (err == -EADDRINUSE) goto retry; /* If 2 threads race to autobind, that is fine. */ if (err == -EBUSY) err = 0; return err; } /** * __netlink_ns_capable - General netlink message capability test * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) { return ((nsp->flags & NETLINK_SKB_DST) || file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(__netlink_ns_capable); /** * netlink_ns_capable - General netlink message capability test * @skb: socket buffer holding a netlink command from userspace * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) { return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); } EXPORT_SYMBOL(netlink_ns_capable); /** * netlink_capable - Netlink global message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, &init_user_ns, cap); } EXPORT_SYMBOL(netlink_capable); /** * netlink_net_capable - Netlink network namespace message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); } EXPORT_SYMBOL(netlink_net_capable); static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); } static void netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions) { struct netlink_sock *nlk = nlk_sk(sk); if (nlk->subscriptions && !subscriptions) __sk_del_bind_node(sk); else if (!nlk->subscriptions && subscriptions) sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); nlk->subscriptions = subscriptions; } static int netlink_realloc_groups(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); unsigned int groups; unsigned long *new_groups; int err = 0; netlink_table_grab(); groups = nl_table[sk->sk_protocol].groups; if (!nl_table[sk->sk_protocol].registered) { err = -ENOENT; goto out_unlock; } if (nlk->ngroups >= groups) goto out_unlock; new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC); if (new_groups == NULL) { err = -ENOMEM; goto out_unlock; } memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); nlk->groups = new_groups; nlk->ngroups = groups; out_unlock: netlink_table_ungrab(); return err; } static void netlink_undo_bind(int group, long unsigned int groups, struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); int undo; if (!nlk->netlink_unbind) return; for (undo = 0; undo < group; undo++) if (test_bit(undo, &groups)) nlk->netlink_unbind(sock_net(sk), undo + 1); } static int netlink_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; unsigned long groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; if (nladdr->nl_family != AF_NETLINK) return -EINVAL; groups = nladdr->nl_groups; /* Only superuser is allowed to listen multicasts */ if (groups) { if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; } if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; /* Paired with WRITE_ONCE() in netlink_insert() */ bound = READ_ONCE(nlk->bound); if (bound) { /* Ensure nlk->portid is up-to-date. */ smp_rmb(); if (nladdr->nl_pid != nlk->portid) return -EINVAL; } if (nlk->netlink_bind && groups) { int group; /* nl_groups is a u32, so cap the maximum groups we can bind */ for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); if (!err) continue; netlink_undo_bind(group, groups, sk); return err; } } /* No need for barriers here as we return to user-space without * using any of the bound attributes. */ netlink_lock_table(); if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) goto unlock; netlink_unlock_table(); netlink_table_grab(); netlink_update_subscriptions(sk, nlk->subscriptions + hweight32(groups) - hweight32(nlk->groups[0])); nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; netlink_update_listeners(sk); netlink_table_ungrab(); return 0; unlock: netlink_unlock_table(); return err; } static int netlink_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { int err = 0; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; if (alen < sizeof(addr->sa_family)) return -EINVAL; if (addr->sa_family == AF_UNSPEC) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, 0); WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) return -EINVAL; if (alen < sizeof(struct sockaddr_nl)) return -EINVAL; if ((nladdr->nl_groups || nladdr->nl_pid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; /* No need for barriers here as we return to user-space without * using any of the bound attributes. * Paired with WRITE_ONCE() in netlink_insert(). */ if (!READ_ONCE(nlk->bound)) err = netlink_autobind(sock); if (err == 0) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; } static int netlink_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; if (peer) { /* Paired with WRITE_ONCE() in netlink_connect() */ nladdr->nl_pid = READ_ONCE(nlk->dst_portid); nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { /* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); } return sizeof(*nladdr); } static int netlink_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* try to hand this ioctl down to the NIC drivers. */ return -ENOIOCTLCMD; } static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) { struct sock *sock; struct netlink_sock *nlk; sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); if (!sock) return ERR_PTR(-ECONNREFUSED); /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); /* dst_portid and sk_state can be changed in netlink_connect() */ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } return sock; } struct sock *netlink_getsockbyfd(int fd) { CLASS(fd, f)(fd); struct inode *inode; struct sock *sock; if (fd_empty(f)) return ERR_PTR(-EBADF); inode = file_inode(fd_file(f)); if (!S_ISSOCK(inode->i_mode)) return ERR_PTR(-ENOTSOCK); sock = SOCKET_I(inode)->sk; if (sock->sk_family != AF_NETLINK) return ERR_PTR(-EINVAL); sock_hold(sock); return sock; } struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) { size_t head_size = SKB_HEAD_ALIGN(size); struct sk_buff *skb; void *data; if (head_size <= PAGE_SIZE || broadcast) return alloc_skb(size, GFP_KERNEL); data = kvmalloc(head_size, GFP_KERNEL); if (!data) return NULL; skb = __build_skb(data, head_size); if (!skb) kvfree(data); else if (is_vmalloc_addr(data)) skb->destructor = netlink_skb_destructor; return skb; } /* * Attach a skb to a netlink socket. * The caller must hold a reference to the destination socket. On error, the * reference is dropped. The skb is not send to the destination, just all * all error checks are performed and memory in the queue is reserved. * Return values: * < 0: error. skb freed, reference to sock dropped. * 0: continue * 1: repeat lookup - reference dropped while waiting for socket memory. */ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { DECLARE_WAITQUEUE(wait, current); struct netlink_sock *nlk; unsigned int rmem; nlk = nlk_sk(sk); rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); if ((rmem == skb->truesize || rmem <= READ_ONCE(sk->sk_rcvbuf)) && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); return 0; } atomic_sub(skb->truesize, &sk->sk_rmem_alloc); if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) netlink_overrun(sk); sock_put(sk); kfree_skb(skb); return -EAGAIN; } __set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&nlk->wait, &wait); rmem = atomic_read(&sk->sk_rmem_alloc); if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) || test_bit(NETLINK_S_CONGESTED, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) *timeo = schedule_timeout(*timeo); __set_current_state(TASK_RUNNING); remove_wait_queue(&nlk->wait, &wait); sock_put(sk); if (signal_pending(current)) { kfree_skb(skb); return sock_intr_errno(*timeo); } return 1; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = skb->len; netlink_deliver_tap(sock_net(sk), skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); return len; } int netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = __netlink_sendskb(sk, skb); sock_put(sk); return len; } void netlink_detachskb(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); sock_put(sk); } static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) { int delta; skb_assert_len(skb); WARN_ON(skb->sk != NULL); delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) return skb; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, allocation); if (!nskb) return skb; consume_skb(skb); skb = nskb; } pskb_expand_head(skb, 0, -delta, (allocation & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); return skb; } static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, struct sock *ssk) { int ret; struct netlink_sock *nlk = nlk_sk(sk); ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; atomic_add(skb->truesize, &sk->sk_rmem_alloc); netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); nlk->netlink_rcv(skb); consume_skb(skb); } else { kfree_skb(skb); } sock_put(sk); return ret; } int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 portid, int nonblock) { struct sock *sk; int err; long timeo; skb = netlink_trim(skb, gfp_any()); timeo = sock_sndtimeo(ssk, nonblock); retry: sk = netlink_getsockbyportid(ssk, portid); if (IS_ERR(sk)) { kfree_skb(skb); return PTR_ERR(sk); } if (netlink_is_kernel(sk)) return netlink_unicast_kernel(sk, skb, ssk); if (sk_filter(sk, skb)) { err = skb->len; kfree_skb(skb); sock_put(sk); return err; } err = netlink_attachskb(sk, skb, &timeo, ssk); if (err == 1) goto retry; if (err) return err; return netlink_sendskb(sk, skb); } EXPORT_SYMBOL(netlink_unicast); int netlink_has_listeners(struct sock *sk, unsigned int group) { int res = 0; struct listeners *listeners; BUG_ON(!netlink_is_kernel(sk)); rcu_read_lock(); listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) res = test_bit(group - 1, listeners->masks); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(netlink_has_listeners); bool netlink_strict_get_check(struct sk_buff *skb) { return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); } EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); unsigned int rmem, rcvbuf; rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); rcvbuf = READ_ONCE(sk->sk_rcvbuf); if ((rmem == skb->truesize || rmem <= rcvbuf) && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); return rmem > (rcvbuf >> 1); } atomic_sub(skb->truesize, &sk->sk_rmem_alloc); return -1; } struct netlink_broadcast_data { struct sock *exclude_sk; struct net *net; u32 portid; u32 group; int failure; int delivery_failure; int congested; int delivered; gfp_t allocation; struct sk_buff *skb, *skb2; int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); void *tx_data; }; static void do_one_broadcast(struct sock *sk, struct netlink_broadcast_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int val; if (p->exclude_sk == sk) return; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) return; if (!net_eq(sock_net(sk), p->net)) { if (!nlk_test_bit(LISTEN_ALL_NSID, sk)) return; if (!peernet_has_id(sock_net(sk), p->net)) return; if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns, CAP_NET_BROADCAST)) return; } if (p->failure) { netlink_overrun(sk); return; } sock_hold(sk); if (p->skb2 == NULL) { if (skb_shared(p->skb)) { p->skb2 = skb_clone(p->skb, p->allocation); } else { p->skb2 = skb_get(p->skb); /* * skb ownership may have been set when * delivered to a previous socket. */ skb_orphan(p->skb2); } } if (p->skb2 == NULL) { netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; goto out; } if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } NETLINK_CB(p->skb2).nsid_is_set = false; if (!net_eq(sock_net(sk), p->net)) { NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED) NETLINK_CB(p->skb2).nsid_is_set = true; } val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; p->skb2 = NULL; } out: sock_put(sk); } int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation, netlink_filter_fn filter, void *filter_data) { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; struct sock *sk; skb = netlink_trim(skb, allocation); info.exclude_sk = ssk; info.net = net; info.portid = portid; info.group = group; info.failure = 0; info.delivery_failure = 0; info.congested = 0; info.delivered = 0; info.allocation = allocation; info.skb = skb; info.skb2 = NULL; info.tx_filter = filter; info.tx_data = filter_data; /* While we sleep in clone, do not allow to change socket list */ netlink_lock_table(); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); consume_skb(skb); netlink_unlock_table(); if (info.delivery_failure) { kfree_skb(info.skb2); return -ENOBUFS; } consume_skb(info.skb2); if (info.delivered) { if (info.congested && gfpflags_allow_blocking(allocation)) yield(); return 0; } return -ESRCH; } EXPORT_SYMBOL(netlink_broadcast_filtered); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation) { return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, NULL, NULL); } EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { struct sock *exclude_sk; u32 portid; u32 group; int code; }; static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int ret = 0; if (sk == p->exclude_sk) goto out; if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) goto out; if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) { ret = 1; goto out; } WRITE_ONCE(sk->sk_err, p->code); sk_error_report(sk); out: return ret; } /** * netlink_set_err - report error to broadcast listeners * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_NO_ENOBUFS socket option. */ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; unsigned long flags; struct sock *sk; int ret = 0; info.exclude_sk = ssk; info.portid = portid; info.group = group; /* sk->sk_err wants a positive error value */ info.code = -code; read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); /* must be called with netlink table grabbed */ static void netlink_update_socket_mc(struct netlink_sock *nlk, unsigned int group, int is_new) { int old, new = !!is_new, subscriptions; old = test_bit(group - 1, nlk->groups); subscriptions = nlk->subscriptions - old + new; __assign_bit(group - 1, nlk->groups, new); netlink_update_subscriptions(&nlk->sk, subscriptions); netlink_update_listeners(&nlk->sk); } static int netlink_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int val = 0; int nr = -1; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (optlen >= sizeof(int) && copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case NETLINK_PKTINFO: nr = NETLINK_F_RECV_PKTINFO; break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { int err; if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; if (!val || val - 1 >= nlk->ngroups) return -EINVAL; if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { err = nlk->netlink_bind(sock_net(sk), val); if (err) return err; } netlink_table_grab(); netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) nlk->netlink_unbind(sock_net(sk), val); break; } case NETLINK_BROADCAST_ERROR: nr = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val); if (val) { clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); } break; case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; nr = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: nr = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: nr = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: nr = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (nr >= 0) assign_bit(nr, &nlk->flags, val); return 0; } static int netlink_getsockopt(struct socket *sock, int level, int optname, sockopt_t *opt) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int flag; int len, val; u32 group; if (level != SOL_NETLINK) return -ENOPROTOOPT; len = opt->optlen; if (len < 0) return -EINVAL; switch (optname) { case NETLINK_PKTINFO: flag = NETLINK_F_RECV_PKTINFO; break; case NETLINK_BROADCAST_ERROR: flag = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: flag = NETLINK_F_RECV_NO_ENOBUFS; break; case NETLINK_LIST_MEMBERSHIPS: { int pos, idx, shift, err = 0; netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; idx = pos / sizeof(unsigned long); shift = (pos % sizeof(unsigned long)) * 8; group = (u32)(nlk->groups[idx] >> shift); if (copy_to_iter(&group, sizeof(u32), &opt->iter_out) != sizeof(u32)) { err = -EFAULT; break; } } opt->optlen = ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)); netlink_unlock_table(); return err; } case NETLINK_LISTEN_ALL_NSID: flag = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: flag = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: flag = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: flag = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = test_bit(flag, &nlk->flags); opt->optlen = len; if (copy_to_iter(&val, len, &opt->iter_out) != len) return -EFAULT; return 0; } static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct nl_pktinfo info; info.group = NETLINK_CB(skb).dst_group; put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); } static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { if (!NETLINK_CB(skb).nsid_is_set) return; put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int), &NETLINK_CB(skb).nsid); } static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); u32 dst_portid; u32 dst_group; struct sk_buff *skb; int err; struct scm_cookie scm; u32 netlink_skb_flags = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; if (len == 0) { pr_warn_once("Zero length message leads to an empty skb\n"); return -ENODATA; } err = scm_send(sock, msg, &scm, true); if (err < 0) return err; if (msg->msg_namelen) { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_nl)) goto out; if (addr->nl_family != AF_NETLINK) goto out; dst_portid = addr->nl_pid; dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { /* Paired with WRITE_ONCE() in netlink_connect() */ dst_portid = READ_ONCE(nlk->dst_portid); dst_group = READ_ONCE(nlk->dst_group); } /* Paired with WRITE_ONCE() in netlink_insert() */ if (!READ_ONCE(nlk->bound)) { err = netlink_autobind(sock); if (err) goto out; } else { /* Ensure nlk is hashed and visible. */ smp_rmb(); } err = -EMSGSIZE; if (len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = netlink_alloc_large_skb(len, dst_group); if (skb == NULL) goto out; NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = scm.creds; NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_from_msg(skb_put(skb, len), msg, len)) { kfree_skb(skb); goto out; } err = security_netlink_send(sk, skb); if (err) { kfree_skb(skb); goto out; } if (dst_group) { refcount_inc(&skb->users); netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT); out: scm_destroy(&scm); return err; } static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; if (flags & MSG_OOB) return -EOPNOTSUPP; copied = 0; skb = skb_recv_datagram(sk, flags, &err); if (skb == NULL) goto out; data_skb = skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES if (unlikely(skb_shinfo(skb)->frag_list)) { /* * If this skb has a frag_list, then here that means that we * will have to use the frag_list skb's data for compat tasks * and the regular skb's data for normal (non-compat) tasks. * * If we need to send the compat skb, assign it to the * 'data_skb' variable so that it will be used below for data * copying. We keep 'skb' for everything else, including * freeing both later. */ if (flags & MSG_CMSG_COMPAT) data_skb = skb_shinfo(skb)->frag_list; } #endif /* Record the max length of recvmsg() calls for future allocations */ max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); max_recvmsg_len = min_t(size_t, max_recvmsg_len, SKB_WITH_OVERHEAD(32768)); WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); addr->nl_family = AF_NETLINK; addr->nl_pad = 0; addr->nl_pid = NETLINK_CB(skb).portid; addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); msg->msg_namelen = sizeof(*addr); } if (nlk_test_bit(RECV_PKTINFO, sk)) netlink_cmsg_recv_pktinfo(msg, skb); if (nlk_test_bit(LISTEN_ALL_NSID, sk)) netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); scm.creds = *NETLINK_CREDS(skb); if (flags & MSG_TRUNC) copied = data_skb->len; skb_free_datagram(sk, skb); if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk, false); if (ret) { WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); } } scm_recv(sock, msg, &scm, flags); out: netlink_rcv_wake(sk); return err ? : copied; } static void netlink_data_ready(struct sock *sk) { BUG(); } /* * We export these functions to other modules. They provide a * complete set of kernel non-blocking support for message * queueing. */ struct sock * __netlink_kernel_create(struct net *net, int unit, struct module *module, struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; unsigned int groups; BUG_ON(!nl_table); if (unit < 0 || unit >= MAX_LINKS) return NULL; if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; if (__netlink_create(net, sock, unit, 1) < 0) goto out_sock_release_nosk; sk = sock->sk; if (!cfg || cfg->groups < 32) groups = 32; else groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; if (cfg && cfg->input) nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, 0)) goto out_sock_release; nlk = nlk_sk(sk); set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags); netlink_table_grab(); if (!nl_table[unit].registered) { nl_table[unit].groups = groups; rcu_assign_pointer(nl_table[unit].listeners, listeners); nl_table[unit].module = module; if (cfg) { nl_table[unit].bind = cfg->bind; nl_table[unit].unbind = cfg->unbind; nl_table[unit].release = cfg->release; nl_table[unit].flags = cfg->flags; } nl_table[unit].registered = 1; } else { kfree(listeners); nl_table[unit].registered++; } netlink_table_ungrab(); return sk; out_sock_release: kfree(listeners); netlink_kernel_release(sk); return NULL; out_sock_release_nosk: sock_release(sock); return NULL; } EXPORT_SYMBOL(__netlink_kernel_create); void netlink_kernel_release(struct sock *sk) { if (sk == NULL || sk->sk_socket == NULL) return; sock_release(sk->sk_socket); } EXPORT_SYMBOL(netlink_kernel_release); int __netlink_change_ngroups(struct sock *sk, unsigned int groups) { struct listeners *new, *old; struct netlink_table *tbl = &nl_table[sk->sk_protocol]; if (groups < 32) groups = 32; if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; old = nl_deref_protected(tbl->listeners); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); kfree_rcu(old, rcu); } tbl->groups = groups; return 0; } /** * netlink_change_ngroups - change number of multicast groups * * This changes the number of multicast groups that are available * on a certain netlink family. Note that it is not possible to * change the number of groups to below 32. Also note that it does * not implicitly clear listeners from groups that are removed when * the number of groups is reduced. * * @sk: The kernel netlink socket, as returned by netlink_kernel_create(). * @groups: The new number of groups. */ int netlink_change_ngroups(struct sock *sk, unsigned int groups) { int err; netlink_table_grab(); err = __netlink_change_ngroups(sk, groups); netlink_table_ungrab(); return err; } void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { struct sock *sk; struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; struct hlist_node *tmp; sk_for_each_bound_safe(sk, tmp, &tbl->mc_list) netlink_update_socket_mc(nlk_sk(sk), group, 0); } struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); nlh = skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; nlh->nlmsg_pid = portid; nlh->nlmsg_seq = seq; if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size); return nlh; } EXPORT_SYMBOL(__nlmsg_put); static size_t netlink_ack_tlv_len(struct netlink_sock *nlk, int err, const struct netlink_ext_ack *extack) { size_t tlvlen; if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) return 0; tlvlen = 0; if (extack->_msg) tlvlen += nla_total_size(strlen(extack->_msg) + 1); if (extack->cookie_len) tlvlen += nla_total_size(extack->cookie_len); /* Following attributes are only reported as error (not warning) */ if (!err) return tlvlen; if (extack->bad_attr) tlvlen += nla_total_size(sizeof(u32)); if (extack->policy) tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); if (extack->miss_type) tlvlen += nla_total_size(sizeof(u32)); if (extack->miss_nest) tlvlen += nla_total_size(sizeof(u32)); return tlvlen; } static bool nlmsg_check_in_payload(const struct nlmsghdr *nlh, const void *addr) { return !WARN_ON(addr < nlmsg_data(nlh) || addr - (const void *) nlh >= nlh->nlmsg_len); } static void netlink_ack_tlv_fill(struct sk_buff *skb, const struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { if (extack->_msg) WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, extack->cookie_len, extack->cookie)); if (!err) return; if (extack->bad_attr && nlmsg_check_in_payload(nlh, extack->bad_attr)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - (const u8 *)nlh)); if (extack->policy) netlink_policy_dump_write_attr(skb, extack->policy, NLMSGERR_ATTR_POLICY); if (extack->miss_type) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE, extack->miss_type)); if (extack->miss_nest && nlmsg_check_in_payload(nlh, extack->miss_nest)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST, (u8 *)extack->miss_nest - (const u8 *)nlh)); } /* * It looks a bit ugly. * It would be better to create kernel thread. */ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, struct netlink_callback *cb, struct netlink_ext_ack *extack) { struct nlmsghdr *nlh; size_t extack_len; nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), NLM_F_MULTI | cb->answer_flags); if (WARN_ON(!nlh)) return -ENOBUFS; nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); extack_len = netlink_ack_tlv_len(nlk, nlk->dump_done_errno, extack); if (extack_len) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; if (skb_tailroom(skb) >= extack_len) { netlink_ack_tlv_fill(skb, cb->nlh, nlk->dump_done_errno, extack); nlmsg_end(skb, nlh); } } return 0; } static int netlink_dump(struct sock *sk, bool lock_taken) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; unsigned int rmem, rcvbuf; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; int alloc_size; if (!lock_taken) mutex_lock(&nlk->nl_cb_mutex); if (!nlk->cb_running) { err = -EINVAL; goto errout_skb; } /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 32KiB allocation * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); if (alloc_min_size < max_recvmsg_len) { alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; skb = alloc_skb(alloc_size, GFP_KERNEL); } if (!skb) goto errout_skb; rcvbuf = READ_ONCE(sk->sk_rcvbuf); rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); if (rmem != skb->truesize && rmem >= rcvbuf) { atomic_sub(skb->truesize, &sk->sk_rmem_alloc); goto errout_skb; } /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as * could fit within the allocated skb. skb is typically allocated * with larger space than required (could be as much as near 2x the * requested size with align to next power of 2 approach). Allowing * dump to use the excess space makes it difficult for a user to have a * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); /* Make sure malicious BPF programs can not read unitialized memory * from skb->head -> skb->data */ skb_reset_network_header(skb); skb_reset_mac_header(skb); netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { cb->extack = &extack; nlk->dump_done_errno = cb->dump(skb, cb); /* EMSGSIZE plus something already in the skb means * that there's more to dump but current skb has filled up. * If the callback really wants to return EMSGSIZE to user space * it needs to do so again, on the next cb->dump() call, * without putting data in the skb. */ if (nlk->dump_done_errno == -EMSGSIZE && skb->len) nlk->dump_done_errno = skb->len; cb->extack = NULL; } if (nlk->dump_done_errno > 0 || skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { mutex_unlock(&nlk->nl_cb_mutex); if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); return 0; } if (netlink_dump_done(nlk, skb, cb, &extack)) goto errout_skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES /* frag_list skb's data is used for compat tasks * and the regular skb's data for normal (non-compat) tasks. * See netlink_recvmsg(). */ if (unlikely(skb_shinfo(skb)->frag_list)) { if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack)) goto errout_skb; } #endif if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); if (cb->done) cb->done(cb); WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(&nlk->nl_cb_mutex); module_put(module); consume_skb(skb); return 0; errout_skb: mutex_unlock(&nlk->nl_cb_mutex); kfree_skb(skb); return err; } int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { struct netlink_callback *cb; struct netlink_sock *nlk; struct sock *sk; int ret; refcount_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { ret = -ECONNREFUSED; goto error_free; } nlk = nlk_sk(sk); mutex_lock(&nlk->nl_cb_mutex); /* A dump is in progress... */ if (nlk->cb_running) { ret = -EBUSY; goto error_unlock; } /* add reference of module which cb->dump belongs to */ if (!try_module_get(control->module)) { ret = -EPROTONOSUPPORT; goto error_unlock; } cb = &nlk->cb; memset(cb, 0, sizeof(*cb)); cb->dump = control->dump; cb->done = control->done; cb->nlh = nlh; cb->data = control->data; cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; cb->flags = control->flags; cb->skb = skb; cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); if (control->start) { cb->extack = control->extack; ret = control->start(cb); cb->extack = NULL; if (ret) goto error_put; } WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; ret = netlink_dump(sk, true); sock_put(sk); if (ret) return ret; /* We successfully started a dump, by returning -EINTR we * signal not to send ACK even if it was requested. */ return -EINTR; error_put: module_put(control->module); error_unlock: sock_put(sk); mutex_unlock(&nlk->nl_cb_mutex); error_free: kfree_skb(skb); return ret; } EXPORT_SYMBOL(__netlink_dump_start); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct sk_buff *skb; struct nlmsghdr *rep; struct nlmsgerr *errmsg; size_t payload = sizeof(*errmsg); struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); unsigned int flags = 0; size_t tlvlen; /* Error messages get the original request appended, unless the user * requests to cap the error message, and get extra error data if * requested. */ if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; tlvlen = netlink_ack_tlv_len(nlk, err, extack); if (tlvlen) flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) goto err_skb; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, sizeof(*errmsg), flags); if (!rep) goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; errmsg->msg = *nlh; if (!(flags & NLM_F_CAPPED)) { if (!nlmsg_append(skb, nlmsg_len(nlh))) goto err_bad_put; memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), nlmsg_len(nlh)); } if (tlvlen) netlink_ack_tlv_fill(skb, nlh, err, extack); nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); return; err_bad_put: nlmsg_free(skb); err_skb: WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)) { struct netlink_ext_ack extack; struct nlmsghdr *nlh; int err; while (skb->len >= nlmsg_total_size(0)) { int msglen; memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return 0; /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) goto ack; /* Skip control messages */ if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) netlink_ack(skb, nlh, err, &extack); skip: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } return 0; } EXPORT_SYMBOL(netlink_rcv_skb); /** * nlmsg_notify - send a notification netlink message * @sk: netlink socket to use * @skb: notification message * @portid: destination netlink portid for reports or 0 * @group: destination multicast group or 0 * @report: 1 to report back, 0 to disable * @flags: allocation flags */ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags) { int err = 0; if (group) { int exclude_portid = 0; if (report) { refcount_inc(&skb->users); exclude_portid = portid; } /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); if (err == -ESRCH) err = 0; } if (report) { int err2; err2 = nlmsg_unicast(sk, skb, portid); if (!err) err = err2; } return err; } EXPORT_SYMBOL(nlmsg_notify); #ifdef CONFIG_PROC_FS struct nl_seq_iter { struct seq_net_private p; struct rhashtable_iter hti; int link; }; static void netlink_walk_start(struct nl_seq_iter *iter) { rhashtable_walk_enter(&nl_table[iter->link].hash, &iter->hti); rhashtable_walk_start(&iter->hti); } static void netlink_walk_stop(struct nl_seq_iter *iter) { rhashtable_walk_stop(&iter->hti); rhashtable_walk_exit(&iter->hti); } static void *__netlink_seq_next(struct seq_file *seq) { struct nl_seq_iter *iter = seq->private; struct netlink_sock *nlk; do { for (;;) { nlk = rhashtable_walk_next(&iter->hti); if (IS_ERR(nlk)) { if (PTR_ERR(nlk) == -EAGAIN) continue; return nlk; } if (nlk) break; netlink_walk_stop(iter); if (++iter->link >= MAX_LINKS) return NULL; netlink_walk_start(iter); } } while (sock_net(&nlk->sk) != seq_file_net(seq)); return nlk; } static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) __acquires(RCU) { struct nl_seq_iter *iter = seq->private; void *obj = SEQ_START_TOKEN; loff_t pos; iter->link = 0; netlink_walk_start(iter); for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) obj = __netlink_seq_next(seq); return obj; } static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return __netlink_seq_next(seq); } static void netlink_native_seq_stop(struct seq_file *seq, void *v) { struct nl_seq_iter *iter = seq->private; if (iter->link >= MAX_LINKS) return; netlink_walk_stop(iter); } static int netlink_native_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk Eth Pid Groups " "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8u %-8llu\n", s, s->sk_protocol, nlk->portid, nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), sk_drops_read(s), sock_i_ino(s) ); } return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__netlink { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct netlink_sock *, sk); }; DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk) static int netlink_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__netlink ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk = nlk_sk((struct sock *)v); return bpf_iter_run_prog(prog, &ctx); } static int netlink_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return netlink_native_seq_show(seq, v); if (v != SEQ_START_TOKEN) return netlink_prog_seq_show(prog, &meta, v); return 0; } static void netlink_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)netlink_prog_seq_show(prog, &meta, v); } netlink_native_seq_stop(seq, v); } #else static int netlink_seq_show(struct seq_file *seq, void *v) { return netlink_native_seq_show(seq, v); } static void netlink_seq_stop(struct seq_file *seq, void *v) { netlink_native_seq_stop(seq, v); } #endif static const struct seq_operations netlink_seq_ops = { .start = netlink_seq_start, .next = netlink_seq_next, .stop = netlink_seq_stop, .show = netlink_seq_show, }; #endif int netlink_register_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_register_notifier); int netlink_unregister_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_unregister_notifier); static const struct proto_ops netlink_ops = { .family = PF_NETLINK, .owner = THIS_MODULE, .release = netlink_release, .bind = netlink_bind, .connect = netlink_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = netlink_getname, .poll = datagram_poll, .ioctl = netlink_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = netlink_setsockopt, .getsockopt_iter = netlink_getsockopt, .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, .mmap = sock_no_mmap, }; static const struct net_proto_family netlink_family_ops = { .family = PF_NETLINK, .create = netlink_create, .owner = THIS_MODULE, /* for consistency 8) */ }; static int __net_init netlink_net_init(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops, sizeof(struct nl_seq_iter))) return -ENOMEM; #endif return 0; } static void __net_exit netlink_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("netlink", net->proc_net); #endif } static void __init netlink_add_usersock_entry(void) { struct listeners *listeners; int groups = 32; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) panic("netlink_add_usersock_entry: Cannot allocate listeners\n"); netlink_table_grab(); nl_table[NETLINK_USERSOCK].groups = groups; rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); nl_table[NETLINK_USERSOCK].module = THIS_MODULE; nl_table[NETLINK_USERSOCK].registered = 1; nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND; netlink_table_ungrab(); } static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, }; static inline u32 netlink_hash(const void *data, u32 len, u32 seed) { const struct netlink_sock *nlk = data; struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); } static const struct rhashtable_params netlink_rhashtable_params = { .head_offset = offsetof(struct netlink_sock, node), .key_len = netlink_compare_arg_len, .obj_hashfn = netlink_hash, .obj_cmpfn = netlink_compare, .automatic_shrinking = true, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) BTF_ID_LIST_SINGLE(btf_netlink_sock_id, struct, netlink_sock) static const struct bpf_iter_seq_info netlink_seq_info = { .seq_ops = &netlink_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct nl_seq_iter), }; static struct bpf_iter_reg netlink_reg_info = { .target = "netlink", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__netlink, sk), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &netlink_seq_info, }; static int __init bpf_iter_register(void) { netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id; return bpf_iter_reg_target(&netlink_reg_info); } #endif static int __init netlink_proto_init(void) { int i; int err = proto_register(&netlink_proto, 0); if (err != 0) goto out; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) err = bpf_iter_register(); if (err) goto out; #endif BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kzalloc_objs(*nl_table, MAX_LINKS); if (!nl_table) goto panic; for (i = 0; i < MAX_LINKS; i++) { if (rhashtable_init(&nl_table[i].hash, &netlink_rhashtable_params) < 0) goto panic; } netlink_add_usersock_entry(); sock_register(&netlink_family_ops); register_pernet_subsys(&netlink_net_ops); register_pernet_subsys(&netlink_tap_net_ops); /* The netlink device handler may be needed early. */ rtnetlink_init(); out: return err; panic: panic("netlink_init: Cannot allocate nl_table\n"); } core_initcall(netlink_proto_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2014 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:mac type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <net/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 #define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:mac"); /* Type specific function prefix */ #define HTYPE hash_mac /* Member elements */ struct hash_mac4_elem { /* Zero valued IP addresses cannot be stored */ union { unsigned char ether[ETH_ALEN]; __be32 foo[2]; }; }; /* Common functions */ static bool hash_mac4_data_equal(const struct hash_mac4_elem *e1, const struct hash_mac4_elem *e2, u32 *multi) { return ether_addr_equal(e1->ether, e2->ether); } static bool hash_mac4_data_list(struct sk_buff *skb, const struct hash_mac4_elem *e) { if (nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_mac4_data_next(struct hash_mac4_elem *next, const struct hash_mac4_elem *e) { } #define MTYPE hash_mac4 #define HOST_MASK 32 #define IP_SET_EMIT_CREATE #define IP_SET_PROTO_UNDEF #include "ip_set_hash_gen.h" static int hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!skb->dev || skb->dev->type != ARPHRD_ETHER || !skb_mac_header_was_set(skb) || skb_mac_header_len(skb) < ETH_HLEN) return -EINVAL; if (opt->flags & IPSET_DIM_ONE_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); if (is_zero_ether_addr(e.ether)) return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_mac4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_ETHER] || nla_len(tb[IPSET_ATTR_ETHER]) != ETH_ALEN)) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; ether_addr_copy(e.ether, nla_data(tb[IPSET_ATTR_ETHER])); if (is_zero_ether_addr(e.ether)) return -IPSET_ERR_HASH_ELEM; return adtfn(set, &e, &ext, &ext, flags); } static struct ip_set_type hash_mac_type __read_mostly = { .name = "hash:mac", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_MAC, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_mac_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_ETHER] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_mac_init(void) { return ip_set_type_register(&hash_mac_type); } static void __exit hash_mac_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_mac_type); } module_init(hash_mac_init); module_exit(hash_mac_fini); |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * f_subset.c -- "CDC Subset" Ethernet link function driver * * Copyright (C) 2003-2005,2008 David Brownell * Copyright (C) 2008 Nokia Corporation */ #include <linux/cleanup.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> #include <linux/etherdevice.h> #include "u_ether.h" #include "u_ether_configfs.h" #include "u_gether.h" /* * This function packages a simple "CDC Subset" Ethernet port with no real * control mechanisms; just raw data transfer over two bulk endpoints. * The data transfer model is exactly that of CDC Ethernet, which is * why we call it the "CDC Subset". * * Because it's not standardized, this has some interoperability issues. * They mostly relate to driver binding, since the data transfer model is * so simple (CDC Ethernet). The original versions of this protocol used * specific product/vendor IDs: byteswapped IDs for Digital Equipment's * SA-1100 "Itsy" board, which could run Linux 2.4 kernels and supported * daughtercards with USB peripheral connectors. (It was used more often * with other boards, using the Itsy identifiers.) Linux hosts recognized * this with CONFIG_USB_ARMLINUX; these devices have only one configuration * and one interface. * * At some point, MCCI defined a (nonconformant) CDC MDLM variant called * "SAFE", which happens to have a mode which is identical to the "CDC * Subset" in terms of data transfer and lack of control model. This was * adopted by later Sharp Zaurus models, and by some other software which * Linux hosts recognize with CONFIG_USB_NET_ZAURUS. * * Because Microsoft's RNDIS drivers are far from robust, we added a few * descriptors to the CDC Subset code, making this code look like a SAFE * implementation. This lets you use MCCI's host side MS-Windows drivers * if you get fed up with RNDIS. It also makes it easier for composite * drivers to work, since they can use class based binding instead of * caring about specific product and vendor IDs. */ struct f_gether { struct gether port; char ethaddr[14]; }; static inline struct f_gether *func_to_geth(struct usb_function *f) { return container_of(f, struct f_gether, port.func); } /*-------------------------------------------------------------------------*/ /* * "Simple" CDC-subset option is a simple vendor-neutral model that most * full speed controllers can handle: one interface, two bulk endpoints. * To assist host side drivers, we fancy it up a bit, and add descriptors so * some host side drivers will understand it as a "SAFE" variant. * * "SAFE" loosely follows CDC WMC MDLM, violating the spec in various ways. * Data endpoints live in the control interface, there's no data interface. * And it's not used to talk to a cell phone radio. */ /* interface descriptor: */ static struct usb_interface_descriptor subset_data_intf = { .bLength = sizeof subset_data_intf, .bDescriptorType = USB_DT_INTERFACE, /* .bInterfaceNumber = DYNAMIC */ .bAlternateSetting = 0, .bNumEndpoints = 2, .bInterfaceClass = USB_CLASS_COMM, .bInterfaceSubClass = USB_CDC_SUBCLASS_MDLM, .bInterfaceProtocol = 0, /* .iInterface = DYNAMIC */ }; static struct usb_cdc_header_desc mdlm_header_desc = { .bLength = sizeof mdlm_header_desc, .bDescriptorType = USB_DT_CS_INTERFACE, .bDescriptorSubType = USB_CDC_HEADER_TYPE, .bcdCDC = cpu_to_le16(0x0110), }; static struct usb_cdc_mdlm_desc mdlm_desc = { .bLength = sizeof mdlm_desc, .bDescriptorType = USB_DT_CS_INTERFACE, .bDescriptorSubType = USB_CDC_MDLM_TYPE, .bcdVersion = cpu_to_le16(0x0100), .bGUID = { 0x5d, 0x34, 0xcf, 0x66, 0x11, 0x18, 0x11, 0xd6, 0xa2, 0x1a, 0x00, 0x01, 0x02, 0xca, 0x9a, 0x7f, }, }; /* since "usb_cdc_mdlm_detail_desc" is a variable length structure, we * can't really use its struct. All we do here is say that we're using * the submode of "SAFE" which directly matches the CDC Subset. */ static u8 mdlm_detail_desc[] = { 6, USB_DT_CS_INTERFACE, USB_CDC_MDLM_DETAIL_TYPE, 0, /* "SAFE" */ 0, /* network control capabilities (none) */ 0, /* network data capabilities ("raw" encapsulation) */ }; static struct usb_cdc_ether_desc ether_desc = { .bLength = sizeof ether_desc, .bDescriptorType = USB_DT_CS_INTERFACE, .bDescriptorSubType = USB_CDC_ETHERNET_TYPE, /* this descriptor actually adds value, surprise! */ /* .iMACAddress = DYNAMIC */ .bmEthernetStatistics = cpu_to_le32(0), /* no statistics */ .wMaxSegmentSize = cpu_to_le16(ETH_FRAME_LEN), .wNumberMCFilters = cpu_to_le16(0), .bNumberPowerFilters = 0, }; /* full speed support: */ static struct usb_endpoint_descriptor fs_subset_in_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bEndpointAddress = USB_DIR_IN, .bmAttributes = USB_ENDPOINT_XFER_BULK, }; static struct usb_endpoint_descriptor fs_subset_out_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bEndpointAddress = USB_DIR_OUT, .bmAttributes = USB_ENDPOINT_XFER_BULK, }; static struct usb_descriptor_header *fs_eth_function[] = { (struct usb_descriptor_header *) &subset_data_intf, (struct usb_descriptor_header *) &mdlm_header_desc, (struct usb_descriptor_header *) &mdlm_desc, (struct usb_descriptor_header *) &mdlm_detail_desc, (struct usb_descriptor_header *) ðer_desc, (struct usb_descriptor_header *) &fs_subset_in_desc, (struct usb_descriptor_header *) &fs_subset_out_desc, NULL, }; /* high speed support: */ static struct usb_endpoint_descriptor hs_subset_in_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bmAttributes = USB_ENDPOINT_XFER_BULK, .wMaxPacketSize = cpu_to_le16(512), }; static struct usb_endpoint_descriptor hs_subset_out_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bmAttributes = USB_ENDPOINT_XFER_BULK, .wMaxPacketSize = cpu_to_le16(512), }; static struct usb_descriptor_header *hs_eth_function[] = { (struct usb_descriptor_header *) &subset_data_intf, (struct usb_descriptor_header *) &mdlm_header_desc, (struct usb_descriptor_header *) &mdlm_desc, (struct usb_descriptor_header *) &mdlm_detail_desc, (struct usb_descriptor_header *) ðer_desc, (struct usb_descriptor_header *) &hs_subset_in_desc, (struct usb_descriptor_header *) &hs_subset_out_desc, NULL, }; /* super speed support: */ static struct usb_endpoint_descriptor ss_subset_in_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bmAttributes = USB_ENDPOINT_XFER_BULK, .wMaxPacketSize = cpu_to_le16(1024), }; static struct usb_endpoint_descriptor ss_subset_out_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bmAttributes = USB_ENDPOINT_XFER_BULK, .wMaxPacketSize = cpu_to_le16(1024), }; static struct usb_ss_ep_comp_descriptor ss_subset_bulk_comp_desc = { .bLength = sizeof ss_subset_bulk_comp_desc, .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, /* the following 2 values can be tweaked if necessary */ /* .bMaxBurst = 0, */ /* .bmAttributes = 0, */ }; static struct usb_descriptor_header *ss_eth_function[] = { (struct usb_descriptor_header *) &subset_data_intf, (struct usb_descriptor_header *) &mdlm_header_desc, (struct usb_descriptor_header *) &mdlm_desc, (struct usb_descriptor_header *) &mdlm_detail_desc, (struct usb_descriptor_header *) ðer_desc, (struct usb_descriptor_header *) &ss_subset_in_desc, (struct usb_descriptor_header *) &ss_subset_bulk_comp_desc, (struct usb_descriptor_header *) &ss_subset_out_desc, (struct usb_descriptor_header *) &ss_subset_bulk_comp_desc, NULL, }; /* string descriptors: */ static struct usb_string geth_string_defs[] = { [0].s = "CDC Ethernet Subset/SAFE", [1].s = "", { } /* end of list */ }; static struct usb_gadget_strings geth_string_table = { .language = 0x0409, /* en-us */ .strings = geth_string_defs, }; static struct usb_gadget_strings *geth_strings[] = { &geth_string_table, NULL, }; /*-------------------------------------------------------------------------*/ static int geth_set_alt(struct usb_function *f, unsigned intf, unsigned alt) { struct f_gether *geth = func_to_geth(f); struct usb_composite_dev *cdev = f->config->cdev; struct net_device *net; /* we know alt == 0, so this is an activation or a reset */ if (geth->port.in_ep->enabled) { DBG(cdev, "reset cdc subset\n"); gether_disconnect(&geth->port); } DBG(cdev, "init + activate cdc subset\n"); if (config_ep_by_speed(cdev->gadget, f, geth->port.in_ep) || config_ep_by_speed(cdev->gadget, f, geth->port.out_ep)) { geth->port.in_ep->desc = NULL; geth->port.out_ep->desc = NULL; return -EINVAL; } net = gether_connect(&geth->port); return PTR_ERR_OR_ZERO(net); } static void geth_disable(struct usb_function *f) { struct f_gether *geth = func_to_geth(f); struct usb_composite_dev *cdev = f->config->cdev; DBG(cdev, "net deactivated\n"); gether_disconnect(&geth->port); } /*-------------------------------------------------------------------------*/ /* serial function driver setup/binding */ static int geth_bind(struct usb_configuration *c, struct usb_function *f) { struct usb_composite_dev *cdev = c->cdev; struct f_gether *geth = func_to_geth(f); struct usb_string *us; int status; struct usb_ep *ep; struct f_gether_opts *gether_opts; struct net_device *net __free(detach_gadget) = NULL; gether_opts = container_of(f->fi, struct f_gether_opts, func_inst); scoped_guard(mutex, &gether_opts->lock) if (gether_opts->bind_count == 0 && !gether_opts->bound) { if (!device_is_registered(&gether_opts->net->dev)) { gether_set_gadget(gether_opts->net, cdev->gadget); status = gether_register_netdev(gether_opts->net); } else status = gether_attach_gadget(gether_opts->net, cdev->gadget); if (status) return status; net = gether_opts->net; } us = usb_gstrings_attach(cdev, geth_strings, ARRAY_SIZE(geth_string_defs)); if (IS_ERR(us)) return PTR_ERR(us); subset_data_intf.iInterface = us[0].id; ether_desc.iMACAddress = us[1].id; /* allocate instance-specific interface IDs */ status = usb_interface_id(c, f); if (status < 0) return status; subset_data_intf.bInterfaceNumber = status; /* allocate instance-specific endpoints */ ep = usb_ep_autoconfig(cdev->gadget, &fs_subset_in_desc); if (!ep) return -ENODEV; geth->port.in_ep = ep; ep = usb_ep_autoconfig(cdev->gadget, &fs_subset_out_desc); if (!ep) return -ENODEV; geth->port.out_ep = ep; /* support all relevant hardware speeds... we expect that when * hardware is dual speed, all bulk-capable endpoints work at * both speeds */ hs_subset_in_desc.bEndpointAddress = fs_subset_in_desc.bEndpointAddress; hs_subset_out_desc.bEndpointAddress = fs_subset_out_desc.bEndpointAddress; ss_subset_in_desc.bEndpointAddress = fs_subset_in_desc.bEndpointAddress; ss_subset_out_desc.bEndpointAddress = fs_subset_out_desc.bEndpointAddress; status = usb_assign_descriptors(f, fs_eth_function, hs_eth_function, ss_eth_function, ss_eth_function); if (status) return status; /* NOTE: all that is done without knowing or caring about * the network link ... which is unavailable to this code * until we're activated via set_alt(). */ gether_opts->bind_count++; retain_and_null_ptr(net); DBG(cdev, "CDC Subset: IN/%s OUT/%s\n", geth->port.in_ep->name, geth->port.out_ep->name); return 0; } static inline struct f_gether_opts *to_f_gether_opts(struct config_item *item) { return container_of(to_config_group(item), struct f_gether_opts, func_inst.group); } /* f_gether_item_ops */ USB_ETHERNET_CONFIGFS_ITEM(gether); /* f_gether_opts_dev_addr */ USB_ETHERNET_CONFIGFS_ITEM_ATTR_DEV_ADDR(gether); /* f_gether_opts_host_addr */ USB_ETHERNET_CONFIGFS_ITEM_ATTR_HOST_ADDR(gether); /* f_gether_opts_qmult */ USB_ETHERNET_CONFIGFS_ITEM_ATTR_QMULT(gether); /* f_gether_opts_ifname */ USB_ETHERNET_CONFIGFS_ITEM_ATTR_IFNAME(gether); static struct configfs_attribute *gether_attrs[] = { &gether_opts_attr_dev_addr, &gether_opts_attr_host_addr, &gether_opts_attr_qmult, &gether_opts_attr_ifname, NULL, }; static const struct config_item_type gether_func_type = { .ct_item_ops = &gether_item_ops, .ct_attrs = gether_attrs, .ct_owner = THIS_MODULE, }; static void geth_free_inst(struct usb_function_instance *f) { struct f_gether_opts *opts; opts = container_of(f, struct f_gether_opts, func_inst); if (device_is_registered(&opts->net->dev)) gether_cleanup(netdev_priv(opts->net)); else free_netdev(opts->net); kfree(opts); } static struct usb_function_instance *geth_alloc_inst(void) { struct f_gether_opts *opts; opts = kzalloc_obj(*opts); if (!opts) return ERR_PTR(-ENOMEM); mutex_init(&opts->lock); opts->func_inst.free_func_inst = geth_free_inst; opts->net = gether_setup_default(); if (IS_ERR(opts->net)) { struct net_device *net = opts->net; kfree(opts); return ERR_CAST(net); } config_group_init_type_name(&opts->func_inst.group, "", &gether_func_type); return &opts->func_inst; } static void geth_free(struct usb_function *f) { struct f_gether *eth; struct f_gether_opts *opts; opts = container_of(f->fi, struct f_gether_opts, func_inst); eth = func_to_geth(f); scoped_guard(mutex, &opts->lock) opts->refcnt--; kfree(eth); } static void geth_unbind(struct usb_configuration *c, struct usb_function *f) { struct f_gether_opts *opts; opts = container_of(f->fi, struct f_gether_opts, func_inst); geth_string_defs[0].id = 0; usb_free_all_descriptors(f); opts->bind_count--; if (opts->bind_count == 0 && !opts->bound) gether_detach_gadget(opts->net); } static struct usb_function *geth_alloc(struct usb_function_instance *fi) { struct f_gether *geth; struct f_gether_opts *opts; int status; /* allocate and initialize one new instance */ geth = kzalloc_obj(*geth); if (!geth) return ERR_PTR(-ENOMEM); opts = container_of(fi, struct f_gether_opts, func_inst); mutex_lock(&opts->lock); opts->refcnt++; /* export host's Ethernet address in CDC format */ status = gether_get_host_addr_cdc(opts->net, geth->ethaddr, sizeof(geth->ethaddr)); if (status < 12) { kfree(geth); mutex_unlock(&opts->lock); return ERR_PTR(-EINVAL); } geth_string_defs[1].s = geth->ethaddr; geth->port.ioport = netdev_priv(opts->net); mutex_unlock(&opts->lock); geth->port.cdc_filter = DEFAULT_FILTER; geth->port.func.name = "cdc_subset"; geth->port.func.bind = geth_bind; geth->port.func.unbind = geth_unbind; geth->port.func.set_alt = geth_set_alt; geth->port.func.disable = geth_disable; geth->port.func.free_func = geth_free; return &geth->port.func; } DECLARE_USB_FUNCTION_INIT(geth, geth_alloc_inst, geth_alloc); MODULE_DESCRIPTION("\"CDC Subset\" Ethernet link function driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("David Brownell"); |
| 32 49 40 5 40 40 21 23 48 48 9 48 6 12 13 49 38 5 32 38 38 24 38 8 25 3 25 25 25 17 51 51 13 51 25 25 25 4 6 4 32 14 21 19 19 19 32 32 32 32 17 32 32 32 32 32 3 2 2 19 19 8 2 19 19 32 20 32 32 32 32 32 3 1 3 3 3 3 2 3 3 3 51 19 32 19 32 3 32 32 31 19 25 25 25 62 25 37 34 34 7 7 7 7 40 7 34 41 7 34 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2016 Facebook */ #include <linux/cpumask.h> #include <linux/spinlock.h> #include <linux/percpu.h> #include "bpf_lru_list.h" #define LOCAL_FREE_TARGET (128) #define LOCAL_NR_SCANS LOCAL_FREE_TARGET #define PERCPU_FREE_TARGET (4) #define PERCPU_NR_SCANS PERCPU_FREE_TARGET #define IS_LOCAL_LIST_TYPE(t) ((t) >= BPF_LOCAL_LIST_T_OFFSET) /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { return READ_ONCE(node->ref); } static void bpf_lru_node_clear_ref(struct bpf_lru_node *node) { WRITE_ONCE(node->ref, 0); } static void bpf_lru_list_count_inc(struct bpf_lru_list *l, enum bpf_lru_list_type type) { if (type < NR_BPF_LRU_LIST_COUNT) l->counts[type]++; } static void bpf_lru_list_count_dec(struct bpf_lru_list *l, enum bpf_lru_list_type type) { if (type < NR_BPF_LRU_LIST_COUNT) l->counts[type]--; } static void __bpf_lru_node_move_to_free(struct bpf_lru_list *l, struct bpf_lru_node *node, struct list_head *free_list, enum bpf_lru_list_type tgt_free_type) { if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type))) return; /* If the removing node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. */ if (&node->list == l->next_inactive_rotation) l->next_inactive_rotation = l->next_inactive_rotation->prev; bpf_lru_list_count_dec(l, node->type); node->type = tgt_free_type; WRITE_ONCE(node->pending_free, 0); list_move(&node->list, free_list); } /* Move nodes from local list to the LRU list */ static void __bpf_lru_node_move_in(struct bpf_lru_list *l, struct bpf_lru_node *node, enum bpf_lru_list_type tgt_type) { if (WARN_ON_ONCE(!IS_LOCAL_LIST_TYPE(node->type)) || WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type))) return; bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; bpf_lru_node_clear_ref(node); /* Reset pending_free only when moving to the free list */ if (tgt_type == BPF_LRU_LIST_T_FREE) WRITE_ONCE(node->pending_free, 0); list_move(&node->list, &l->lists[tgt_type]); } /* Move nodes between or within active and inactive list (like * active to inactive, inactive to active or tail of active back to * the head of active). */ static void __bpf_lru_node_move(struct bpf_lru_list *l, struct bpf_lru_node *node, enum bpf_lru_list_type tgt_type) { if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)) || WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type))) return; if (node->type != tgt_type) { bpf_lru_list_count_dec(l, node->type); bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } bpf_lru_node_clear_ref(node); /* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. */ if (&node->list == l->next_inactive_rotation) l->next_inactive_rotation = l->next_inactive_rotation->prev; list_move(&node->list, &l->lists[tgt_type]); } static bool bpf_lru_list_inactive_low(const struct bpf_lru_list *l) { return l->counts[BPF_LRU_LIST_T_INACTIVE] < l->counts[BPF_LRU_LIST_T_ACTIVE]; } /* Rotate the active list: * 1. Start from tail * 2. If the node has the ref bit set, it will be rotated * back to the head of active list with the ref bit cleared. * Give this node one more chance to survive in the active list. * 3. If the ref bit is not set, move it to the head of the * inactive list. * 4. It will at most scan nr_scans nodes */ static void __bpf_lru_list_rotate_active(struct bpf_lru *lru, struct bpf_lru_list *l) { struct list_head *active = &l->lists[BPF_LRU_LIST_T_ACTIVE]; struct bpf_lru_node *node, *tmp_node, *first_node; unsigned int i = 0; first_node = list_first_entry(active, struct bpf_lru_node, list); list_for_each_entry_safe_reverse(node, tmp_node, active, list) { if (bpf_lru_node_is_ref(node)) __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE); else __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); if (++i == lru->nr_scans || node == first_node) break; } } /* Rotate the inactive list. It starts from the next_inactive_rotation * 1. If the node has ref bit set, it will be moved to the head * of active list with the ref bit cleared. * 2. If the node does not have ref bit set, it will leave it * at its current location (i.e. do nothing) so that it can * be considered during the next inactive_shrink. * 3. It will at most scan nr_scans nodes */ static void __bpf_lru_list_rotate_inactive(struct bpf_lru *lru, struct bpf_lru_list *l) { struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE]; struct list_head *cur, *last, *next = inactive; struct bpf_lru_node *node; unsigned int i = 0; if (list_empty(inactive)) return; last = l->next_inactive_rotation->next; if (last == inactive) last = last->next; cur = l->next_inactive_rotation; while (i < lru->nr_scans) { if (cur == inactive) { cur = cur->prev; continue; } node = list_entry(cur, struct bpf_lru_node, list); next = cur->prev; if (bpf_lru_node_is_ref(node)) __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE); if (cur == last) break; cur = next; i++; } l->next_inactive_rotation = next; } /* Shrink the inactive list. It starts from the tail of the * inactive list and only move the nodes without the ref bit * set to the designated free list. */ static unsigned int __bpf_lru_list_shrink_inactive(struct bpf_lru *lru, struct bpf_lru_list *l, unsigned int tgt_nshrink, struct list_head *free_list, enum bpf_lru_list_type tgt_free_type) { struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE]; struct bpf_lru_node *node, *tmp_node; unsigned int nshrinked = 0; unsigned int i = 0; list_for_each_entry_safe_reverse(node, tmp_node, inactive, list) { if (bpf_lru_node_is_ref(node) && !READ_ONCE(node->pending_free)) { __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE); } else if (READ_ONCE(node->pending_free) || lru->del_from_htab(lru->del_arg, node)) { __bpf_lru_node_move_to_free(l, node, free_list, tgt_free_type); if (++nshrinked == tgt_nshrink) break; } if (++i == lru->nr_scans) break; } return nshrinked; } /* 1. Rotate the active list (if needed) * 2. Always rotate the inactive list */ static void __bpf_lru_list_rotate(struct bpf_lru *lru, struct bpf_lru_list *l) { if (bpf_lru_list_inactive_low(l)) __bpf_lru_list_rotate_active(lru, l); __bpf_lru_list_rotate_inactive(lru, l); } /* Calls __bpf_lru_list_shrink_inactive() to shrink some * ref-bit-cleared nodes and move them to the designated * free list. * * If it cannot get a free node after calling * __bpf_lru_list_shrink_inactive(). It will just remove * one node from either inactive or active list without * honoring the ref-bit. It prefers inactive list to active * list in this situation. */ static unsigned int __bpf_lru_list_shrink(struct bpf_lru *lru, struct bpf_lru_list *l, unsigned int tgt_nshrink, struct list_head *free_list, enum bpf_lru_list_type tgt_free_type) { struct bpf_lru_node *node, *tmp_node; struct list_head *force_shrink_list; unsigned int nshrinked; nshrinked = __bpf_lru_list_shrink_inactive(lru, l, tgt_nshrink, free_list, tgt_free_type); if (nshrinked) return nshrinked; /* Do a force shrink by ignoring the reference bit */ if (!list_empty(&l->lists[BPF_LRU_LIST_T_INACTIVE])) force_shrink_list = &l->lists[BPF_LRU_LIST_T_INACTIVE]; else force_shrink_list = &l->lists[BPF_LRU_LIST_T_ACTIVE]; list_for_each_entry_safe_reverse(node, tmp_node, force_shrink_list, list) { if (READ_ONCE(node->pending_free) || lru->del_from_htab(lru->del_arg, node)) { __bpf_lru_node_move_to_free(l, node, free_list, tgt_free_type); return 1; } } return 0; } /* Flush the nodes from the local pending list to the LRU list */ static void __local_list_flush(struct bpf_lru_list *l, struct bpf_lru_locallist *loc_l) { struct bpf_lru_node *node, *tmp_node; list_for_each_entry_safe_reverse(node, tmp_node, &loc_l->pending_list, list) { if (READ_ONCE(node->pending_free)) __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_FREE); else if (bpf_lru_node_is_ref(node)) __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_ACTIVE); else __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_INACTIVE); } } static void bpf_lru_list_push_free(struct bpf_lru_list *l, struct bpf_lru_node *node) { unsigned long flags; if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type))) return; if (raw_res_spin_lock_irqsave(&l->lock, flags)) { WRITE_ONCE(node->pending_free, 1); return; } __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE); raw_res_spin_unlock_irqrestore(&l->lock, flags); } static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l) { struct bpf_lru_list *l = &lru->common_lru.lru_list; struct bpf_lru_node *node, *tmp_node; unsigned int nfree = 0; LIST_HEAD(tmp_free); if (raw_res_spin_lock(&l->lock)) return; __local_list_flush(l, loc_l); __bpf_lru_list_rotate(lru, l); list_for_each_entry_safe(node, tmp_node, &l->lists[BPF_LRU_LIST_T_FREE], list) { __bpf_lru_node_move_to_free(l, node, &tmp_free, BPF_LRU_LOCAL_LIST_T_FREE); if (++nfree == lru->target_free) break; } if (nfree < lru->target_free) __bpf_lru_list_shrink(lru, l, lru->target_free - nfree, &tmp_free, BPF_LRU_LOCAL_LIST_T_FREE); raw_res_spin_unlock(&l->lock); /* * Transfer the harvested nodes from the temporary list_head into * the lockless per-CPU free llist. */ list_for_each_entry_safe(node, tmp_node, &tmp_free, list) { list_del(&node->list); llist_add(&node->llist, &loc_l->free_llist); } } static void __local_list_add_pending(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l, int cpu, struct bpf_lru_node *node, u32 hash) { *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; WRITE_ONCE(node->pending_free, 0); bpf_lru_node_clear_ref(node); list_add(&node->list, &loc_l->pending_list); } static struct bpf_lru_node * __local_list_pop_free(struct bpf_lru_locallist *loc_l) { struct llist_node *llnode; llnode = llist_del_first(&loc_l->free_llist); if (!llnode) return NULL; return container_of(llnode, struct bpf_lru_node, llist); } static struct bpf_lru_node * __local_list_pop_pending(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l) { struct bpf_lru_node *node; bool force = false; ignore_ref: /* Get from the tail (i.e. older element) of the pending list. */ list_for_each_entry_reverse(node, &loc_l->pending_list, list) { if ((!bpf_lru_node_is_ref(node) || force) && (READ_ONCE(node->pending_free) || lru->del_from_htab(lru->del_arg, node))) { list_del(&node->list); return node; } } if (!force) { force = true; goto ignore_ref; } return NULL; } static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, u32 hash) { struct list_head *free_list; struct bpf_lru_node *node = NULL; struct bpf_lru_list *l; unsigned long flags; int cpu = raw_smp_processor_id(); l = per_cpu_ptr(lru->percpu_lru, cpu); if (raw_res_spin_lock_irqsave(&l->lock, flags)) return NULL; __bpf_lru_list_rotate(lru, l); free_list = &l->lists[BPF_LRU_LIST_T_FREE]; if (list_empty(free_list)) __bpf_lru_list_shrink(lru, l, PERCPU_FREE_TARGET, free_list, BPF_LRU_LIST_T_FREE); if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; bpf_lru_node_clear_ref(node); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); } raw_res_spin_unlock_irqrestore(&l->lock, flags); return node; } static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru, u32 hash) { struct bpf_lru_locallist *loc_l, *steal_loc_l; struct bpf_common_lru *clru = &lru->common_lru; struct bpf_lru_node *node; int steal, first_steal; unsigned long flags; int cpu = raw_smp_processor_id(); loc_l = per_cpu_ptr(clru->local_list, cpu); if (raw_res_spin_lock_irqsave(&loc_l->lock, flags)) return NULL; node = __local_list_pop_free(loc_l); if (!node) { bpf_lru_list_pop_free_to_local(lru, loc_l); node = __local_list_pop_free(loc_l); } if (node) __local_list_add_pending(lru, loc_l, cpu, node, hash); raw_res_spin_unlock_irqrestore(&loc_l->lock, flags); if (node) return node; /* * No free nodes found from the local free list and * the global LRU list. * * Steal from the local free/pending list of the * current CPU and remote CPU in RR. It starts * with the loc_l->next_steal CPU. * * Acquire the victim's lock before touching either list. On * acquisition failure (rqspinlock AA or timeout) skip the victim * and try the next CPU. */ first_steal = loc_l->next_steal; steal = first_steal; do { steal_loc_l = per_cpu_ptr(clru->local_list, steal); if (!raw_res_spin_lock_irqsave(&steal_loc_l->lock, flags)) { node = __local_list_pop_free(steal_loc_l); if (!node) node = __local_list_pop_pending(lru, steal_loc_l); raw_res_spin_unlock_irqrestore(&steal_loc_l->lock, flags); } steal = cpumask_next_wrap(steal, cpu_possible_mask); } while (!node && steal != first_steal); loc_l->next_steal = steal; if (!node) return NULL; if (raw_res_spin_lock_irqsave(&loc_l->lock, flags)) { /* * The local pending lock can't be acquired (rqspinlock AA * or timeout). Return the stolen node to the per-CPU * free_llist instead of orphaning it; the next pop_free on * this CPU will pick it up. */ node->type = BPF_LRU_LOCAL_LIST_T_FREE; bpf_lru_node_clear_ref(node); WRITE_ONCE(node->pending_free, 0); llist_add(&node->llist, &loc_l->free_llist); return NULL; } __local_list_add_pending(lru, loc_l, cpu, node, hash); raw_res_spin_unlock_irqrestore(&loc_l->lock, flags); return node; } struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash) { if (lru->percpu) return bpf_percpu_lru_pop_free(lru, hash); else return bpf_common_lru_pop_free(lru, hash); } static void bpf_common_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { u8 node_type = READ_ONCE(node->type); unsigned long flags; if (WARN_ON_ONCE(node_type == BPF_LRU_LIST_T_FREE) || WARN_ON_ONCE(node_type == BPF_LRU_LOCAL_LIST_T_FREE)) return; if (node_type == BPF_LRU_LOCAL_LIST_T_PENDING) { struct bpf_lru_locallist *loc_l; loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu); if (raw_res_spin_lock_irqsave(&loc_l->lock, flags)) { WRITE_ONCE(node->pending_free, 1); return; } if (unlikely(node->type != BPF_LRU_LOCAL_LIST_T_PENDING)) { raw_res_spin_unlock_irqrestore(&loc_l->lock, flags); goto check_lru_list; } node->type = BPF_LRU_LOCAL_LIST_T_FREE; bpf_lru_node_clear_ref(node); list_del(&node->list); raw_res_spin_unlock_irqrestore(&loc_l->lock, flags); llist_add(&node->llist, &loc_l->free_llist); return; } check_lru_list: bpf_lru_list_push_free(&lru->common_lru.lru_list, node); } static void bpf_percpu_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { struct bpf_lru_list *l; unsigned long flags; l = per_cpu_ptr(lru->percpu_lru, node->cpu); if (raw_res_spin_lock_irqsave(&l->lock, flags)) { WRITE_ONCE(node->pending_free, 1); return; } __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE); raw_res_spin_unlock_irqrestore(&l->lock, flags); } void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { if (lru->percpu) bpf_percpu_lru_push_free(lru, node); else bpf_common_lru_push_free(lru, node); } static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems) { struct bpf_lru_list *l = &lru->common_lru.lru_list; u32 i; for (i = 0; i < nr_elems; i++) { struct bpf_lru_node *node; node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; node->pending_free = 0; bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } lru->target_free = clamp((nr_elems / num_possible_cpus()) / 2, 1, LOCAL_FREE_TARGET); } static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems) { u32 i, pcpu_entries; int cpu; struct bpf_lru_list *l; pcpu_entries = nr_elems / num_possible_cpus(); i = 0; for_each_possible_cpu(cpu) { struct bpf_lru_node *node; l = per_cpu_ptr(lru->percpu_lru, cpu); again: node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; node->pending_free = 0; bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; if (i == nr_elems) break; if (i % pcpu_entries) goto again; } } void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems) { if (lru->percpu) bpf_percpu_lru_populate(lru, buf, node_offset, elem_size, nr_elems); else bpf_common_lru_populate(lru, buf, node_offset, elem_size, nr_elems); } static void bpf_lru_locallist_init(struct bpf_lru_locallist *loc_l, int cpu) { INIT_LIST_HEAD(&loc_l->pending_list); init_llist_head(&loc_l->free_llist); loc_l->next_steal = cpu; raw_res_spin_lock_init(&loc_l->lock); } static void bpf_lru_list_init(struct bpf_lru_list *l) { int i; for (i = 0; i < NR_BPF_LRU_LIST_T; i++) INIT_LIST_HEAD(&l->lists[i]); for (i = 0; i < NR_BPF_LRU_LIST_COUNT; i++) l->counts[i] = 0; l->next_inactive_rotation = &l->lists[BPF_LRU_LIST_T_INACTIVE]; raw_res_spin_lock_init(&l->lock); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, del_from_htab_func del_from_htab, void *del_arg) { int cpu; if (percpu) { lru->percpu_lru = alloc_percpu(struct bpf_lru_list); if (!lru->percpu_lru) return -ENOMEM; for_each_possible_cpu(cpu) { struct bpf_lru_list *l; l = per_cpu_ptr(lru->percpu_lru, cpu); bpf_lru_list_init(l); } lru->nr_scans = PERCPU_NR_SCANS; } else { struct bpf_common_lru *clru = &lru->common_lru; clru->local_list = alloc_percpu(struct bpf_lru_locallist); if (!clru->local_list) return -ENOMEM; for_each_possible_cpu(cpu) { struct bpf_lru_locallist *loc_l; loc_l = per_cpu_ptr(clru->local_list, cpu); bpf_lru_locallist_init(loc_l, cpu); } bpf_lru_list_init(&clru->lru_list); lru->nr_scans = LOCAL_NR_SCANS; } lru->percpu = percpu; lru->del_from_htab = del_from_htab; lru->del_arg = del_arg; lru->hash_offset = hash_offset; return 0; } void bpf_lru_destroy(struct bpf_lru *lru) { if (lru->percpu) free_percpu(lru->percpu_lru); else free_percpu(lru->common_lru.local_list); } |
| 1 1 5 1 1 4 7 2 9 15 9 6 15 8 9 9 9 2 25 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 | /* SPDX-License-Identifier: GPL-2.0 */ /* XDP user-space ring structure * Copyright(c) 2018 Intel Corporation. */ #ifndef _LINUX_XSK_QUEUE_H #define _LINUX_XSK_QUEUE_H #include <linux/types.h> #include <linux/if_xdp.h> #include <net/xdp_sock.h> #include <net/xsk_buff_pool.h> #include "xsk.h" struct xdp_ring { u32 producer ____cacheline_aligned_in_smp; /* Hinder the adjacent cache prefetcher to prefetch the consumer * pointer if the producer pointer is touched and vice versa. */ u32 pad1 ____cacheline_aligned_in_smp; u32 consumer ____cacheline_aligned_in_smp; u32 pad2 ____cacheline_aligned_in_smp; u32 flags; u32 pad3 ____cacheline_aligned_in_smp; }; /* Used for the RX and TX queues for packets */ struct xdp_rxtx_ring { struct xdp_ring ptrs; struct xdp_desc desc[] ____cacheline_aligned_in_smp; }; /* Used for the fill and completion queues for buffers */ struct xdp_umem_ring { struct xdp_ring ptrs; u64 desc[] ____cacheline_aligned_in_smp; }; struct xsk_queue { u32 ring_mask; u32 nentries; u32 cached_prod; u32 cached_cons; struct xdp_ring *ring; u64 invalid_descs; u64 queue_empty_descs; size_t ring_vmalloc_size; /* Mutual exclusion of the completion ring in the SKB mode. * Protect: when sockets share a single cq when the same netdev * and queue id is shared. */ spinlock_t cq_cached_prod_lock; }; struct parsed_desc { u32 mb; u32 valid; }; struct xsk_tx_batch { u32 tx_descs; u32 reclaim_descs; bool budget_limited; }; static inline u32 xsk_tx_batch_cq_descs(const struct xsk_tx_batch *batch) { return batch->tx_descs + batch->reclaim_descs; } /* The structure of the shared state of the rings are a simple * circular buffer, as outlined in * Documentation/core-api/circular-buffers.rst. For the Rx and * completion ring, the kernel is the producer and user space is the * consumer. For the Tx and fill rings, the kernel is the consumer and * user space is the producer. * * producer consumer * * if (LOAD ->consumer) { (A) LOAD.acq ->producer (C) * STORE $data LOAD $data * STORE.rel ->producer (B) STORE.rel ->consumer (D) * } * * (A) pairs with (D), and (B) pairs with (C). * * Starting with (B), it protects the data from being written after * the producer pointer. If this barrier was missing, the consumer * could observe the producer pointer being set and thus load the data * before the producer has written the new data. The consumer would in * this case load the old data. * * (C) protects the consumer from speculatively loading the data before * the producer pointer actually has been read. If we do not have this * barrier, some architectures could load old data as speculative loads * are not discarded as the CPU does not know there is a dependency * between ->producer and data. * * (A) is a control dependency that separates the load of ->consumer * from the stores of $data. In case ->consumer indicates there is no * room in the buffer to store $data we do not. The dependency will * order both of the stores after the loads. So no barrier is needed. * * (D) protects the load of the data to be observed to happen after the * store of the consumer pointer. If we did not have this memory * barrier, the producer could observe the consumer pointer being set * and overwrite the data with a new value before the consumer got the * chance to read the old value. The consumer would thus miss reading * the old entry and very likely read the new entry twice, once right * now and again after circling through the ring. */ /* The operations on the rings are the following: * * producer consumer * * RESERVE entries PEEK in the ring for entries * WRITE data into the ring READ data from the ring * SUBMIT entries RELEASE entries * * The producer reserves one or more entries in the ring. It can then * fill in these entries and finally submit them so that they can be * seen and read by the consumer. * * The consumer peeks into the ring to see if the producer has written * any new entries. If so, the consumer can then read these entries * and when it is done reading them release them back to the producer * so that the producer can use these slots to fill in new entries. * * The function names below reflect these operations. */ /* Functions that read and validate content from consumer rings. */ static inline void __xskq_cons_read_addr_unchecked(struct xsk_queue *q, u32 cached_cons, u64 *addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; u32 idx = cached_cons & q->ring_mask; *addr = ring->desc[idx]; } static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) { if (q->cached_cons != q->cached_prod) { __xskq_cons_read_addr_unchecked(q, q->cached_cons, addr); return true; } return false; } static inline bool xp_unused_options_set(u32 options) { return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA); } static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { u64 len = desc->len; u64 addr, offset; if (!len) return false; /* Can overflow if desc->addr < pool->tx_metadata_len */ if (check_sub_overflow(desc->addr, pool->tx_metadata_len, &addr)) return false; offset = addr & (pool->chunk_size - 1); /* * Can't overflow: @offset is guaranteed to be < ``U32_MAX`` * (pool->chunk_size is ``u32``), @len is guaranteed * to be <= ``U32_MAX``. */ if (offset + len + pool->tx_metadata_len > pool->chunk_size) return false; if (addr >= pool->addrs_cnt) return false; if (xp_unused_options_set(desc->options)) return false; return true; } static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { u64 len = desc->len; u64 addr, end; if (!len) return false; /* Can't overflow: @len is guaranteed to be <= ``U32_MAX`` */ len += pool->tx_metadata_len; if (len > pool->chunk_size) return false; /* Can overflow if desc->addr is close to 0 */ if (check_sub_overflow(xp_unaligned_add_offset_to_addr(desc->addr), pool->tx_metadata_len, &addr)) return false; if (addr >= pool->addrs_cnt) return false; /* Can overflow if pool->addrs_cnt is high enough */ if (check_add_overflow(addr, len, &end) || end > pool->addrs_cnt) return false; if (xp_desc_crosses_non_contig_pg(pool, addr, len)) return false; if (xp_unused_options_set(desc->options)) return false; return true; } static inline bool xp_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { return pool->unaligned ? xp_unaligned_validate_desc(pool, desc) : xp_aligned_validate_desc(pool, desc); } static inline bool xskq_has_descs(struct xsk_queue *q) { return q->cached_cons != q->cached_prod; } static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, struct xsk_buff_pool *pool) { if (!xp_validate_desc(pool, d)) { q->invalid_descs++; return false; } return true; } static inline bool xskq_cons_read_desc(struct xsk_queue *q, struct xdp_desc *desc, struct xsk_buff_pool *pool) { if (q->cached_cons != q->cached_prod) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = q->cached_cons & q->ring_mask; *desc = ring->desc[idx]; return xskq_cons_is_valid_desc(q, desc, pool); } q->queue_empty_descs++; return false; } static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt) { q->cached_cons += cnt; } static inline void parse_desc(struct xsk_queue *q, struct xsk_buff_pool *pool, struct xdp_desc *desc, struct parsed_desc *parsed) { parsed->valid = xskq_cons_is_valid_desc(q, desc, pool); parsed->mb = xp_mb_desc(desc); } static inline struct xsk_tx_batch xskq_cons_read_desc_batch(struct xdp_sock *xs, struct xsk_buff_pool *pool, struct xdp_desc *descs, u32 max) { bool drain = READ_ONCE(xs->drain_cont); u32 cached_cons, nb_entries = 0; struct xsk_tx_batch batch = {}; struct xsk_queue *q = xs->tx; u32 nr_frags = 0; cached_cons = q->cached_cons; while (cached_cons != q->cached_prod && nb_entries < max) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = cached_cons & q->ring_mask; struct parsed_desc parsed; descs[nb_entries] = ring->desc[idx]; cached_cons++; parse_desc(q, pool, &descs[nb_entries], &parsed); if (unlikely(!parsed.valid)) drain = true; nr_frags++; nb_entries++; if (likely(!parsed.mb)) { if (unlikely(drain)) { batch.reclaim_descs = nr_frags; WRITE_ONCE(xs->drain_cont, false); nr_frags = 0; break; } batch.tx_descs += nr_frags; nr_frags = 0; continue; } if (nr_frags == pool->xdp_zc_max_segs) drain = true; } if (nr_frags) { if (drain) { batch.reclaim_descs = nr_frags; WRITE_ONCE(xs->drain_cont, true); } else { if (nb_entries == max) batch.budget_limited = true; cached_cons -= nr_frags; } } /* Release valid plus any invalid entries */ xskq_cons_release_n(q, cached_cons - q->cached_cons); return batch; } /* Functions for consumers */ static inline void __xskq_cons_release(struct xsk_queue *q) { smp_store_release(&q->ring->consumer, q->cached_cons); /* D, matchees A */ } static inline void __xskq_cons_peek(struct xsk_queue *q) { /* Refresh the local pointer */ q->cached_prod = smp_load_acquire(&q->ring->producer); /* C, matches B */ } static inline void xskq_cons_get_entries(struct xsk_queue *q) { __xskq_cons_release(q); __xskq_cons_peek(q); } static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max) { u32 entries = q->cached_prod - q->cached_cons; if (entries >= max) return max; __xskq_cons_peek(q); entries = q->cached_prod - q->cached_cons; return entries >= max ? max : entries; } static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); return xskq_cons_read_addr_unchecked(q, addr); } static inline bool xskq_cons_peek_desc(struct xsk_queue *q, struct xdp_desc *desc, struct xsk_buff_pool *pool) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); return xskq_cons_read_desc(q, desc, pool); } /* To improve performance in the xskq_cons_release functions, only update local state here. * Reflect this to global state when we get new entries from the ring in * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop. */ static inline void xskq_cons_release(struct xsk_queue *q) { q->cached_cons++; } static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt) { q->cached_cons -= cnt; } static inline u32 xskq_cons_present_entries(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer); } /* Functions for producers */ static inline u32 xskq_get_prod(struct xsk_queue *q) { return READ_ONCE(q->ring->producer); } static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) { u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); if (free_entries >= max) return max; /* Refresh the local tail pointer */ q->cached_cons = READ_ONCE(q->ring->consumer); free_entries = q->nentries - (q->cached_prod - q->cached_cons); return free_entries >= max ? max : free_entries; } static inline bool xskq_prod_is_full(struct xsk_queue *q) { return xskq_prod_nb_free(q, 1) ? false : true; } static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt) { q->cached_prod -= cnt; } static inline int xskq_prod_reserve(struct xsk_queue *q) { if (xskq_prod_is_full(q)) return -ENOSPC; /* A, matches D */ q->cached_prod++; return 0; } static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; if (xskq_prod_is_full(q)) return -ENOSPC; /* A, matches D */ ring->desc[q->cached_prod++ & q->ring_mask] = addr; return 0; } static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; ring->desc[idx & q->ring_mask] = addr; } static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs, u32 nb_entries) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; u32 i, cached_prod; /* A, matches D */ cached_prod = q->cached_prod; for (i = 0; i < nb_entries; i++) ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr; q->cached_prod = cached_prod; } static inline void __xskq_prod_reserve_desc(struct xsk_queue *q, u64 addr, u32 len, u32 flags) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx; /* A, matches D */ idx = q->cached_prod++ & q->ring_mask; ring->desc[idx].addr = addr; ring->desc[idx].len = len; ring->desc[idx].options = flags; } static inline int xskq_prod_reserve_desc(struct xsk_queue *q, u64 addr, u32 len, u32 flags) { if (xskq_prod_is_full(q)) return -ENOBUFS; __xskq_prod_reserve_desc(q, addr, len, flags); return 0; } static inline void __xskq_prod_submit(struct xsk_queue *q, u32 idx) { smp_store_release(&q->ring->producer, idx); /* B, matches C */ } static inline void xskq_prod_submit(struct xsk_queue *q) { __xskq_prod_submit(q, q->cached_prod); } static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries) { __xskq_prod_submit(q, q->ring->producer + nb_entries); } static inline bool xskq_prod_is_empty(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ return READ_ONCE(q->ring->consumer) == READ_ONCE(q->ring->producer); } /* For both producers and consumers */ static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q) { return q ? q->invalid_descs : 0; } static inline u64 xskq_nb_queue_empty_descs(struct xsk_queue *q) { return q ? q->queue_empty_descs : 0; } struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); void xskq_destroy(struct xsk_queue *q_ops); #endif /* _LINUX_XSK_QUEUE_H */ |
| 2 4 2 2 2 4 11 9 2 4 2 2 22 25 1 17 22 3 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | // SPDX-License-Identifier: GPL-2.0 #include "linux/io_uring/query.h" #include "query.h" #include "io_uring.h" #include "zcrx.h" union io_query_data { struct io_uring_query_opcode opcodes; struct io_uring_query_zcrx zcrx; struct io_uring_query_zcrx_event zcrx_notif; struct io_uring_query_scq scq; }; #define IO_MAX_QUERY_SIZE sizeof(union io_query_data) #define IO_MAX_QUERY_ENTRIES 1000 static ssize_t io_query_ops(union io_query_data *data) { struct io_uring_query_opcode *e = &data->opcodes; e->nr_request_opcodes = IORING_OP_LAST; e->nr_register_opcodes = IORING_REGISTER_LAST; e->feature_flags = IORING_FEAT_FLAGS; e->ring_setup_flags = IORING_SETUP_FLAGS; e->enter_flags = IORING_ENTER_FLAGS; e->sqe_flags = SQE_VALID_FLAGS; e->nr_query_opcodes = __IO_URING_QUERY_MAX; e->__pad = 0; return sizeof(*e); } static ssize_t io_query_zcrx(union io_query_data *data) { struct io_uring_query_zcrx *e = &data->zcrx; e->register_flags = ZCRX_SUPPORTED_REG_FLAGS; e->area_flags = IORING_ZCRX_AREA_DMABUF; e->nr_ctrl_opcodes = __ZCRX_CTRL_LAST; e->rq_hdr_size = sizeof(struct io_uring); e->rq_hdr_alignment = L1_CACHE_BYTES; e->features = ZCRX_FEATURES; e->__resv2 = 0; return sizeof(*e); } static ssize_t io_query_zcrx_notif(union io_query_data *data) { struct io_uring_query_zcrx_event *e = &data->zcrx_notif; e->event_flags = ZCRX_EVENT_TYPE_MASK; e->stats_size = sizeof(struct zcrx_stats); e->stats_off_alignment = __alignof__(struct zcrx_stats); e->__resv1 = 0; memset(&e->__resv2, 0, sizeof(e->__resv2)); return sizeof(*e); } static ssize_t io_query_scq(union io_query_data *data) { struct io_uring_query_scq *e = &data->scq; e->hdr_size = sizeof(struct io_rings); e->hdr_alignment = SMP_CACHE_BYTES; return sizeof(*e); } static int io_handle_query_entry(union io_query_data *data, void __user *uhdr, u64 *next_entry) { struct io_uring_query_hdr hdr; size_t usize, res_size = 0; ssize_t ret = -EINVAL; void __user *udata; if (copy_from_user(&hdr, uhdr, sizeof(hdr))) return -EFAULT; usize = hdr.size; hdr.size = min(hdr.size, IO_MAX_QUERY_SIZE); udata = u64_to_user_ptr(hdr.query_data); if (hdr.query_op >= __IO_URING_QUERY_MAX) { ret = -EOPNOTSUPP; goto out; } if (!mem_is_zero(hdr.__resv, sizeof(hdr.__resv)) || hdr.result || !hdr.size) goto out; if (copy_from_user(data, udata, hdr.size)) return -EFAULT; switch (hdr.query_op) { case IO_URING_QUERY_OPCODES: ret = io_query_ops(data); break; case IO_URING_QUERY_ZCRX: ret = io_query_zcrx(data); break; case IO_URING_QUERY_ZCRX_EVENT: ret = io_query_zcrx_notif(data); break; case IO_URING_QUERY_SCQ: ret = io_query_scq(data); break; } if (ret >= 0) { if (WARN_ON_ONCE(ret > IO_MAX_QUERY_SIZE)) return -EFAULT; res_size = ret; ret = 0; } out: hdr.result = ret; hdr.size = min_t(size_t, usize, res_size); if (copy_struct_to_user(udata, usize, data, hdr.size, NULL)) return -EFAULT; if (copy_to_user(uhdr, &hdr, sizeof(hdr))) return -EFAULT; *next_entry = hdr.next_entry; return 0; } int io_query(void __user *arg, unsigned nr_args) { union io_query_data entry_buffer; void __user *uhdr = arg; int ret, nr = 0; memset(&entry_buffer, 0, sizeof(entry_buffer)); if (nr_args) return -EINVAL; while (uhdr) { u64 next_hdr; ret = io_handle_query_entry(&entry_buffer, uhdr, &next_hdr); if (ret) return ret; uhdr = u64_to_user_ptr(next_hdr); /* Have some limit to avoid a potential cycle */ if (++nr >= IO_MAX_QUERY_ENTRIES) return -ERANGE; if (fatal_signal_pending(current)) return -EINTR; cond_resched(); } return 0; } |
| 55 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 | /* * User address space access functions. * * For licencing details see kernel-base/COPYING */ #include <linux/uaccess.h> #include <linux/export.h> #include <linux/instrumented.h> #include <asm/tlbflush.h> /** * copy_from_user_nmi - NMI safe copy from user * @to: Pointer to the destination buffer * @from: Pointer to a user space address of the current task * @n: Number of bytes to copy * * Returns: The number of not copied bytes. 0 is success, i.e. all bytes copied * * Contrary to other copy_from_user() variants this function can be called * from NMI context. Despite the name it is not restricted to be called * from NMI context. It is safe to be called from any other context as * well. It disables pagefaults across the copy which means a fault will * abort the copy. * * For NMI context invocations this relies on the nested NMI work to allow * atomic faults from the NMI path; the nested NMI paths are careful to * preserve CR2. */ unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n) { unsigned long ret; if (!__access_ok(from, n)) return n; if (!nmi_uaccess_okay()) return n; /* * Even though this function is typically called from NMI/IRQ context * disable pagefaults so that its behaviour is consistent even when * called from other contexts. */ pagefault_disable(); instrument_copy_from_user_before(to, from, n); ret = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, ret); pagefault_enable(); return ret; } EXPORT_SYMBOL_GPL(copy_from_user_nmi); |
| 5 5 5 56 2 2 52 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IP Payload Compression Protocol (IPComp) - RFC3173. * * Copyright (c) 2003 James Morris <jmorris@intercode.com.au> * Copyright (c) 2003-2025 Herbert Xu <herbert@gondor.apana.org.au> * * Todo: * - Tunable compression parameters. * - Compression stats. * - Adaptive compression. */ #include <crypto/acompress.h> #include <linux/err.h> #include <linux/module.h> #include <linux/skbuff_ref.h> #include <linux/slab.h> #include <net/ipcomp.h> #include <net/xfrm.h> #define IPCOMP_SCRATCH_SIZE 65400 struct ipcomp_skb_cb { struct xfrm_skb_cb xfrm; struct acomp_req *req; }; struct ipcomp_data { u16 threshold; struct crypto_acomp *tfm; }; struct ipcomp_req_extra { struct xfrm_state *x; struct scatterlist sg[]; }; static inline struct ipcomp_skb_cb *ipcomp_cb(struct sk_buff *skb) { struct ipcomp_skb_cb *cb = (void *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof(skb->cb)); return cb; } static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen) { struct acomp_req *req = ipcomp_cb(skb)->req; struct ipcomp_req_extra *extra; struct scatterlist *dsg; int len, dlen; if (unlikely(!req)) return err; extra = acomp_request_extra(req); dsg = extra->sg; if (unlikely(err)) goto out_free_req; dlen = req->dlen; pskb_trim_unique(skb, 0); __skb_put(skb, hlen); /* Only update truesize on input. */ if (!hlen) skb->truesize += dlen; skb->data_len = dlen; skb->len += dlen; do { skb_frag_t *frag; struct page *page; frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags; page = sg_page(dsg); dsg = sg_next(dsg); len = PAGE_SIZE; if (dlen < len) len = dlen; skb_frag_fill_page_desc(frag, page, 0, len); skb_shinfo(skb)->nr_frags++; } while ((dlen -= len)); out_free_req: for (; dsg && sg_page(dsg); dsg = sg_next(dsg)) __free_page(sg_page(dsg)); acomp_request_free(req); return err; } static int ipcomp_input_done2(struct sk_buff *skb, int err) { struct ip_comp_hdr *ipch = ip_comp_hdr(skb); const int plen = skb->len; skb->transport_header = skb->network_header + sizeof(*ipch); return ipcomp_post_acomp(skb, err, 0) ?: skb->len < (plen + sizeof(ip_comp_hdr)) ? -EINVAL : ipch->nexthdr; } static void ipcomp_input_done(void *data, int err) { struct sk_buff *skb = data; xfrm_input_resume(skb, ipcomp_input_done2(skb, err)); } static struct acomp_req *ipcomp_setup_req(struct xfrm_state *x, struct sk_buff *skb, int minhead, int dlen) { const int dnfrags = min(MAX_SKB_FRAGS, 16); struct ipcomp_data *ipcd = x->data; struct ipcomp_req_extra *extra; struct scatterlist *sg, *dsg; const int plen = skb->len; struct crypto_acomp *tfm; struct acomp_req *req; int nfrags; int total; int err; int i; ipcomp_cb(skb)->req = NULL; do { struct sk_buff *trailer; if (skb->len > PAGE_SIZE) { if (skb_linearize_cow(skb)) return ERR_PTR(-ENOMEM); nfrags = 1; break; } if (!skb_cloned(skb) && skb_headlen(skb) >= minhead) { if (!skb_is_nonlinear(skb)) { nfrags = 1; break; } else if (!skb_has_frag_list(skb)) { nfrags = skb_shinfo(skb)->nr_frags; nfrags++; break; } } nfrags = skb_cow_data(skb, skb_headlen(skb) < minhead ? minhead - skb_headlen(skb) : 0, &trailer); if (nfrags < 0) return ERR_PTR(nfrags); } while (0); tfm = ipcd->tfm; req = acomp_request_alloc_extra( tfm, sizeof(*extra) + sizeof(*sg) * (nfrags + dnfrags), GFP_ATOMIC); ipcomp_cb(skb)->req = req; if (!req) return ERR_PTR(-ENOMEM); extra = acomp_request_extra(req); extra->x = x; dsg = extra->sg; sg = dsg + dnfrags; sg_init_table(sg, nfrags); err = skb_to_sgvec(skb, sg, 0, plen); if (unlikely(err < 0)) return ERR_PTR(err); sg_init_table(dsg, dnfrags); total = 0; for (i = 0; i < dnfrags && total < dlen; i++) { struct page *page; page = alloc_page(GFP_ATOMIC); if (!page) break; sg_set_page(dsg + i, page, PAGE_SIZE, 0); total += PAGE_SIZE; } if (!i) return ERR_PTR(-ENOMEM); sg_mark_end(dsg + i - 1); dlen = min(dlen, total); acomp_request_set_params(req, sg, dsg, plen, dlen); return req; } static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) { struct acomp_req *req; int err; req = ipcomp_setup_req(x, skb, 0, IPCOMP_SCRATCH_SIZE); err = PTR_ERR(req); if (IS_ERR(req)) goto out; acomp_request_set_callback(req, 0, ipcomp_input_done, skb); err = crypto_acomp_decompress(req); if (err == -EINPROGRESS) return err; out: return ipcomp_input_done2(skb, err); } int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb) { struct ip_comp_hdr *ipch __maybe_unused; if (!pskb_may_pull(skb, sizeof(*ipch))) return -EINVAL; skb->ip_summed = CHECKSUM_NONE; /* Remove ipcomp header and decompress original payload */ __skb_pull(skb, sizeof(*ipch)); return ipcomp_decompress(x, skb); } EXPORT_SYMBOL_GPL(ipcomp_input); static int ipcomp_output_push(struct sk_buff *skb) { skb_push(skb, -skb_network_offset(skb)); return 0; } static int ipcomp_output_done2(struct xfrm_state *x, struct sk_buff *skb, int err) { struct ip_comp_hdr *ipch; err = ipcomp_post_acomp(skb, err, sizeof(*ipch)); if (err) goto out_ok; /* Install ipcomp header, convert into ipcomp datagram. */ ipch = ip_comp_hdr(skb); ipch->nexthdr = *skb_mac_header(skb); ipch->flags = 0; ipch->cpi = htons((u16 )ntohl(x->id.spi)); *skb_mac_header(skb) = IPPROTO_COMP; out_ok: return ipcomp_output_push(skb); } static void ipcomp_output_done(void *data, int err) { struct ipcomp_req_extra *extra; struct sk_buff *skb = data; struct acomp_req *req; req = ipcomp_cb(skb)->req; extra = acomp_request_extra(req); xfrm_output_resume(skb_to_full_sk(skb), skb, ipcomp_output_done2(extra->x, skb, err)); } static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) { struct ip_comp_hdr *ipch __maybe_unused; struct acomp_req *req; int err; req = ipcomp_setup_req(x, skb, sizeof(*ipch), skb->len - sizeof(*ipch)); err = PTR_ERR(req); if (IS_ERR(req)) goto out; acomp_request_set_callback(req, 0, ipcomp_output_done, skb); err = crypto_acomp_compress(req); if (err == -EINPROGRESS) return err; out: return ipcomp_output_done2(x, skb, err); } int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb) { struct ipcomp_data *ipcd = x->data; if (skb->len < ipcd->threshold) { /* Don't bother compressing */ return ipcomp_output_push(skb); } return ipcomp_compress(x, skb); } EXPORT_SYMBOL_GPL(ipcomp_output); static void ipcomp_free_data(struct ipcomp_data *ipcd) { crypto_free_acomp(ipcd->tfm); } void ipcomp_destroy(struct xfrm_state *x) { struct ipcomp_data *ipcd = x->data; if (!ipcd) return; ipcomp_free_data(ipcd); kfree(ipcd); } EXPORT_SYMBOL_GPL(ipcomp_destroy); int ipcomp_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { int err; struct ipcomp_data *ipcd; struct xfrm_algo_desc *calg_desc; err = -EINVAL; if (!x->calg) { NL_SET_ERR_MSG(extack, "Missing required compression algorithm"); goto out; } if (x->encap) { NL_SET_ERR_MSG(extack, "IPComp is not compatible with encapsulation"); goto out; } err = -ENOMEM; ipcd = kzalloc_obj(*ipcd); if (!ipcd) goto out; ipcd->tfm = crypto_alloc_acomp(x->calg->alg_name, 0, 0); if (IS_ERR(ipcd->tfm)) goto error; calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0); BUG_ON(!calg_desc); ipcd->threshold = calg_desc->uinfo.comp.threshold; x->data = ipcd; err = 0; out: return err; error: ipcomp_free_data(ipcd); kfree(ipcd); goto out; } EXPORT_SYMBOL_GPL(ipcomp_init_state); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); |
| 3637 5455 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_USER_H #define _LINUX_SCHED_USER_H #include <linux/uidgid.h> #include <linux/atomic.h> #include <linux/percpu_counter.h> #include <linux/refcount.h> #include <linux/ratelimit.h> /* * Some day this will be a full-fledged user tracking system.. */ struct user_struct { refcount_t __count; /* reference count */ #ifdef CONFIG_EPOLL struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */ #endif unsigned long unix_inflight; /* How many files in flight in unix sockets */ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ /* Hash table maintenance information */ struct hlist_node uidhash_node; kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE atomic_t nr_watches; /* The number of watches this user currently has */ #endif /* Miscellaneous per-user rate limit */ struct ratelimit_state ratelimit; }; extern int uids_sysfs_init(void); extern struct user_struct *find_user(kuid_t); extern struct user_struct root_user; #define INIT_USER (&root_user) /* per-UID process charging. */ extern struct user_struct * alloc_uid(kuid_t); static inline struct user_struct *get_uid(struct user_struct *u) { refcount_inc(&u->__count); return u; } extern void free_uid(struct user_struct *); #endif /* _LINUX_SCHED_USER_H */ |
| 10 1 9 1 1 3 3 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> * Copyright (c) 2013 Eric Leblond <eric@regit.org> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_reject.h> #include <linux/icmp.h> #include <linux/icmpv6.h> const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { [NFTA_REJECT_TYPE] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 }, }; EXPORT_SYMBOL_GPL(nft_reject_policy); int nft_reject_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_PRE_ROUTING)); } EXPORT_SYMBOL_GPL(nft_reject_validate); int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); int icmp_code; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: case NFT_REJECT_ICMPX_UNREACH: if (tb[NFTA_REJECT_ICMP_CODE] == NULL) return -EINVAL; icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); if (priv->type == NFT_REJECT_ICMPX_UNREACH && icmp_code > NFT_REJECT_ICMPX_MAX) return -EINVAL; priv->icmp_code = icmp_code; break; case NFT_REJECT_TCP_RST: break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(nft_reject_init); int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_reject *priv = nft_expr_priv(expr); if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) goto nla_put_failure; switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: case NFT_REJECT_ICMPX_UNREACH: if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; default: break; } return 0; nla_put_failure: return -1; } EXPORT_SYMBOL_GPL(nft_reject_dump); static u8 icmp_code_v4[NFT_REJECT_ICMPX_MAX + 1] = { [NFT_REJECT_ICMPX_NO_ROUTE] = ICMP_NET_UNREACH, [NFT_REJECT_ICMPX_PORT_UNREACH] = ICMP_PORT_UNREACH, [NFT_REJECT_ICMPX_HOST_UNREACH] = ICMP_HOST_UNREACH, [NFT_REJECT_ICMPX_ADMIN_PROHIBITED] = ICMP_PKT_FILTERED, }; int nft_reject_icmp_code(u8 code) { if (unlikely(code > NFT_REJECT_ICMPX_MAX)) { DEBUG_NET_WARN_ON_ONCE(1); return ICMP_NET_UNREACH; } return icmp_code_v4[code]; } EXPORT_SYMBOL_GPL(nft_reject_icmp_code); static u8 icmp_code_v6[NFT_REJECT_ICMPX_MAX + 1] = { [NFT_REJECT_ICMPX_NO_ROUTE] = ICMPV6_NOROUTE, [NFT_REJECT_ICMPX_PORT_UNREACH] = ICMPV6_PORT_UNREACH, [NFT_REJECT_ICMPX_HOST_UNREACH] = ICMPV6_ADDR_UNREACH, [NFT_REJECT_ICMPX_ADMIN_PROHIBITED] = ICMPV6_ADM_PROHIBITED, }; int nft_reject_icmpv6_code(u8 code) { if (unlikely(code > NFT_REJECT_ICMPX_MAX)) { DEBUG_NET_WARN_ON_ONCE(1); return ICMPV6_NOROUTE; } return icmp_code_v6[code]; } EXPORT_SYMBOL_GPL(nft_reject_icmpv6_code); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Netfilter x_tables over nftables module"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Routines to manage notifier chains for passing status changes to any * interested routines. We need this instead of hard coded call lists so * that modules can poke their nose into the innards. The network devices * needed them so here they are for the rest of you. * * Alan Cox <Alan.Cox@linux.org> */ #ifndef _LINUX_NOTIFIER_H #define _LINUX_NOTIFIER_H #include <linux/errno.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/srcu.h> /* * Notifier chains are of four types: * * Atomic notifier chains: Chain callbacks run in interrupt/atomic * context. Callouts are not allowed to block. * Blocking notifier chains: Chain callbacks run in process context. * Callouts are allowed to block. * Raw notifier chains: There are no restrictions on callbacks, * registration, or unregistration. All locking and protection * must be provided by the caller. * SRCU notifier chains: A variant of blocking notifier chains, with * the same restrictions. * * atomic_notifier_chain_register() may be called from an atomic context, * but blocking_notifier_chain_register() and srcu_notifier_chain_register() * must be called from a process context. Ditto for the corresponding * _unregister() routines. * * atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(), * and srcu_notifier_chain_unregister() _must not_ be called from within * the call chain. * * SRCU notifier chains are an alternative form of blocking notifier chains. * They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for * protection of the chain links. This means there is _very_ low overhead * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very * often but notifier_blocks will seldom be removed. */ struct notifier_block; typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); struct notifier_block { notifier_fn_t notifier_call; struct notifier_block __rcu *next; int priority; }; struct atomic_notifier_head { spinlock_t lock; struct notifier_block __rcu *head; }; struct blocking_notifier_head { struct rw_semaphore rwsem; struct notifier_block __rcu *head; }; struct raw_notifier_head { struct notifier_block __rcu *head; }; struct srcu_notifier_head { struct mutex mutex; struct srcu_usage srcuu; struct srcu_struct srcu; struct notifier_block __rcu *head; }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ } while (0) #define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ init_rwsem(&(name)->rwsem); \ (name)->head = NULL; \ } while (0) #define RAW_INIT_NOTIFIER_HEAD(name) do { \ (name)->head = NULL; \ } while (0) /* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); #define ATOMIC_NOTIFIER_INIT(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } #define BLOCKING_NOTIFIER_INIT(name) { \ .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ .srcuu = __SRCU_USAGE_INIT(name.srcuu), \ .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu, 0), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ ATOMIC_NOTIFIER_INIT(name) #define BLOCKING_NOTIFIER_HEAD(name) \ struct blocking_notifier_head name = \ BLOCKING_NOTIFIER_INIT(name) #define RAW_NOTIFIER_HEAD(name) \ struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) #else #define _SRCU_NOTIFIER_HEAD(name, mod) \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name) #endif #define SRCU_NOTIFIER_HEAD(name) \ _SRCU_NOTIFIER_HEAD(name, /* not static */) #define SRCU_NOTIFIER_HEAD_STATIC(name) \ _SRCU_NOTIFIER_HEAD(name, static) #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_register_unique_prio( struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register_unique_prio( struct blocking_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v); extern int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v); extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ #define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) /* Bad/Veto action */ /* * Clean way to return from the notifier and stop further calls. */ #define NOTIFY_STOP (NOTIFY_OK|NOTIFY_STOP_MASK) /* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */ static inline int notifier_from_errno(int err) { if (err) return NOTIFY_STOP_MASK | (NOTIFY_OK - err); return NOTIFY_OK; } /* Restore (negative) errno value from notify return value. */ static inline int notifier_to_errno(int ret) { ret &= ~NOTIFY_STOP_MASK; return ret > NOTIFY_OK ? NOTIFY_OK - ret : 0; } /* * Declared notifiers so far. I can imagine quite a few more chains * over time (eg laptop power reset chains, reboot chain (to clean * device units up), device [un]mount chain, module load/unload chain, * low memory chain, screenblank chain (for plug in modular screenblankers) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ /* CPU notfiers are defined in include/linux/cpu.h. */ /* netdevice notifiers are defined in include/linux/netdevice.h */ /* reboot notifiers are defined in include/linux/reboot.h. */ /* Hibernation and suspend events are defined in include/linux/suspend.h. */ /* Virtual Terminal events are defined in include/linux/vt.h. */ #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and * KBD_KEYSYM. */ #define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */ #define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */ #define KBD_UNICODE 0x0003 /* Keyboard unicode */ #define KBD_KEYSYM 0x0004 /* Keyboard keysym */ #define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * CPU/APIC topology * * The APIC IDs describe the system topology in multiple domain levels. * The CPUID topology parser provides the information which part of the * APIC ID is associated to the individual levels: * * [PACKAGE][DIEGRP][DIE][TILE][MODULE][CORE][THREAD] * * The root space contains the package (socket) IDs. * * Not enumerated levels consume 0 bits space, but conceptually they are * always represented. If e.g. only CORE and THREAD levels are enumerated * then the DIE, MODULE and TILE have the same physical ID as the PACKAGE. * * If SMT is not supported, then the THREAD domain is still used. It then * has the same physical ID as the CORE domain and is the only child of * the core domain. * * This allows a unified view on the system independent of the enumerated * domain levels without requiring any conditionals in the code. */ #define pr_fmt(fmt) "CPU topo: " fmt #include <linux/cpu.h> #include <xen/xen.h> #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/smp.h> #include <asm/numa.h> #include "cpu.h" /* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID); DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, CPU_ACPIID_INVALID); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid); /* Bitmap of physically present CPUs. */ DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC) __read_mostly; /* Used for CPU number allocation and parallel CPU bringup */ u32 cpuid_to_apicid[] __ro_after_init = { [0 ... NR_CPUS - 1] = BAD_APICID, }; /* Bitmaps to mark registered APICs at each topology domain */ static struct { DECLARE_BITMAP(map, MAX_LOCAL_APIC); } apic_maps[TOPO_MAX_DOMAIN] __ro_after_init; /* * Keep track of assigned, disabled and rejected CPUs. Present assigned * with 1 as CPU #0 is reserved for the boot CPU. */ static struct { unsigned int nr_assigned_cpus; unsigned int nr_disabled_cpus; unsigned int nr_rejected_cpus; u32 boot_cpu_apic_id; u32 real_bsp_apic_id; } topo_info __ro_after_init = { .nr_assigned_cpus = 1, .boot_cpu_apic_id = BAD_APICID, .real_bsp_apic_id = BAD_APICID, }; #define domain_weight(_dom) bitmap_weight(apic_maps[_dom].map, MAX_LOCAL_APIC) bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { return phys_id == (u64)cpuid_to_apicid[cpu]; } static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { if (!(apicid & (__max_threads_per_core - 1))) cpumask_set_cpu(cpu, &__cpu_primary_thread_mask); } /* * Convert the APIC ID to a domain level ID by masking out the low bits * below the domain level @dom. */ static inline u32 topo_apicid(u32 apicid, enum x86_topology_domains dom) { if (dom == TOPO_SMT_DOMAIN) return apicid; return apicid & (UINT_MAX << x86_topo_system.dom_shifts[dom - 1]); } static int topo_lookup_cpuid(u32 apic_id) { int i; /* CPU# to APICID mapping is persistent once it is established */ for (i = 0; i < topo_info.nr_assigned_cpus; i++) { if (cpuid_to_apicid[i] == apic_id) return i; } return -ENODEV; } static __init int topo_get_cpunr(u32 apic_id) { int cpu = topo_lookup_cpuid(apic_id); if (cpu >= 0) return cpu; return topo_info.nr_assigned_cpus++; } static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) { #if defined(CONFIG_SMP) || defined(CONFIG_X86_64) early_per_cpu(x86_cpu_to_apicid, cpu) = apic_id; early_per_cpu(x86_cpu_to_acpiid, cpu) = acpi_id; #endif set_cpu_present(cpu, true); } static __init bool check_for_real_bsp(u32 apic_id) { bool is_bsp = false, has_apic_base = boot_cpu_data.x86 >= 6; u64 msr; /* * There is no real good way to detect whether this a kdump() * kernel, but except on the Voyager SMP monstrosity which is not * longer supported, the real BSP APIC ID is the first one which is * enumerated by firmware. That allows to detect whether the boot * CPU is the real BSP. If it is not, then do not register the APIC * because sending INIT to the real BSP would reset the whole * system. * * The first APIC ID which is enumerated by firmware is detectable * because the boot CPU APIC ID is registered before that without * invoking this code. */ if (topo_info.real_bsp_apic_id != BAD_APICID) return false; /* * Check whether the enumeration order is broken by evaluating the * BSP bit in the APICBASE MSR. If the CPU does not have the * APICBASE MSR then the BSP detection is not possible and the * kernel must rely on the firmware enumeration order. */ if (has_apic_base) { rdmsrq(MSR_IA32_APICBASE, msr); is_bsp = !!(msr & MSR_IA32_APICBASE_BSP); } if (apic_id == topo_info.boot_cpu_apic_id) { /* * If the boot CPU has the APIC BSP bit set then the * firmware enumeration is agreeing. If the CPU does not * have the APICBASE MSR then the only choice is to trust * the enumeration order. */ if (is_bsp || !has_apic_base) { topo_info.real_bsp_apic_id = apic_id; return false; } /* * If the boot APIC is enumerated first, but the APICBASE * MSR does not have the BSP bit set, then there is no way * to discover the real BSP here. Assume a crash kernel and * limit the number of CPUs to 1 as an INIT to the real BSP * would reset the machine. */ pr_warn("Enumerated BSP APIC %x is not marked in APICBASE MSR\n", apic_id); pr_warn("Assuming crash kernel. Limiting to one CPU to prevent machine INIT\n"); set_nr_cpu_ids(1); goto fwbug; } pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x != %x\n", topo_info.boot_cpu_apic_id, apic_id); if (is_bsp) { /* * The boot CPU has the APIC BSP bit set. Use it and complain * about the broken firmware enumeration. */ topo_info.real_bsp_apic_id = topo_info.boot_cpu_apic_id; goto fwbug; } pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n"); topo_info.real_bsp_apic_id = apic_id; return true; fwbug: pr_warn(FW_BUG "APIC enumeration order not specification compliant\n"); return false; } static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level, unsigned long *map) { unsigned int end; /* Calculate the exclusive end */ end = lvlid + (1U << x86_topo_system.dom_shifts[at_level]); return bitmap_weight_from(map, lvlid, end); } static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present) { int cpu, dom; if (present) { set_bit(apic_id, phys_cpu_present_map); /* * Double registration is valid in case of the boot CPU * APIC because that is registered before the enumeration * of the APICs via firmware parsers or VM guest * mechanisms. */ if (apic_id == topo_info.boot_cpu_apic_id) cpu = 0; else cpu = topo_get_cpunr(apic_id); cpuid_to_apicid[cpu] = apic_id; topo_set_cpuids(cpu, apic_id, acpi_id); } else { topo_info.nr_disabled_cpus++; } /* * Register present and possible CPUs in the domain * maps. cpu_possible_map will be updated in * topology_init_possible_cpus() after enumeration is done. */ for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) set_bit(topo_apicid(apic_id, dom), apic_maps[dom].map); } /** * topology_register_apic - Register an APIC in early topology maps * @apic_id: The APIC ID to set up * @acpi_id: The ACPI ID associated to the APIC * @present: True if the corresponding CPU is present */ void __init topology_register_apic(u32 apic_id, u32 acpi_id, bool present) { if (apic_id >= MAX_LOCAL_APIC) { pr_err_once("APIC ID %x exceeds kernel limit of: %x\n", apic_id, MAX_LOCAL_APIC - 1); topo_info.nr_rejected_cpus++; return; } if (check_for_real_bsp(apic_id)) { topo_info.nr_rejected_cpus++; return; } /* CPU numbers exhausted? */ if (apic_id != topo_info.boot_cpu_apic_id && topo_info.nr_assigned_cpus >= nr_cpu_ids) { pr_warn_once("CPU limit of %d reached. Ignoring further CPUs\n", nr_cpu_ids); topo_info.nr_rejected_cpus++; return; } topo_register_apic(apic_id, acpi_id, present); } /** * topology_register_boot_apic - Register the boot CPU APIC * @apic_id: The APIC ID to set up * * Separate so CPU #0 can be assigned */ void __init topology_register_boot_apic(u32 apic_id) { WARN_ON_ONCE(topo_info.boot_cpu_apic_id != BAD_APICID); topo_info.boot_cpu_apic_id = apic_id; topo_register_apic(apic_id, CPU_ACPIID_INVALID, true); } /** * topology_get_logical_id - Retrieve the logical ID at a given topology domain level * @apicid: The APIC ID for which to lookup the logical ID * @at_level: The topology domain level to use * * @apicid must be a full APIC ID, not the normalized variant. It's valid to have * all bits below the domain level specified by @at_level to be clear. So both * real APIC IDs and backshifted normalized APIC IDs work correctly. * * Returns: * - >= 0: The requested logical ID * - -ERANGE: @apicid is out of range * - -ENODEV: @apicid is not registered */ int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level) { /* Remove the bits below @at_level to get the proper level ID of @apicid */ unsigned int lvlid = topo_apicid(apicid, at_level); if (lvlid >= MAX_LOCAL_APIC) return -ERANGE; if (!test_bit(lvlid, apic_maps[at_level].map)) return -ENODEV; /* Get the number of set bits before @lvlid. */ return bitmap_weight(apic_maps[at_level].map, lvlid); } EXPORT_SYMBOL_GPL(topology_get_logical_id); /** * topology_unit_count - Retrieve the count of specified units at a given topology domain level * @apicid: The APIC ID which specifies the search range * @which_units: The domain level specifying the units to count * @at_level: The domain level at which @which_units have to be counted * * This returns the number of possible units according to the enumerated * information. * * E.g. topology_count_units(apicid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN) * counts the number of possible cores in the package to which @apicid * belongs. * * @at_level must obviously be greater than @which_level to produce useful * results. If @at_level is equal to @which_units the result is * unsurprisingly 1. If @at_level is less than @which_units the results * is by definition undefined and the function returns 0. */ unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units, enum x86_topology_domains at_level) { /* Remove the bits below @at_level to get the proper level ID of @apicid */ unsigned int lvlid = topo_apicid(apicid, at_level); if (lvlid >= MAX_LOCAL_APIC) return 0; if (!test_bit(lvlid, apic_maps[at_level].map)) return 0; if (which_units > at_level) return 0; if (which_units == at_level) return 1; return topo_unit_count(lvlid, at_level, apic_maps[which_units].map); } #ifdef CONFIG_SMP int topology_get_primary_thread(unsigned int cpu) { u32 apic_id = cpuid_to_apicid[cpu]; /* * Get the core domain level APIC id, which is the primary thread * and return the CPU number assigned to it. */ return topo_lookup_cpuid(topo_apicid(apic_id, TOPO_CORE_DOMAIN)); } #endif #ifdef CONFIG_ACPI_HOTPLUG_CPU /** * topology_hotplug_apic - Handle a physical hotplugged APIC after boot * @apic_id: The APIC ID to set up * @acpi_id: The ACPI ID associated to the APIC */ int topology_hotplug_apic(u32 apic_id, u32 acpi_id) { int cpu; if (apic_id >= MAX_LOCAL_APIC) return -EINVAL; /* Reject if the APIC ID was not registered during enumeration. */ if (!test_bit(apic_id, apic_maps[TOPO_SMT_DOMAIN].map)) return -ENODEV; cpu = topo_lookup_cpuid(apic_id); if (cpu < 0) return -ENOSPC; set_bit(apic_id, phys_cpu_present_map); topo_set_cpuids(cpu, apic_id, acpi_id); cpu_mark_primary_thread(cpu, apic_id); return cpu; } /** * topology_hotunplug_apic - Remove a physical hotplugged APIC after boot * @cpu: The CPU number for which the APIC ID is removed */ void topology_hotunplug_apic(unsigned int cpu) { u32 apic_id = cpuid_to_apicid[cpu]; if (apic_id == BAD_APICID) return; per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; clear_bit(apic_id, phys_cpu_present_map); set_cpu_present(cpu, false); } #endif #ifdef CONFIG_X86_LOCAL_APIC static unsigned int max_possible_cpus __initdata = NR_CPUS; /** * topology_apply_cmdline_limits_early - Apply topology command line limits early * * Ensure that command line limits are in effect before firmware parsing * takes place. */ void __init topology_apply_cmdline_limits_early(void) { unsigned int possible = nr_cpu_ids; /* 'maxcpus=0' 'nosmp' 'nolapic' */ if (!setup_max_cpus || apic_is_disabled) possible = 1; /* 'possible_cpus=N' */ possible = min_t(unsigned int, max_possible_cpus, possible); if (possible < nr_cpu_ids) { pr_info("Limiting to %u possible CPUs\n", possible); set_nr_cpu_ids(possible); } } static __init bool restrict_to_up(void) { if (!smp_found_config) return true; /* * XEN PV is special as it does not advertise the local APIC * properly, but provides a fake topology for it so that the * infrastructure works. So don't apply the restrictions vs. APIC * here. */ if (xen_pv_domain()) return false; return apic_is_disabled; } void __init topology_init_possible_cpus(void) { unsigned int assigned = topo_info.nr_assigned_cpus; unsigned int disabled = topo_info.nr_disabled_cpus; unsigned int cnta, cntb, cpu, allowed = 1; unsigned int total = assigned + disabled; u32 apicid, firstid; /* * If there was no APIC registered, then fake one so that the * topology bitmap is populated. That ensures that the code below * is valid and the various query interfaces can be used * unconditionally. This does not affect the actual APIC code in * any way because either the local APIC address has not been * registered or the local APIC was disabled on the command line. */ if (topo_info.boot_cpu_apic_id == BAD_APICID) topology_register_boot_apic(0); if (!restrict_to_up()) { if (WARN_ON_ONCE(assigned > nr_cpu_ids)) { disabled += assigned - nr_cpu_ids; assigned = nr_cpu_ids; } allowed = min_t(unsigned int, total, nr_cpu_ids); } if (total > allowed) pr_warn("%u possible CPUs exceed the limit of %u\n", total, allowed); assigned = min_t(unsigned int, allowed, assigned); disabled = allowed - assigned; topo_info.nr_assigned_cpus = assigned; topo_info.nr_disabled_cpus = disabled; total_cpus = allowed; set_nr_cpu_ids(allowed); cnta = domain_weight(TOPO_PKG_DOMAIN); __max_logical_packages = cnta; pr_info("Max. logical packages: %3u\n", __max_logical_packages); cntb = num_phys_nodes(); __num_nodes_per_package = DIV_ROUND_UP(cntb, cnta); pr_info("Max. logical nodes: %3u\n", cntb); pr_info("Num. nodes per package:%3u\n", __num_nodes_per_package); cntb = domain_weight(TOPO_DIE_DOMAIN); __max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta)); pr_info("Max. logical dies: %3u\n", cntb); pr_info("Max. dies per package: %3u\n", __max_dies_per_package); cnta = domain_weight(TOPO_CORE_DOMAIN); cntb = domain_weight(TOPO_SMT_DOMAIN); /* * Can't use order delta here as order(cnta) can be equal * order(cntb) even if cnta != cntb. */ __max_threads_per_core = DIV_ROUND_UP(cntb, cnta); pr_info("Max. threads per core: %3u\n", __max_threads_per_core); firstid = find_first_bit(apic_maps[TOPO_SMT_DOMAIN].map, MAX_LOCAL_APIC); __num_cores_per_package = topology_unit_count(firstid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN); pr_info("Num. cores per package: %3u\n", __num_cores_per_package); __num_threads_per_package = topology_unit_count(firstid, TOPO_SMT_DOMAIN, TOPO_PKG_DOMAIN); pr_info("Num. threads per package: %3u\n", __num_threads_per_package); pr_info("Allowing %u present CPUs plus %u hotplug CPUs\n", assigned, disabled); if (topo_info.nr_rejected_cpus) pr_info("Rejected CPUs %u\n", topo_info.nr_rejected_cpus); init_cpu_present(cpumask_of(0)); init_cpu_possible(cpumask_of(0)); /* Assign CPU numbers to non-present CPUs */ for (apicid = 0; disabled; disabled--, apicid++) { apicid = find_next_andnot_bit(apic_maps[TOPO_SMT_DOMAIN].map, phys_cpu_present_map, MAX_LOCAL_APIC, apicid); if (apicid >= MAX_LOCAL_APIC) break; cpuid_to_apicid[topo_info.nr_assigned_cpus++] = apicid; } for (cpu = 0; cpu < allowed; cpu++) { apicid = cpuid_to_apicid[cpu]; set_cpu_possible(cpu, true); if (apicid == BAD_APICID) continue; cpu_mark_primary_thread(cpu, apicid); set_cpu_present(cpu, test_bit(apicid, phys_cpu_present_map)); } } /* * Late SMP disable after sizing CPU masks when APIC/IOAPIC setup failed. */ void __init topology_reset_possible_cpus_up(void) { init_cpu_present(cpumask_of(0)); init_cpu_possible(cpumask_of(0)); bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC); if (topo_info.boot_cpu_apic_id != BAD_APICID) set_bit(topo_info.boot_cpu_apic_id, phys_cpu_present_map); } static int __init setup_possible_cpus(char *str) { get_option(&str, &max_possible_cpus); return 0; } early_param("possible_cpus", setup_possible_cpus); #endif |
| 88 86 7 2 9 9 7 2 90 83 10 87 9 84 76 2 76 72 72 72 72 6 14 5 1 5 1 5 4 1 5 45 4 44 3 13 15 6 1 5 1 2 6 1 5 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cgroup.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include "cgroup-internal.h" #include <trace/events/cgroup.h> /* * Update CGRP_FROZEN of cgroup.flag * Return true if flags is updated; false if flags has no change */ static bool cgroup_update_frozen_flag(struct cgroup *cgrp, bool frozen) { lockdep_assert_held(&css_set_lock); /* Already there? */ if (test_bit(CGRP_FROZEN, &cgrp->flags) == frozen) return false; if (frozen) set_bit(CGRP_FROZEN, &cgrp->flags); else clear_bit(CGRP_FROZEN, &cgrp->flags); cgroup_file_notify(&cgrp->events_file); TRACE_CGROUP_PATH(notify_frozen, cgrp, frozen); return true; } /* * Propagate the cgroup frozen state upwards by the cgroup tree. */ static void cgroup_propagate_frozen(struct cgroup *cgrp, bool frozen) { int desc = 1; /* * If the new state is frozen, some freezing ancestor cgroups may change * their state too, depending on if all their descendants are frozen. * * Otherwise, all ancestor cgroups are forced into the non-frozen state. */ while ((cgrp = cgroup_parent(cgrp))) { if (frozen) { cgrp->freezer.nr_frozen_descendants += desc; if (!test_bit(CGRP_FREEZE, &cgrp->flags) || (cgrp->freezer.nr_frozen_descendants != cgrp->nr_descendants)) continue; } else { cgrp->freezer.nr_frozen_descendants -= desc; } if (cgroup_update_frozen_flag(cgrp, frozen)) desc++; } } /* * Revisit the cgroup frozen state. * Checks if the cgroup is really frozen and perform all state transitions. */ void cgroup_update_frozen(struct cgroup *cgrp) { bool frozen; /* * If the cgroup has to be frozen (CGRP_FREEZE bit set), * and all tasks are frozen and/or stopped, let's consider * the cgroup frozen. Otherwise it's not frozen. */ frozen = test_bit(CGRP_FREEZE, &cgrp->flags) && cgrp->freezer.nr_frozen_tasks == __cgroup_task_count(cgrp); /* If flags is updated, update the state of ancestor cgroups. */ if (cgroup_update_frozen_flag(cgrp, frozen)) cgroup_propagate_frozen(cgrp, frozen); } /* * Increment cgroup's nr_frozen_tasks. */ static void cgroup_inc_frozen_cnt(struct cgroup *cgrp) { cgrp->freezer.nr_frozen_tasks++; } /* * Decrement cgroup's nr_frozen_tasks. */ static void cgroup_dec_frozen_cnt(struct cgroup *cgrp) { cgrp->freezer.nr_frozen_tasks--; WARN_ON_ONCE(cgrp->freezer.nr_frozen_tasks < 0); } /* * Enter frozen/stopped state, if not yet there. Update cgroup's counters, * and revisit the state of the cgroup, if necessary. */ void cgroup_enter_frozen(void) { struct cgroup *cgrp; if (current->frozen) return; spin_lock_irq(&css_set_lock); current->frozen = true; cgrp = task_dfl_cgroup(current); cgroup_inc_frozen_cnt(cgrp); cgroup_update_frozen(cgrp); spin_unlock_irq(&css_set_lock); } /* * Conditionally leave frozen/stopped state. Update cgroup's counters, * and revisit the state of the cgroup, if necessary. * * If always_leave is not set, and the cgroup is freezing, * we're racing with the cgroup freezing. In this case, we don't * drop the frozen counter to avoid a transient switch to * the unfrozen state. */ void cgroup_leave_frozen(bool always_leave) { struct cgroup *cgrp; spin_lock_irq(&css_set_lock); cgrp = task_dfl_cgroup(current); if (always_leave || !test_bit(CGRP_FREEZE, &cgrp->flags)) { cgroup_dec_frozen_cnt(cgrp); cgroup_update_frozen(cgrp); WARN_ON_ONCE(!current->frozen); current->frozen = false; } else if (!(current->jobctl & JOBCTL_TRAP_FREEZE)) { spin_lock(¤t->sighand->siglock); current->jobctl |= JOBCTL_TRAP_FREEZE; set_thread_flag(TIF_SIGPENDING); spin_unlock(¤t->sighand->siglock); } spin_unlock_irq(&css_set_lock); } /* * Freeze or unfreeze the task by setting or clearing the JOBCTL_TRAP_FREEZE * jobctl bit. */ static void cgroup_freeze_task(struct task_struct *task, bool freeze) { unsigned long flags; /* If the task is about to die, don't bother with freezing it. */ if (!lock_task_sighand(task, &flags)) return; if (freeze) { task->jobctl |= JOBCTL_TRAP_FREEZE; signal_wake_up(task, false); } else { task->jobctl &= ~JOBCTL_TRAP_FREEZE; wake_up_process(task); } unlock_task_sighand(task, &flags); } /* * Freeze or unfreeze all tasks in the given cgroup. */ static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze, u64 ts_nsec) { struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); write_seqcount_begin(&cgrp->freezer.freeze_seq); if (freeze) { set_bit(CGRP_FREEZE, &cgrp->flags); cgrp->freezer.freeze_start_nsec = ts_nsec; } else { clear_bit(CGRP_FREEZE, &cgrp->flags); cgrp->freezer.frozen_nsec += (ts_nsec - cgrp->freezer.freeze_start_nsec); } write_seqcount_end(&cgrp->freezer.freeze_seq); spin_unlock_irq(&css_set_lock); if (freeze) TRACE_CGROUP_PATH(freeze, cgrp); else TRACE_CGROUP_PATH(unfreeze, cgrp); css_task_iter_start(&cgrp->self, 0, &it); while ((task = css_task_iter_next(&it))) { /* * Ignore kernel threads here. Freezing cgroups containing * kthreads isn't supported. */ if (task->flags & PF_KTHREAD) continue; cgroup_freeze_task(task, freeze); } css_task_iter_end(&it); /* * Cgroup state should be revisited here to cover empty leaf cgroups * and cgroups which descendants are already in the desired state. */ spin_lock_irq(&css_set_lock); if (cgrp->nr_descendants == cgrp->freezer.nr_frozen_descendants) cgroup_update_frozen(cgrp); spin_unlock_irq(&css_set_lock); } /* * Adjust the task state (freeze or unfreeze) and revisit the state of * source and destination cgroups. */ void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst) { lockdep_assert_held(&css_set_lock); /* * Kernel threads are not supposed to be frozen at all. */ if (task->flags & PF_KTHREAD) return; /* * It's not necessary to do changes if both of the src and dst cgroups * are not freezing and task is not frozen. */ if (!test_bit(CGRP_FREEZE, &src->flags) && !test_bit(CGRP_FREEZE, &dst->flags) && !task->frozen) return; /* * Adjust counters of freezing and frozen tasks. * Note, that if the task is frozen, but the destination cgroup is not * frozen, we bump both counters to keep them balanced. */ if (task->frozen) { cgroup_inc_frozen_cnt(dst); cgroup_dec_frozen_cnt(src); } cgroup_update_frozen(dst); cgroup_update_frozen(src); /* * Force the task to the desired state. */ cgroup_freeze_task(task, test_bit(CGRP_FREEZE, &dst->flags)); } void cgroup_freeze(struct cgroup *cgrp, bool freeze) { struct cgroup_subsys_state *css; struct cgroup *parent; struct cgroup *dsct; bool applied = false; u64 ts_nsec; bool old_e; lockdep_assert_held(&cgroup_mutex); /* * Nothing changed? Just exit. */ if (cgrp->freezer.freeze == freeze) return; cgrp->freezer.freeze = freeze; ts_nsec = ktime_get_ns(); /* * Propagate changes downwards the cgroup tree. */ css_for_each_descendant_pre(css, &cgrp->self) { dsct = css->cgroup; if (cgroup_is_dead(dsct)) continue; /* * e_freeze is affected by parent's e_freeze and dst's freeze. * If old e_freeze eq new e_freeze, no change, its children * will not be affected. So do nothing and skip the subtree */ old_e = dsct->freezer.e_freeze; parent = cgroup_parent(dsct); dsct->freezer.e_freeze = (dsct->freezer.freeze || parent->freezer.e_freeze); if (dsct->freezer.e_freeze == old_e) { css = css_rightmost_descendant(css); continue; } /* * Do change actual state: freeze or unfreeze. */ cgroup_do_freeze(dsct, freeze, ts_nsec); applied = true; } /* * Even if the actual state hasn't changed, let's notify a user. * The state can be enforced by an ancestor cgroup: the cgroup * can already be in the desired state or it can be locked in the * opposite state, so that the transition will never happen. * In both cases it's better to notify a user, that there is * nothing to wait for. */ if (!applied) { TRACE_CGROUP_PATH(notify_frozen, cgrp, test_bit(CGRP_FROZEN, &cgrp->flags)); cgroup_file_notify(&cgrp->events_file); } } |
| 419 1 27 393 27 7413 3 471 6919 419 7161 5040 381 38 3 6 30 1949 1 1930 16 1948 60 5646 695 7216 402 31 31 28 28 5 5 1 1 6 6 9 9 49 5 2 12 1 32 10 1417 2172 6915 71 85 18 97 7263 7254 106 392 361 47 364 358 7076 1397 2985 7084 4366 7257 7277 76 4321 7275 399 7254 2286 1675 6857 3019 5179 5472 5185 894 7393 7399 7417 35 4884 30 7384 7344 63 63 63 284 121 121 115 201 7377 7317 114 7334 6322 2049 201 4 127 128 593 16 6426 1 7178 5 7177 113 7172 7169 190 2 186 45 142 5616 6693 1979 52 5287 74 6707 18 5654 2368 3627 3486 3491 3488 389 3557 3 3551 2 1 3550 351 385 2 1 381 1005 1158 732 893 684 35 35 660 15 5 1 1 1 1 1 1 1 31 2 40 17 31 12 12 12 4 8 15 26 38 494 448 467 1 29 39 15 461 64 465 15 39 31 490 487 4 78 1 77 3994 3 3983 14 1 3909 3973 2955 1208 3990 19 27 388 412 1579 2 48 3155 304 89 14 3238 3242 2 3080 49 46 59 3196 6152 2778 5448 797 2 1 123 964 750 572 21 1789 2 7 3 1787 1723 105 1787 7224 7181 2 12 341 68 1248 2 63 1251 1160 552 1248 52 61 974 684 4 1104 61 479 1 426 571 720 382 925 3 285 1206 391 4799 4808 1581 4389 1315 4035 1811 386 3039 4252 57 4900 146 116 30 130 130 3 16 126 109 4 8 116 3 8 5411 5311 174 89 146 126 225 138 217 1 6 706 26 4784 29 5261 1716 3419 980 5549 1 3744 2834 4202 1 148 148 646 1785 7400 1467 5889 3303 186 7236 340 1786 6234 229 5189 6576 410 7107 48 7117 903 6349 697 964 6341 3 9 7386 7 7275 177 7277 335 7395 7390 65 35 30 3270 1 5510 5517 5525 163 100 267 11 271 225 40 5750 4 1 33 3441 15 4045 93 89 93 4122 4110 35 2672 4045 3767 65 3693 1154 4173 166 4053 4032 40 4032 593 3748 4044 21 176 20 1262 1394 111 1306 1300 176 21 194 194 1261 1304 2028 38 1987 2055 2045 2580 1807 1801 35 35 2160 2160 2160 2144 2142 1 77 76 16 1 15 89 10 79 88 41 47 37 4 33 15 2 13 78 78 1 78 2776 2772 15 1 378 377 4 2 373 2 201 187 367 1001 1004 1004 83 15 38 4 42 2 141 1 1 142 83 221 141 83 33 5 1 1 213 40 1 1 1 1 1 1 1 214 1306 63 1 62 62 10 51 45 10 37 1471 50 1472 4073 2363 39 1221 2293 66 1877 301 4037 21 4035 147 17 605 2222 599 1780 653 1667 2 21 2207 2213 9 14 1663 644 1747 642 1664 643 39 622 7 2210 2156 85 1 1764 528 21 516 2 511 175 1774 477 2116 653 1666 643 1753 2219 4 1 2 1 770 3574 12 3985 153 7 2 122 4 4148 28 2967 580 1666 587 73 174 1775 477 3776 126 3779 2647 476 26 4060 3784 3554 687 4 674 4050 4048 477 3651 155 398 3996 3769 147 4038 3943 151 37 1 1 36 5 35 6 17 18 44 8 1 8 35 57 38 27 4365 2 44 56 1534 4240 4068 2433 3913 4386 69 4348 4328 115 4328 4336 30 30 30 30 29 30 30 1016 167 1 896 12 12 132 41 41 53 508 25 24 99 3 96 3 94 94 29 2 92 1 10 83 161 6 167 167 41 127 127 121 7 5 125 93 93 75 72 522 3 2 516 516 515 100 456 109 585 185 521 108 457 516 4 2 517 483 478 114 113 92 3 1 88 88 87 23 60 30 60 115 34 1 1 1 1 10 92 92 5 4 95 66 65 83 5 1 77 77 1 4 5 68 68 84 23 15 60 6 4 1 66 90 1 49 41 89 43 41 190 2 2 186 24 167 222 20 48 186 5 4 189 164 163 63 63 35 2 1 1 30 3 1 26 81 3 37 1 35 33 4 4 34 37 37 44 39 210 2 2 109 68 35 5 3 124 32 43 62 11 196 59 42 68 39 3 9 85 196 197 193 5 118 72 95 93 136 52 51 105 26 14 40 112 32 194 112 90 64 113 32 283 2 4 54 18 1 1 1 1 40 175 18 19 104 2 107 213 217 9 7 233 158 157 19 19 108 107 13 27 9 36 42 5 5 16 18 3 15 2 18 18 18 1 5 1 16 7 18 11 7 7 7 5 5 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/wordpart.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include <asm/runtime-const.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ /* SLAB cache for struct filename instances */ static struct kmem_cache *__names_cache __ro_after_init; #define names_cache runtime_const_ptr(__names_cache) /* * Type of the last component on LOOKUP_PARENT */ enum last_type {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; void __init filename_init(void) { __names_cache = kmem_cache_create_usercopy("names_cache", sizeof(struct filename), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, offsetof(struct filename, iname), EMBEDDED_NAME_MAX, NULL); runtime_const_init(ptr, __names_cache); } static inline struct filename *alloc_filename(void) { return kmem_cache_alloc(names_cache, GFP_KERNEL); } static inline void free_filename(struct filename *p) { kmem_cache_free(names_cache, p); } static inline void initname(struct filename *name) { name->aname = NULL; name->refcnt = 1; } static int getname_long(struct filename *name, const char __user *filename) { int len; char *p __free(kfree) = kmalloc(PATH_MAX, GFP_KERNEL); if (unlikely(!p)) return -ENOMEM; memcpy(p, &name->iname, EMBEDDED_NAME_MAX); len = strncpy_from_user(p + EMBEDDED_NAME_MAX, filename + EMBEDDED_NAME_MAX, PATH_MAX - EMBEDDED_NAME_MAX); if (unlikely(len < 0)) return len; if (unlikely(len == PATH_MAX - EMBEDDED_NAME_MAX)) return -ENAMETOOLONG; name->name = no_free_ptr(p); return 0; } static struct filename * do_getname(const char __user *filename, int flags, bool incomplete) { struct filename *result; char *kname; int len; result = alloc_filename(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); /* * First, try to embed the struct filename inside the names_cache * allocation */ kname = (char *)result->iname; result->name = kname; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); /* * Handle both empty path and copy failure in one go. */ if (unlikely(len <= 0)) { /* The empty path is special. */ if (!len && !(flags & LOOKUP_EMPTY)) len = -ENOENT; } /* * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a * separate struct filename so we can dedicate the entire * names_cache allocation for the pathname, and re-do the copy from * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) len = getname_long(result, filename); if (unlikely(len < 0)) { free_filename(result); return ERR_PTR(len); } initname(result); if (likely(!incomplete)) audit_getname(result); return result; } struct filename * getname_flags(const char __user *filename, int flags) { return do_getname(filename, flags, false); } struct filename *getname_uflags(const char __user *filename, int uflags) { int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; return getname_flags(filename, flags); } struct filename *__getname_maybe_null(const char __user *pathname) { char c; /* try to save on allocations; loss on um, though */ if (get_user(c, pathname)) return ERR_PTR(-EFAULT); if (!c) return NULL; CLASS(filename_flags, name)(pathname, LOOKUP_EMPTY); /* empty pathname translates to NULL */ if (!IS_ERR(name) && !(name->name[0])) return NULL; return no_free_ptr(name); } static struct filename *do_getname_kernel(const char *filename, bool incomplete) { struct filename *result; int len = strlen(filename) + 1; char *p; if (unlikely(len > PATH_MAX)) return ERR_PTR(-ENAMETOOLONG); result = alloc_filename(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { p = (char *)result->iname; memcpy(p, filename, len); } else { p = kmemdup(filename, len, GFP_KERNEL); if (unlikely(!p)) { free_filename(result); return ERR_PTR(-ENOMEM); } } result->name = p; initname(result); if (likely(!incomplete)) audit_getname(result); return result; } struct filename *getname_kernel(const char *filename) { return do_getname_kernel(filename, false); } EXPORT_SYMBOL(getname_kernel); void putname(struct filename *name) { int refcnt; if (IS_ERR_OR_NULL(name)) return; refcnt = name->refcnt; if (unlikely(refcnt != 1)) { if (WARN_ON_ONCE(!refcnt)) return; name->refcnt--; return; } if (unlikely(name->name != name->iname)) kfree(name->name); free_filename(name); } EXPORT_SYMBOL(putname); static inline int __delayed_getname(struct delayed_filename *v, const char __user *string, int flags) { v->__incomplete_filename = do_getname(string, flags, true); return PTR_ERR_OR_ZERO(v->__incomplete_filename); } int delayed_getname(struct delayed_filename *v, const char __user *string) { return __delayed_getname(v, string, 0); } int delayed_getname_uflags(struct delayed_filename *v, const char __user *string, int uflags) { int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; return __delayed_getname(v, string, flags); } int putname_to_delayed(struct delayed_filename *v, struct filename *name) { if (likely(name->refcnt == 1)) { v->__incomplete_filename = name; return 0; } name->refcnt--; v->__incomplete_filename = do_getname_kernel(name->name, true); return PTR_ERR_OR_ZERO(v->__incomplete_filename); } void dismiss_delayed_filename(struct delayed_filename *v) { putname(no_free_ptr(v->__incomplete_filename)); } struct filename *complete_getname(struct delayed_filename *v) { struct filename *res = no_free_ptr(v->__incomplete_filename); if (!IS_ERR(res)) audit_getname(res); return res; } /** * check_acl - perform ACL permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the ACL permission checking. Since this function * retrieve POSIX acls it needs to know whether it is called from a blocking or * non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ static int check_acl(struct mnt_idmap *idmap, struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; if (mask & MAY_NOT_BLOCK) { acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); if (!acl) return -EAGAIN; /* no ->get_inode_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(idmap, inode, acl, mask); } acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { int error = posix_acl_permission(idmap, inode, acl, mask); posix_acl_release(acl); return error; } #endif return -EAGAIN; } /* * Very quick optimistic "we know we have no ACL's" check. * * Note that this is purely for ACL_TYPE_ACCESS, and purely * for the "we have cached that there are no ACLs" case. * * If this returns true, we know there are no ACLs. But if * it returns false, we might still not have ACLs (it could * be the is_uncached_acl() case). */ static inline bool no_acl_inode(struct inode *inode) { #ifdef CONFIG_FS_POSIX_ACL return likely(!READ_ONCE(inode->i_acl)); #else return true; #endif } /** * acl_permission_check - perform basic UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the basic UNIX permission checking. Since this * function may retrieve POSIX acls it needs to know whether it is called from a * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ static int acl_permission_check(struct mnt_idmap *idmap, struct inode *inode, int mask) { unsigned int mode = inode->i_mode; vfsuid_t vfsuid; /* * Common cheap case: everybody has the requested * rights, and there are no ACLs to check. No need * to do any owner/group checks in that case. * * - 'mask&7' is the requested permission bit set * - multiplying by 0111 spreads them out to all of ugo * - '& ~mode' looks for missing inode permission bits * - the '!' is for "no missing permissions" * * After that, we just need to check that there are no * ACL's on the inode - do the 'IS_POSIXACL()' check last * because it will dereference the ->i_sb pointer and we * want to avoid that if at all possible. */ if (!((mask & 7) * 0111 & ~mode)) { if (no_acl_inode(inode)) return 0; if (!IS_POSIXACL(inode)) return 0; } /* Are we the owner? If so, ACL's don't matter */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (likely(vfsuid_eq_kuid(vfsuid, current_fsuid()))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; } /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { int error = check_acl(idmap, inode, mask); if (error != -EAGAIN) return error; } /* Only RWX matters for group/other mode bits */ mask &= 7; /* * Are the group permissions different from * the other permissions in the bits we care * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) mode >>= 3; } /* Bits in 'mode' clear that we require? */ return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem * @idmap: idmap of the mount the inode was found from * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int generic_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int ret; /* * Do the basic permission checks. */ ret = acl_permission_check(idmap, inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } /* * Searching includes executable on directories, else just read. */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. * Executable DACs are overridable when there is * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); /** * do_inode_permission - UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) return inode->i_op->permission(idmap, inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } return generic_permission(idmap, inode, mask); } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. * * Note: lookup_inode_permission_may_exec() does not call here. If you add * MAY_EXEC checks, adjust it. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { if (mask & MAY_WRITE) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; } /** * inode_permission - Check for access rights to a given inode * @idmap: idmap of the mount the inode was found from * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (unlikely(retval)) return retval; if (mask & MAY_WRITE) { /* * Nobody gets write access to an immutable file. */ if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; /* * Updating mtime will likely cause i_uid and i_gid to be * written back improperly if their true value is unknown * to the vfs. */ if (unlikely(HAS_UNMAPPED_ID(idmap, inode))) return -EACCES; } retval = do_inode_permission(idmap, inode, mask); if (unlikely(retval)) return retval; retval = devcgroup_inode_permission(inode, mask); if (unlikely(retval)) return retval; return security_inode_permission(inode, mask); } EXPORT_SYMBOL(inode_permission); /* * lookup_inode_permission_may_exec - Check traversal right for given inode * * This is a special case routine for may_lookup() making assumptions specific * to path traversal. Use inode_permission() if you are doing something else. * * Work is shaved off compared to inode_permission() as follows: * - we know for a fact there is no MAY_WRITE to worry about * - it is an invariant the inode is a directory * * Since majority of real-world traversal happens on inodes which grant it for * everyone, we check it upfront and only resort to more expensive work if it * fails. * * Filesystems which have their own ->permission hook and consequently miss out * on IOP_FASTPERM can still get the optimization if they set IOP_FASTPERM_MAY_EXEC * on their directory inodes. */ static __always_inline int lookup_inode_permission_may_exec(struct mnt_idmap *idmap, struct inode *inode, int mask) { /* Lookup already checked this to return -ENOTDIR */ VFS_BUG_ON_INODE(!S_ISDIR(inode->i_mode), inode); VFS_BUG_ON((mask & ~MAY_NOT_BLOCK) != 0); mask |= MAY_EXEC; if (unlikely(!(inode->i_opflags & (IOP_FASTPERM | IOP_FASTPERM_MAY_EXEC)))) return inode_permission(idmap, inode, mask); if (unlikely(((inode->i_mode & 0111) != 0111) || !no_acl_inode(inode))) return inode_permission(idmap, inode, mask); return security_inode_permission(inode, mask); } /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { mntget(path->mnt); dget(path->dentry); } EXPORT_SYMBOL(path_get); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { dput(path->dentry); mntput(path->mnt); } EXPORT_SYMBOL(path_put); #define EMBEDDED_LEVELS 2 struct nameidata { struct path path; struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags, state; unsigned seq, next_seq, m_seq, r_seq; enum last_type last_type; unsigned depth; int total_link_count; struct saved { struct path link; struct delayed_call done; const char *name; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; const char *pathname; struct nameidata *saved; unsigned root_seq; int dfd; vfsuid_t dir_vfsuid; umode_t dir_mode; } __randomize_layout; #define ND_ROOT_PRESET 1 #define ND_ROOT_GRABBED 2 #define ND_JUMPED 4 static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; p->depth = 0; p->dfd = dfd; p->name = name; p->pathname = likely(name) ? name->name : ""; p->path.mnt = NULL; p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name, const struct path *root) { __set_nameidata(p, dfd, name); p->state = 0; if (unlikely(root)) { p->state = ND_ROOT_PRESET; p->root = *root; } } static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; current->nameidata = old; if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack); } static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; p= kmalloc_objs(struct saved, MAXSYMLINKS, nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!p)) return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; return true; } /** * path_connected - Verify that a dentry is below mnt.mnt_root * @mnt: The mountpoint to check. * @dentry: The dentry to check. * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; /* Bind mounts can have disconnected paths */ if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) { int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; do_delayed_call(&last->done); clear_delayed_call(&last->done); } } static void leave_rcu(struct nameidata *nd) { nd->flags &= ~LOOKUP_RCU; nd->seq = nd->next_seq = 0; rcu_read_unlock(); } static void terminate_walk(struct nameidata *nd) { if (unlikely(nd->depth)) drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); if (nd->state & ND_ROOT_GRABBED) { path_put(&nd->root); nd->state &= ~ND_ROOT_GRABBED; } } else { leave_rcu(nd); } nd->depth = 0; nd->path.mnt = NULL; nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; path->dentry = NULL; return false; } if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) { path->dentry = NULL; return false; } return !read_seqcount_retry(&path->dentry->d_seq, seq); } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { return __legitimize_path(path, seq, nd->m_seq); } static bool legitimize_links(struct nameidata *nd) { int i; VFS_BUG_ON(nd->flags & LOOKUP_CACHED); for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd); nd->depth = i + 1; return false; } } return true; } static bool legitimize_root(struct nameidata *nd) { /* Nothing to do if nd->root is zero or is managed by the VFS user. */ if (!nd->root.mnt || (nd->state & ND_ROOT_PRESET)) return true; nd->state |= ND_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; VFS_BUG_ON(!(nd->flags & LOOKUP_RCU)); if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; goto out1; } if (unlikely(nd->depth && !legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; leave_rcu(nd); BUG_ON(nd->inode != parent->d_inode); return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: leave_rcu(nd); return false; } /** * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: next dentry to step into * Returns: true on success, false on failure * * Similar to try_to_unlazy(), but here we have the next dentry already * picked by rcu-walk and want to legitimize that in addition to the current * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) { int res; VFS_BUG_ON(!(nd->flags & LOOKUP_RCU)); if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; goto out2; } if (unlikely(nd->depth && !legitimize_links(nd))) goto out2; res = __legitimize_mnt(nd->path.mnt, nd->m_seq); if (unlikely(res)) { if (res > 0) goto out2; goto out1; } if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* * We need to move both the parent and the dentry from the RCU domain * to be properly refcounted. And the sequence number in the dentry * validates *both* dentry counters, since we checked the sequence * number of the parent after we got the child sequence number. So we * know the parent must still be valid if the child sequence number is */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) goto out_dput; /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. */ if (unlikely(!legitimize_root(nd))) goto out_dput; leave_rcu(nd); return true; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: leave_rcu(nd); return false; out_dput: leave_rcu(nd); dput(dentry); return false; } static inline int d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) return dentry->d_op->d_revalidate(dir, name, dentry, flags); else return 1; } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { struct dentry *dentry = nd->path.dentry; int status; if (nd->flags & LOOKUP_RCU) { /* * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ if (likely(!(nd->state & ND_ROOT_PRESET))) if (likely(!(nd->flags & LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't * ever step outside the root during lookup" and should already * be guaranteed by the rest of namei, we want to avoid a namei * BUG resulting in userspace being given a path that was not * scoped within the root at some point during the lookup. * * So, do a final sanity-check to make sure that in the * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED) * we won't silently return an fd completely outside of the * requested root to userspace. * * Userspace could move the path outside the root after this * check, but as discussed elsewhere this is not a concern (the * resolved file was inside the root at some point). */ if (!path_is_under(&nd->path, &nd->root)) return -EXDEV; } if (likely(!(nd->state & ND_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) return 0; status = dentry->d_op->d_weak_revalidate(dentry, nd->flags); if (status > 0) return 0; if (!status) status = -ESTALE; return status; } static int set_root(struct nameidata *nd) { struct fs_struct *fs = current->fs; /* * Jumping to the real root in a scoped-lookup is a BUG in namei, but we * still have to ensure it doesn't happen because it will cause a breakout * from the dirfd. */ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED)) return -ENOTRECOVERABLE; if (nd->flags & LOOKUP_RCU) { unsigned seq; do { seq = read_seqbegin(&fs->seq); nd->root = fs->root; nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqretry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); nd->state |= ND_ROOT_GRABBED; } return 0; } static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) return -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { /* Absolute path arguments to path_init() are allowed. */ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt) return -EXDEV; } if (!nd->root.mnt) { int error = set_root(nd); if (unlikely(error)) return error; } if (nd->flags & LOOKUP_RCU) { struct dentry *d; nd->path = nd->root; d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; if (read_seqcount_retry(&d->d_seq, nd->seq)) return -ECHILD; } else { path_put(&nd->path); nd->path = nd->root; path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } nd->state |= ND_JUMPED; return 0; } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(const struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS)) goto err; error = -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { if (nd->path.mnt != path->mnt) goto err; } /* Not currently safe for scoped-lookups. */ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) goto err; path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; nd->state |= ND_JUMPED; return 0; err: path_put(path); return error; } static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } static int sysctl_protected_symlinks __read_mostly; static int sysctl_protected_hardlinks __read_mostly; static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; #ifdef CONFIG_SYSCTL static const struct ctl_table namei_sysctls[] = { { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "protected_hardlinks", .data = &sysctl_protected_hardlinks, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "protected_fifos", .data = &sysctl_protected_fifos, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "protected_regular", .data = &sysctl_protected_regular, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, }; static int __init init_fs_namei_sysctls(void) { register_sysctl_init("fs", namei_sysctls); return 0; } fs_initcall(init_fs_namei_sysctls); #endif /* CONFIG_SYSCTL */ /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * @inode: Used for idmapping. * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { struct mnt_idmap *idmap; vfsuid_t vfsuid; if (!sysctl_protected_symlinks) return 0; idmap = mnt_idmap(nd->path.mnt); vfsuid = i_uid_into_vfsuid(idmap, inode); /* Allowed if owner and follower match. */ if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return 0; /* Allowed if parent directory not sticky and world-writable. */ if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ if (vfsuid_valid(nd->dir_vfsuid) && vfsuid_eq(nd->dir_vfsuid, vfsuid)) return 0; if (nd->flags & LOOKUP_RCU) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } /** * safe_hardlink_source - Check for safe hardlink conditions * @idmap: idmap of the mount the inode was found from * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; /* Special files should not get pinned to the filesystem. */ if (!S_ISREG(mode)) return false; /* Setuid files should not get pinned to the filesystem. */ if (mode & S_ISUID) return false; /* Executable setgid files should not get pinned to the filesystem. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ if (inode_permission(idmap, inode, MAY_READ | MAY_WRITE)) return false; return true; } /** * may_linkat - Check permissions for creating a hardlink * @idmap: idmap of the mount the inode was found from * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if successful, -ve on error. */ int may_linkat(struct mnt_idmap *idmap, const struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; if (!sysctl_protected_hardlinks) return 0; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ if (safe_hardlink_source(idmap, inode) || inode_owner_or_capable(idmap, inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @idmap: idmap of the mount the inode was found from * @nd: nameidata pathwalk data * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd, struct inode *const inode) { umode_t dir_mode = nd->dir_mode; vfsuid_t dir_vfsuid = nd->dir_vfsuid, i_vfsuid; if (likely(!(dir_mode & S_ISVTX))) return 0; if (S_ISREG(inode->i_mode) && !sysctl_protected_regular) return 0; if (S_ISFIFO(inode->i_mode) && !sysctl_protected_fifos) return 0; i_vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq(i_vfsuid, dir_vfsuid)) return 0; if (vfsuid_eq_kuid(i_vfsuid, current_fsuid())) return 0; if (likely(dir_mode & 0002)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create"); return -EACCES; } if (dir_mode & 0020) { if (sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create_fifo"); return -EACCES; } if (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create_regular"); return -EACCES; } } return 0; } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); struct mount *parent; struct dentry *mountpoint; read_seqlock_excl(&mount_lock); parent = mnt->mnt_parent; if (parent == mnt) { read_sequnlock_excl(&mount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); read_sequnlock_excl(&mount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); path->mnt = &parent->mnt; return 1; } EXPORT_SYMBOL(follow_up); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { while (mnt_has_parent(m)) { struct dentry *mountpoint = m->mnt_mountpoint; m = m->mnt_parent; if (unlikely(root->dentry == mountpoint && root->mnt == &m->mnt)) break; if (mountpoint != m->mnt.mnt_root) { path->mnt = &m->mnt; path->dentry = mountpoint; *seqp = read_seqcount_begin(&mountpoint->d_seq); return true; } } return false; } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { bool found; rcu_read_lock(); while (1) { unsigned seq, mseq = read_seqbegin(&mount_lock); found = choose_mountpoint_rcu(m, root, path, &seq); if (unlikely(!found)) { if (!read_seqretry(&mount_lock, mseq)) break; } else { if (likely(__legitimize_path(path, seq, mseq))) break; rcu_read_unlock(); path_put(path); rcu_read_lock(); } } rcu_read_unlock(); return found; } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. * * We do, however, want to mount if someone wants to open or * create a file of any type under the mountpoint, wants to * traverse through the mountpoint or wants to open the * mounted directory. Also, autofs may mark negative dentries * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && dentry->d_inode) return -EISDIR; /* No need to trigger automounts if mountpoint crossing is disabled. */ if (lookup_flags & LOOKUP_NO_XDEV) return -EXDEV; if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; return finish_automount(dentry->d_op->d_automount(path), path); } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_rwsem * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { if (lookup_flags & LOOKUP_NO_XDEV) { ret = -EXDEV; break; } ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); // here we know it's positive flags = path->dentry->d_flags; need_mntput = true; if (unlikely(lookup_flags & LOOKUP_NO_XDEV)) { ret = -EXDEV; break; } continue; } } if (!(flags & DCACHE_NEED_AUTOMOUNT)) break; // uncovered automount point ret = follow_automount(path, count, lookup_flags); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (ret == -EISDIR) ret = 0; // possible if you race with several mount --move if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; *jumped = need_mntput; return ret; } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { unsigned flags = smp_load_acquire(&path->dentry->d_flags); /* fastpath */ if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { *jumped = false; if (unlikely(d_flags_negative(flags))) return -ENOENT; return 0; } return __traverse_mounts(path, flags, jumped, count, lookup_flags); } int follow_down_one(struct path *path) { struct vfsmount *mounted; mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); return 1; } return 0; } EXPORT_SYMBOL(follow_down_one); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path, unsigned int flags) { struct vfsmount *mnt = path->mnt; bool jumped; int ret = traverse_mounts(path, &jumped, NULL, flags); if (path->mnt != mnt) mntput(mnt); return ret; } EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path) { struct dentry *dentry = path->dentry; unsigned int flags = dentry->d_flags; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return false; for (;;) { /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { int res = dentry->d_op->d_manage(path, true); if (res) return res == -EISDIR; flags = dentry->d_flags; } if (flags & DCACHE_MOUNTED) { struct mount *mounted = __lookup_mnt(path->mnt, dentry); if (mounted) { path->mnt = &mounted->mnt; dentry = path->dentry = mounted->mnt.mnt_root; nd->state |= ND_JUMPED; nd->next_seq = read_seqcount_begin(&dentry->d_seq); flags = dentry->d_flags; // makes sure that non-RCU pathwalk could reach // this state. if (read_seqretry(&mount_lock, nd->m_seq)) return false; continue; } if (read_seqretry(&mount_lock, nd->m_seq)) return false; } return !(flags & DCACHE_NEED_AUTOMOUNT); } } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path) { bool jumped; int ret; path->mnt = nd->path.mnt; path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = nd->next_seq; if (likely(!d_managed(dentry))) return 0; if (likely(__follow_mount_rcu(nd, path))) return 0; // *path and nd->next_seq might've been clobbered path->mnt = nd->path.mnt; path->dentry = dentry; nd->next_seq = seq; if (unlikely(!try_to_unlazy_next(nd, dentry))) return -ECHILD; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) nd->state |= ND_JUMPED; if (unlikely(ret)) { dput(path->dentry); if (path->mnt != nd->path.mnt) mntput(path->mnt); } return ret; } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry = d_lookup(dir, name); if (dentry) { int error = d_revalidate(dir->d_inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); dput(dentry); return ERR_PTR(error); } } return dentry; } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed. * Will return -EEXIST if name is found and LOOKUP_EXCL was passed. */ static struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry; struct dentry *old; struct inode *dir; dentry = lookup_dcache(name, base, flags); if (dentry) goto found; /* Don't create child dentry for a dead directory. */ dir = base->d_inode; if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; } found: if (IS_ERR(dentry)) return dentry; if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) { dput(dentry); return ERR_PTR(-ENOENT); } if (d_is_positive(dentry) && (flags & LOOKUP_EXCL)) { dput(dentry); return ERR_PTR(-EEXIST); } return dentry; } /** * lookup_fast - do fast lockless (but racy) lookup of a dentry * @nd: current nameidata * * Do a fast, but racy lookup in the dcache for the given dentry, and * revalidate it. Returns a valid dentry pointer or NULL if one wasn't * found. On error, an ERR_PTR will be returned. * * If this function returns a valid dentry and the walk is no longer * lazy, the dentry will carry a reference that must later be put. If * RCU mode is still in force, then this is not the case and the dentry * must be legitimized before use. If this returns NULL, then the walk * will no longer be in RCU mode. */ static struct dentry *lookup_fast(struct nameidata *nd) { struct dentry *dentry, *parent = nd->path.dentry; int status = 1; /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, the caller is * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq); if (unlikely(!dentry)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. */ if (read_seqcount_retry(&parent->d_seq, nd->seq)) return ERR_PTR(-ECHILD); status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry)) return ERR_PTR(-ECHILD); if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); return ERR_PTR(status); } return dentry; } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) return ERR_PTR(-ENOENT); again: dentry = d_alloc_parallel(dir, name); if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { int error = d_revalidate(inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); dput(dentry); goto again; } dput(dentry); dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); d_lookup_done(dentry); if (unlikely(old)) { dput(dentry); dentry = old; } } return dentry; } static noinline struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; inode_lock_shared(inode); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static struct dentry *lookup_slow_killable(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; if (inode_lock_shared_killable(inode)) return ERR_PTR(-EINTR); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static inline int may_lookup(struct mnt_idmap *idmap, struct nameidata *restrict nd) { int err, mask; mask = nd->flags & LOOKUP_RCU ? MAY_NOT_BLOCK : 0; err = lookup_inode_permission_may_exec(idmap, nd->inode, mask); if (likely(!err)) return 0; // If we failed, and we weren't in LOOKUP_RCU, it's final if (!(nd->flags & LOOKUP_RCU)) return err; // Drop out of RCU mode to make sure it wasn't transient if (!try_to_unlazy(nd)) return -ECHILD; // redo it all non-lazy if (err != -ECHILD) // hard error return err; return lookup_inode_permission_may_exec(idmap, nd->inode, 0); } static int reserve_stack(struct nameidata *nd, struct path *link) { if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) return -ELOOP; if (likely(nd->depth != EMBEDDED_LEVELS)) return 0; if (likely(nd->stack != nd->internal)) return 0; if (likely(nd_alloc_stack(nd))) return 0; if (nd->flags & LOOKUP_RCU) { // we need to grab link before we do unlazy. And we can't skip // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, nd->next_seq); if (!try_to_unlazy(nd) || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) return 0; } return -ENOMEM; } enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; static noinline const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, int flags) { struct saved *last; const char *res; int error; if (nd->flags & LOOKUP_RCU) { /* make sure that d_is_symlink from step_into_slowpath() matches the inode */ if (read_seqcount_retry(&link->dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); } else { if (link->mnt == nd->path.mnt) mntget(link->mnt); } error = reserve_stack(nd, link); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); return ERR_PTR(error); } last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); last->seq = nd->next_seq; if (flags & WALK_TRAILING) { error = may_follow_link(nd, inode); if (unlikely(error)) return ERR_PTR(error); } if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (unlikely(atime_needs_update(&last->link, inode))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } touch_atime(&last->link); cond_resched(); } error = security_inode_follow_link(link->dentry, inode, nd->flags & LOOKUP_RCU); if (unlikely(error)) return ERR_PTR(error); res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); } else { res = get(link->dentry, inode, &last->done); } if (!res) goto all_done; if (IS_ERR(res)) return res; } if (*res == '/') { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); while (unlikely(*++res == '/')) ; } if (*res) return res; all_done: // pure jump put_link(nd); return NULL; } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. * * NOTE: dentry must be what nd->next_seq had been sampled from. */ static noinline const char *step_into_slowpath(struct nameidata *nd, int flags, struct dentry *dentry) { struct path path; struct inode *inode; int err; err = handle_mounts(nd, dentry, &path); if (unlikely(err < 0)) return ERR_PTR(err); inode = path.dentry->d_inode; if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ if (nd->flags & LOOKUP_RCU) { if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); if (unlikely(!inode)) return ERR_PTR(-ENOENT); } else { dput(nd->path.dentry); if (nd->path.mnt != path.mnt) mntput(nd->path.mnt); } nd->path = path; nd->inode = inode; nd->seq = nd->next_seq; return NULL; } return pick_link(nd, &path, inode, flags); } static __always_inline const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry) { /* * In the common case we are in rcu-walk and traversing over a non-mounted on * directory (as opposed to e.g., a symlink). * * We can handle that and negative entries with the checks below. */ if (likely((nd->flags & LOOKUP_RCU) && !d_managed(dentry) && !d_is_symlink(dentry))) { struct inode *inode = dentry->d_inode; if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); if (unlikely(!inode)) return ERR_PTR(-ENOENT); nd->path.dentry = dentry; /* nd->path.mnt remains unchanged as no mount point was crossed */ nd->inode = inode; nd->seq = nd->next_seq; return NULL; } return step_into_slowpath(nd, flags, dentry); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd) { struct dentry *parent, *old; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; unsigned seq; if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), &nd->root, &path, &seq)) goto in_root; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-ECHILD); nd->path = path; nd->inode = path.dentry->d_inode; nd->seq = seq; // makes sure that non-RCU pathwalk could reach this state if (read_seqretry(&mount_lock, nd->m_seq)) return ERR_PTR(-ECHILD); /* we know that mountpoint was pinned */ } old = nd->path.dentry; parent = old->d_parent; nd->next_seq = read_seqcount_begin(&parent->d_seq); // makes sure that non-RCU pathwalk could reach this state if (read_seqcount_retry(&old->d_seq, nd->seq)) return ERR_PTR(-ECHILD); if (unlikely(!path_connected(nd->path.mnt, parent))) return ERR_PTR(-ECHILD); return parent; in_root: if (read_seqretry(&mount_lock, nd->m_seq)) return ERR_PTR(-ECHILD); if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-ECHILD); nd->next_seq = nd->seq; return nd->path.dentry; } static struct dentry *follow_dotdot(struct nameidata *nd) { struct dentry *parent; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; if (!choose_mountpoint(real_mount(nd->path.mnt), &nd->root, &path)) goto in_root; path_put(&nd->path); nd->path = path; nd->inode = path.dentry->d_inode; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-EXDEV); } /* rare case of legitimate dget_parent()... */ parent = dget_parent(nd->path.dentry); if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent); return ERR_PTR(-ENOENT); } return parent; in_root: if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-EXDEV); return dget(nd->path.dentry); } static const char *handle_dots(struct nameidata *nd, enum last_type type) { if (type == LAST_DOTDOT) { const char *error = NULL; struct dentry *parent; if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); if (unlikely(error)) return error; } if (nd->flags & LOOKUP_RCU) parent = follow_dotdot_rcu(nd); else parent = follow_dotdot(nd); if (IS_ERR(parent)) return ERR_CAST(parent); error = step_into(nd, WALK_NOFOLLOW, parent); if (unlikely(error)) return error; if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * If there was a racing rename or mount along our * path, then we can't be sure that ".." hasn't jumped * above nd->root (and so userspace should retry or use * some fallback). */ smp_rmb(); if (__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq)) return ERR_PTR(-EAGAIN); if (__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq)) return ERR_PTR(-EAGAIN); } } return NULL; } static __always_inline const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { if (unlikely(nd->depth) && !(flags & WALK_MORE)) put_link(nd); return handle_dots(nd, nd->last_type); } dentry = lookup_fast(nd); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (unlikely(!dentry)) { dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); if (IS_ERR(dentry)) return ERR_CAST(dentry); } if (unlikely(nd->depth) && !(flags & WALK_MORE)) put_link(nd); return step_into(nd, flags, dentry); } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol64(x,12),\ x += y, y = rol64(y,45),\ y *= 9 ) /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { y ^= x * GOLDEN_RATIO_64; y *= GOLDEN_RATIO_64; return y >> 32; } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol32(x, 7),\ x += y, y = rol32(y,20),\ y *= 9 ) static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long a, x = 0, y = (unsigned long)salt; for (;;) { if (!len) goto done; a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; HASH_MIX(x, y, a); name += sizeof(unsigned long); len -= sizeof(unsigned long); } x ^= a & bytemask_from_count(len); done: return fold_hash(x, y); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long a = 0, x = 0, y = (unsigned long)salt; unsigned long adata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); } while (!has_zero(a, &adata, &constants)); adata = prep_zero_mask(a, adata, &constants); mask = create_zero_mask(adata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } EXPORT_SYMBOL(hashlen_string); /* * hash_name - Calculate the length and hash of the path component * @nd: the path resolution state * @name: the pathname to read the component from * @lastword: if the component fits in a single word, LAST_WORD_IS_DOT, * LAST_WORD_IS_DOTDOT, or some other value depending on whether the * component is '.', '..', or something else. Otherwise, @lastword is 0. * * Returns: a pointer to the terminating '/' or NUL character in @name. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { unsigned long a, b, x, y = (unsigned long)nd->path.dentry; unsigned long adata, bdata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; /* * The first iteration is special, because it can result in * '.' and '..' and has no mixing other than the final fold. */ a = load_unaligned_zeropad(name); b = a ^ REPEAT_BYTE('/'); if (has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)) { adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); a &= zero_bytemask(mask); *lastword = a; len = find_zero(mask); nd->last.hash = fold_hash(a, y); nd->last.len = len; return name + len; } len = 0; x = 0; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); a &= zero_bytemask(mask); x ^= a; len += find_zero(mask); *lastword = 0; // Multi-word components cannot be DOT or DOTDOT nd->last.hash = fold_hash(x, y); nd->last.len = len; return name + len; } /* * Note that the 'last' word is always zero-masked, but * was loaded as a possibly big-endian word. */ #ifdef __BIG_ENDIAN #define LAST_WORD_IS_DOT (0x2eul << (BITS_PER_LONG-8)) #define LAST_WORD_IS_DOTDOT (0x2e2eul << (BITS_PER_LONG-16)) #endif #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { unsigned long hash = init_name_hash(nd->path.dentry); unsigned long len = 0, c, last = 0; c = (unsigned char)*name; do { last = (last << 8) + c; len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); // This is reliable for DOT or DOTDOT, since the component // cannot contain NUL characters - top bits being zero means // we cannot have had any other pathnames. *lastword = last; nd->last.hash = end_name_hash(hash); nd->last.len = len; return name + len; } #endif #ifndef LAST_WORD_IS_DOT #define LAST_WORD_IS_DOT 0x2e #define LAST_WORD_IS_DOTDOT 0x2e2e #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { int depth = 0; // depth <= nd->depth int err; nd->last_type = LAST_ROOT; nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); if (*name == '/') { do { name++; } while (unlikely(*name == '/')); } if (unlikely(!*name)) { nd->dir_mode = 0; // short-circuit the 'hardening' idiocy return 0; } /* At this point we know we have a real path component. */ for(;;) { struct mnt_idmap *idmap; const char *link; unsigned long lastword; idmap = mnt_idmap(nd->path.mnt); err = may_lookup(idmap, nd); if (unlikely(err)) return err; nd->last.name = name; name = hash_name(nd, name, &lastword); switch(lastword) { case LAST_WORD_IS_DOTDOT: nd->last_type = LAST_DOTDOT; nd->state |= ND_JUMPED; break; case LAST_WORD_IS_DOT: nd->last_type = LAST_DOT; break; default: nd->last_type = LAST_NORM; nd->state &= ~ND_JUMPED; struct dentry *parent = nd->path.dentry; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { err = parent->d_op->d_hash(parent, &nd->last); if (err < 0) return err; } } if (!*name) goto OK; /* * If it wasn't NUL, we know it was '/'. Skip that * slash, and continue until no more slashes. */ do { name++; } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ if (likely(!depth)) { nd->dir_vfsuid = i_uid_into_vfsuid(idmap, nd->inode); nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; } /* last component of nested symlink */ name = nd->stack[--depth].name; link = walk_component(nd, 0); } else { /* not the last component */ link = walk_component(nd, WALK_MORE); } if (unlikely(link)) { if (IS_ERR(link)) return PTR_ERR(link); /* a symlink to follow */ nd->stack[depth++].name = name; name = link; continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; } } } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { int error; const char *s = nd->pathname; /* LOOKUP_CACHED requires RCU, ask caller to retry */ if (unlikely((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)) return ERR_PTR(-EAGAIN); if (unlikely(!*s)) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); else nd->seq = nd->next_seq = 0; nd->flags = flags; nd->state |= ND_JUMPED; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); if (unlikely(nd->state & ND_ROOT_PRESET)) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) return ERR_PTR(-ENOTDIR); nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); nd->root_seq = nd->seq; } else { path_get(&nd->path); } return s; } nd->root.mnt = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && likely(!(flags & LOOKUP_IN_ROOT))) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); return s; } /* Relative pathname -- get the starting-point it is relative to. */ if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; unsigned seq; do { seq = read_seqbegin(&fs->seq); nd->path = fs->pwd; nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqretry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); nd->inode = nd->path.dentry->d_inode; } } else { /* Caller must check execute permissions on the starting path component */ CLASS(fd_raw, f)(nd->dfd); struct dentry *dentry; if (fd_empty(f)) return ERR_PTR(-EBADF); if (flags & LOOKUP_LINKAT_EMPTY) { if (fd_file(f)->f_cred != current_cred() && !ns_capable(fd_file(f)->f_cred->user_ns, CAP_DAC_READ_SEARCH)) return ERR_PTR(-ENOENT); } dentry = fd_file(f)->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) return ERR_PTR(-ENOTDIR); nd->path = fd_file(f)->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } } /* For scoped-lookups we need to set the root to the dirfd as well. */ if (unlikely(flags & LOOKUP_IS_SCOPED)) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; } else { path_get(&nd->root); nd->state |= ND_ROOT_GRABBED; } } return s; } static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { if (!(nd->flags & LOOKUP_RCU)) dget(nd->path.dentry); nd->next_seq = nd->seq; return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry)); } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); int err; if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) { err = handle_lookup_down(nd); if (unlikely(err < 0)) s = ERR_PTR(err); } while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { err = handle_lookup_down(nd); nd->state &= ~ND_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); set_nameidata(&nd, dfd, name, root); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); if (unlikely(retval == -ESTALE)) retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) audit_inode(name, path->dentry, flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); return retval; } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { const char *s = path_init(nd, flags); int err = link_path_walk(s, nd); if (!err) err = complete_walk(nd); if (!err) { *parent = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } /* Note: this does not consume "name" */ static int __filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, enum last_type *type, const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); set_nameidata(&nd, dfd, name, root); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); if (unlikely(retval == -ESTALE)) retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent); if (likely(!retval)) { *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } restore_nameidata(); return retval; } static int filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, enum last_type *type) { return __filename_parentat(dfd, name, flags, parent, last, type, NULL); } static struct dentry *__start_dirop(struct dentry *parent, struct qstr *name, unsigned int lookup_flags, unsigned int state) { struct dentry *dentry; struct inode *dir = d_inode(parent); if (state == TASK_KILLABLE) { int ret = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); if (ret) return ERR_PTR(ret); } else { inode_lock_nested(dir, I_MUTEX_PARENT); } dentry = lookup_one_qstr_excl(name, parent, lookup_flags); if (IS_ERR(dentry)) inode_unlock(dir); return dentry; } /** * start_dirop - begin a create or remove dirop, performing locking and lookup * @parent: the dentry of the parent in which the operation will occur * @name: a qstr holding the name within that parent * @lookup_flags: intent and other lookup flags. * * The lookup is performed and necessary locks are taken so that, on success, * the returned dentry can be operated on safely. * The qstr must already have the hash value calculated. * * Returns: a locked dentry, or an error. * */ struct dentry *start_dirop(struct dentry *parent, struct qstr *name, unsigned int lookup_flags) { return __start_dirop(parent, name, lookup_flags, TASK_NORMAL); } /** * end_dirop - signal completion of a dirop * @de: the dentry which was returned by start_dirop or similar. * * If the de is an error, nothing happens. Otherwise any lock taken to * protect the dentry is dropped and the dentry itself is release (dput()). */ void end_dirop(struct dentry *de) { if (!IS_ERR(de)) { inode_unlock(de->d_parent->d_inode); dput(de); } } EXPORT_SYMBOL(end_dirop); /* does lookup, returns the object with parent locked */ struct dentry *start_removing_path(const char *name, struct path *path) { CLASS(filename_kernel, filename)(name); struct path parent_path __free(path_put) = {}; struct dentry *d; struct qstr last; enum last_type type; int error; error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type); if (error) return ERR_PTR(error); if (unlikely(type != LAST_NORM)) return ERR_PTR(-EINVAL); /* don't fail immediately if it's r/o, at least try to report other errors */ error = mnt_want_write(parent_path.mnt); d = start_dirop(parent_path.dentry, &last, 0); if (IS_ERR(d)) goto drop; if (error) goto fail; path->dentry = no_free_ptr(parent_path.dentry); path->mnt = no_free_ptr(parent_path.mnt); return d; fail: end_dirop(d); d = ERR_PTR(error); drop: if (!error) mnt_drop_write(parent_path.mnt); return d; } /** * kern_path_parent: lookup path returning parent and target * @name: path name * @path: path to store parent in * * The path @name should end with a normal component, not "." or ".." or "/". * A lookup is performed and if successful the parent information * is store in @parent and the dentry is returned. * * The dentry maybe negative, the parent will be positive. * * Returns: dentry or error. */ struct dentry *kern_path_parent(const char *name, struct path *path) { struct path parent_path __free(path_put) = {}; CLASS(filename_kernel, filename)(name); struct dentry *d; struct qstr last; enum last_type type; int error; error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type); if (error) return ERR_PTR(error); if (unlikely(type != LAST_NORM)) return ERR_PTR(-EINVAL); d = lookup_noperm_unlocked(&last, parent_path.dentry); if (IS_ERR(d)) return d; path->dentry = no_free_ptr(parent_path.dentry); path->mnt = no_free_ptr(parent_path.mnt); return d; } int kern_path(const char *name, unsigned int flags, struct path *path) { CLASS(filename_kernel, filename)(name); return filename_lookup(AT_FDCWD, filename, flags, path, NULL); } EXPORT_SYMBOL(kern_path); /** * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair * @filename: filename structure * @flags: lookup flags * @parent: pointer to struct path to fill * @last: last component * @root: pointer to struct path of the base directory */ int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, const struct path *root) { enum last_type type; int err = __filename_parentat(AT_FDCWD, filename, flags, parent, last, &type, root); if (err) return err; if (unlikely(type != LAST_NORM)) { path_put(parent); return -EINVAL; } return 0; } EXPORT_SYMBOL(vfs_path_parent_lookup); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { CLASS(filename_kernel, filename)(name); struct path root = {.mnt = mnt, .dentry = dentry}; /* the first argument of filename_lookup() is ignored with root */ return filename_lookup(AT_FDCWD, filename, flags, path, &root); } EXPORT_SYMBOL(vfs_path_lookup); int lookup_noperm_common(struct qstr *qname, struct dentry *base) { const char *name = qname->name; u32 len = qname->len; qname->hash = full_name_hash(base, name, len); if (!len) return -EACCES; if (name_is_dot_dotdot(name, len)) return -EACCES; while (len--) { unsigned int c = *(const unsigned char *)name++; if (c == '/' || c == '\0') return -EACCES; } /* * See if the low-level filesystem might want * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { int err = base->d_op->d_hash(base, qname); if (err < 0) return err; } return 0; } static int lookup_one_common(struct mnt_idmap *idmap, struct qstr *qname, struct dentry *base) { int err; err = lookup_noperm_common(qname, base); if (err < 0) return err; return inode_permission(idmap, base->d_inode, MAY_EXEC); } /** * try_lookup_noperm - filesystem helper to lookup single pathname component * @name: qstr storing pathname component to lookup * @base: base directory to lookup from * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist or an error if there is a problem with the name. * The function does not try to create a dentry and if one * is found it doesn't try to revalidate it. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. It does no permission checking. * * No locks need be held - only a counted reference to @base is needed. * * Returns: * - ref-counted dentry on success, or * - %NULL if name could not be found, or * - ERR_PTR(-EACCES) if name is dot or dotdot or contains a slash or nul, or * - ERR_PTR() if fs provide ->d_hash, and this returned an error. */ struct dentry *try_lookup_noperm(struct qstr *name, struct dentry *base) { int err; err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); return d_lookup(base, name); } EXPORT_SYMBOL(try_lookup_noperm); /** * lookup_noperm - filesystem helper to lookup single pathname component * @name: qstr storing pathname component to lookup * @base: base directory to lookup from * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. It does no permission checking. * * The caller must hold base->i_rwsem. */ struct dentry *lookup_noperm(struct qstr *name, struct dentry *base) { struct dentry *dentry; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); dentry = lookup_dcache(name, base, 0); return dentry ? dentry : __lookup_slow(name, base, 0); } EXPORT_SYMBOL(lookup_noperm); /** * lookup_one - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr holding pathname component to lookup * @base: base directory to lookup from * * This can be used for in-kernel filesystem clients such as file servers. * * The caller must hold base->i_rwsem. */ struct dentry *lookup_one(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { struct dentry *dentry; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); dentry = lookup_dcache(name, base, 0); return dentry ? dentry : __lookup_slow(name, base, 0); } EXPORT_SYMBOL(lookup_one); /** * lookup_one_unlocked - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr olding pathname component to lookup * @base: base directory to lookup from * * This can be used for in-kernel filesystem clients such as file servers. * * Unlike lookup_one, it should be called without the parent * i_rwsem held, and will take the i_rwsem itself if necessary. * * Returns: - A dentry, possibly negative, or * - same errors as try_lookup_noperm() or * - ERR_PTR(-ENOENT) if parent has been removed, or * - ERR_PTR(-EACCES) if parent directory is not searchable. */ struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { int err; struct dentry *ret; err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); ret = lookup_dcache(name, base, 0); if (!ret) ret = lookup_slow(name, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_unlocked); /** * lookup_one_positive_killable - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr olding pathname component to lookup * @base: base directory to lookup from * * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns * known positive or ERR_PTR(). This is what most of the users want. * * Note that pinned negative with unlocked parent _can_ become positive at any * time, so callers of lookup_one_unlocked() need to be very careful; pinned * positives have >d_inode stable, so this one avoids such problems. * * This can be used for in-kernel filesystem clients such as file servers. * * It should be called without the parent i_rwsem held, and will take * the i_rwsem itself if necessary. If a fatal signal is pending or * delivered, it will return %-EINTR if the lock is needed. * * Returns: A dentry, possibly negative, or * - same errors as lookup_one_unlocked() or * - ERR_PTR(-EINTR) if a fatal signal is pending. */ struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { int err; struct dentry *ret; err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); ret = lookup_dcache(name, base, 0); if (!ret) ret = lookup_slow_killable(name, base, 0); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_one_positive_killable); /** * lookup_one_positive_unlocked - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr holding pathname component to lookup * @base: base directory to lookup from * * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns * known positive or ERR_PTR(). This is what most of the users want. * * Note that pinned negative with unlocked parent _can_ become positive at any * time, so callers of lookup_one_unlocked() need to be very careful; pinned * positives have >d_inode stable, so this one avoids such problems. * * This can be used for in-kernel filesystem clients such as file servers. * * The helper should be called without i_rwsem held. * * Returns: A positive dentry, or * - ERR_PTR(-ENOENT) if the name could not be found, or * - same errors as lookup_one_unlocked(). */ struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { struct dentry *ret = lookup_one_unlocked(idmap, name, base); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_one_positive_unlocked); /** * lookup_noperm_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. It does no permission checking. * * Unlike lookup_noperm(), it should be called without the parent * i_rwsem held, and will take the i_rwsem itself if necessary. * * Unlike try_lookup_noperm() it *does* revalidate the dentry if it already * existed. * * Returns: A dentry, possibly negative, or * - ERR_PTR(-ENOENT) if parent has been removed, or * - same errors as try_lookup_noperm() */ struct dentry *lookup_noperm_unlocked(struct qstr *name, struct dentry *base) { struct dentry *ret; int err; err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); ret = lookup_dcache(name, base, 0); if (!ret) ret = lookup_slow(name, base, 0); return ret; } EXPORT_SYMBOL(lookup_noperm_unlocked); /* * Like lookup_noperm_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_noperm_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. * * Returns: A positive dentry, or * - ERR_PTR(-ENOENT) if name cannot be found or parent has been removed, or * - same errors as try_lookup_noperm() */ struct dentry *lookup_noperm_positive_unlocked(struct qstr *name, struct dentry *base) { struct dentry *ret; ret = lookup_noperm_unlocked(name, base); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_noperm_positive_unlocked); /** * start_creating - prepare to create a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to prepare to create the name * @name: the name to be created * * Locks are taken and a lookup is performed prior to creating * an object in a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name already exists, a positive dentry is returned, so * behaviour is similar to O_CREAT without O_EXCL, which doesn't fail * with -EEXIST. * * Returns: a negative or positive dentry, or an error. */ struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, LOOKUP_CREATE); } EXPORT_SYMBOL(start_creating); /** * start_removing - prepare to remove a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to find the name * @name: the name to be removed * * Locks are taken and a lookup in performed prior to removing * an object from a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name doesn't exist, an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * Returns: a positive dentry, or an error. */ struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, 0); } EXPORT_SYMBOL(start_removing); /** * start_creating_killable - prepare to create a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to prepare to create the name * @name: the name to be created * * Locks are taken and a lookup in performed prior to creating * an object in a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name already exists, a positive dentry is returned. * * If a signal is received or was already pending, the function aborts * with -EINTR; * * Returns: a negative or positive dentry, or an error. */ struct dentry *start_creating_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return __start_dirop(parent, name, LOOKUP_CREATE, TASK_KILLABLE); } EXPORT_SYMBOL(start_creating_killable); /** * start_removing_killable - prepare to remove a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to find the name * @name: the name to be removed * * Locks are taken and a lookup in performed prior to removing * an object from a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name doesn't exist, an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * If a signal is received or was already pending, the function aborts * with -EINTR; * * Returns: a positive dentry, or an error. */ struct dentry *start_removing_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return __start_dirop(parent, name, 0, TASK_KILLABLE); } EXPORT_SYMBOL(start_removing_killable); /** * start_creating_noperm - prepare to create a given name without permission checking * @parent: directory in which to prepare to create the name * @name: the name to be created * * Locks are taken and a lookup in performed prior to creating * an object in a directory. * * If the name already exists, a positive dentry is returned. * * Returns: a negative or positive dentry, or an error. */ struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name) { int err = lookup_noperm_common(name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, LOOKUP_CREATE); } EXPORT_SYMBOL(start_creating_noperm); /** * start_removing_noperm - prepare to remove a given name without permission checking * @parent: directory in which to find the name * @name: the name to be removed * * Locks are taken and a lookup in performed prior to removing * an object from a directory. * * If the name doesn't exist, an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * Returns: a positive dentry, or an error. */ struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name) { int err = lookup_noperm_common(name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, 0); } EXPORT_SYMBOL(start_removing_noperm); /** * start_creating_dentry - prepare to create a given dentry * @parent: directory from which dentry should be removed * @child: the dentry to be removed * * A lock is taken to protect the dentry again other dirops and * the validity of the dentry is checked: correct parent and still hashed. * * If the dentry is valid and negative a reference is taken and * returned. If not an error is returned. * * end_creating() should be called when creation is complete, or aborted. * * Returns: the valid dentry, or an error. */ struct dentry *start_creating_dentry(struct dentry *parent, struct dentry *child) { inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); if (unlikely(IS_DEADDIR(parent->d_inode) || child->d_parent != parent || d_unhashed(child))) { inode_unlock(parent->d_inode); return ERR_PTR(-EINVAL); } if (d_is_positive(child)) { inode_unlock(parent->d_inode); return ERR_PTR(-EEXIST); } return dget(child); } EXPORT_SYMBOL(start_creating_dentry); /** * start_removing_dentry - prepare to remove a given dentry * @parent: directory from which dentry should be removed * @child: the dentry to be removed * * A lock is taken to protect the dentry again other dirops and * the validity of the dentry is checked: correct parent and still hashed. * * If the dentry is valid and positive, a reference is taken and * returned. If not an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * Returns: the valid dentry, or an error. */ struct dentry *start_removing_dentry(struct dentry *parent, struct dentry *child) { inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); if (unlikely(IS_DEADDIR(parent->d_inode) || child->d_parent != parent || d_unhashed(child))) { inode_unlock(parent->d_inode); return ERR_PTR(-EINVAL); } if (d_is_negative(child)) { inode_unlock(parent->d_inode); return ERR_PTR(-ENOENT); } return dget(child); } EXPORT_SYMBOL(start_removing_dentry); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { /* Find something mounted on "pts" in the same directory as * the input path. */ struct dentry *parent = dget_parent(path->dentry); struct dentry *child; if (unlikely(!path_connected(path->mnt, parent))) { dput(parent); return -ENOENT; } dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &QSTR("pts")); if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; dput(parent); follow_down(path, 0); return 0; } #endif int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { CLASS(filename_flags, filename)(name, flags); return filename_lookup(dfd, filename, flags, path, NULL); } EXPORT_SYMBOL(user_path_at); int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), fsuid)) return 0; if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, dir), fsuid)) return 0; return !capable_wrt_inode_uidgid(idmap, inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ int may_delete_dentry(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; if (d_is_negative(victim)) return -ENOENT; BUG_ON(!inode); BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; if (check_sticky(idmap, dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; if (victim->d_flags & DCACHE_NFSFS_RENAMED) return -EBUSY; return 0; } EXPORT_SYMBOL(may_delete_dentry); /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ int may_create_dentry(struct mnt_idmap *idmap, struct inode *dir, struct dentry *child) { audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; if (!fsuidgid_has_mapping(dir->i_sb, idmap)) return -EOVERFLOW; return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); } EXPORT_SYMBOL(may_create_dentry); // p1 != p2, both are on the same filesystem, ->s_vfs_rename_mutex is held static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) { struct dentry *p = p1, *q = p2, *r; while ((r = p->d_parent) != p2 && r != p) p = r; if (r == p2) { // p is a child of p2 and an ancestor of p1 or p1 itself inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } // p is the root of connected component that contains p1 // p2 does not occur on the path from p to p1 while ((r = q->d_parent) != p1 && r != p && r != q) q = r; if (r == p1) { // q is a child of p1 and an ancestor of p2 or p2 itself inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return q; } else if (likely(r == p)) { // both p2 and p1 are descendents of p inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return NULL; } else { // no common ancestor at the time we'd been called mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); return ERR_PTR(-EXDEV); } } /* * p1 and p2 should be directories on the same fs. */ static struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); return lock_two_directories(p1, p2); } /* * c1 and p2 should be on the same fs. */ static struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2) { if (READ_ONCE(c1->d_parent) == p2) { /* * hopefully won't need to touch ->s_vfs_rename_mutex at all. */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); /* * now that p2 is locked, nobody can move in or out of it, * so the test below is safe. */ if (likely(c1->d_parent == p2)) return NULL; /* * c1 got moved out of p2 while we'd been taking locks; * unlock and fall back to slow case. */ inode_unlock(p2->d_inode); } mutex_lock(&c1->d_sb->s_vfs_rename_mutex); /* * nobody can move out of any directories on this fs. */ if (likely(c1->d_parent != p2)) return lock_two_directories(c1->d_parent, p2); /* * c1 got moved into p2 while we were taking locks; * we need p2 locked and ->s_vfs_rename_mutex unlocked, * for consistency with lock_rename(). */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); mutex_unlock(&c1->d_sb->s_vfs_rename_mutex); return NULL; } static void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } /** * __start_renaming - lookup and lock names for rename * @rd: rename data containing parents and flags, and * for receiving found dentries * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, * LOOKUP_NO_SYMLINKS etc). * @old_last: name of object in @rd.old_parent * @new_last: name of object in @rd.new_parent * * Look up two names and ensure locks are in place for * rename. * * On success the found dentries are stored in @rd.old_dentry, * @rd.new_dentry and an extra ref is taken on @rd.old_parent. * These references and the lock are dropped by end_renaming(). * * The passed in qstrs must have the hash calculated, and no permission * checking is performed. * * Returns: zero or an error. */ static int __start_renaming(struct renamedata *rd, int lookup_flags, struct qstr *old_last, struct qstr *new_last) { struct dentry *trap; struct dentry *d1, *d2; int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; int err; if (rd->flags & RENAME_EXCHANGE) target_flags = 0; if (rd->flags & RENAME_NOREPLACE) target_flags |= LOOKUP_EXCL; trap = lock_rename(rd->old_parent, rd->new_parent); if (IS_ERR(trap)) return PTR_ERR(trap); d1 = lookup_one_qstr_excl(old_last, rd->old_parent, lookup_flags); err = PTR_ERR(d1); if (IS_ERR(d1)) goto out_unlock; d2 = lookup_one_qstr_excl(new_last, rd->new_parent, lookup_flags | target_flags); err = PTR_ERR(d2); if (IS_ERR(d2)) goto out_dput_d1; if (d1 == trap) { /* source is an ancestor of target */ err = -EINVAL; goto out_dput_d2; } if (d2 == trap) { /* target is an ancestor of source */ if (rd->flags & RENAME_EXCHANGE) err = -EINVAL; else err = -ENOTEMPTY; goto out_dput_d2; } rd->old_dentry = d1; rd->new_dentry = d2; dget(rd->old_parent); return 0; out_dput_d2: dput(d2); out_dput_d1: dput(d1); out_unlock: unlock_rename(rd->old_parent, rd->new_parent); return err; } /** * start_renaming - lookup and lock names for rename with permission checking * @rd: rename data containing parents and flags, and * for receiving found dentries * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, * LOOKUP_NO_SYMLINKS etc). * @old_last: name of object in @rd.old_parent * @new_last: name of object in @rd.new_parent * * Look up two names and ensure locks are in place for * rename. * * On success the found dentries are stored in @rd.old_dentry, * @rd.new_dentry. Also the refcount on @rd->old_parent is increased. * These references and the lock are dropped by end_renaming(). * * The passed in qstrs need not have the hash calculated, and basic * eXecute permission checking is performed against @rd.mnt_idmap. * * Returns: zero or an error. */ int start_renaming(struct renamedata *rd, int lookup_flags, struct qstr *old_last, struct qstr *new_last) { int err; err = lookup_one_common(rd->mnt_idmap, old_last, rd->old_parent); if (err) return err; err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent); if (err) return err; return __start_renaming(rd, lookup_flags, old_last, new_last); } EXPORT_SYMBOL(start_renaming); static int __start_renaming_dentry(struct renamedata *rd, int lookup_flags, struct dentry *old_dentry, struct qstr *new_last) { struct dentry *trap; struct dentry *d2; int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; int err; if (rd->flags & RENAME_EXCHANGE) target_flags = 0; if (rd->flags & RENAME_NOREPLACE) target_flags |= LOOKUP_EXCL; /* Already have the dentry - need to be sure to lock the correct parent */ trap = lock_rename_child(old_dentry, rd->new_parent); if (IS_ERR(trap)) return PTR_ERR(trap); if (d_unhashed(old_dentry) || (rd->old_parent && rd->old_parent != old_dentry->d_parent)) { /* dentry was removed, or moved and explicit parent requested */ err = -EINVAL; goto out_unlock; } d2 = lookup_one_qstr_excl(new_last, rd->new_parent, lookup_flags | target_flags); err = PTR_ERR(d2); if (IS_ERR(d2)) goto out_unlock; if (old_dentry == trap) { /* source is an ancestor of target */ err = -EINVAL; goto out_dput_d2; } if (d2 == trap) { /* target is an ancestor of source */ if (rd->flags & RENAME_EXCHANGE) err = -EINVAL; else err = -ENOTEMPTY; goto out_dput_d2; } rd->old_dentry = dget(old_dentry); rd->new_dentry = d2; rd->old_parent = dget(old_dentry->d_parent); return 0; out_dput_d2: dput(d2); out_unlock: unlock_rename(old_dentry->d_parent, rd->new_parent); return err; } /** * start_renaming_dentry - lookup and lock name for rename with permission checking * @rd: rename data containing parents and flags, and * for receiving found dentries * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, * LOOKUP_NO_SYMLINKS etc). * @old_dentry: dentry of name to move * @new_last: name of target in @rd.new_parent * * Look up target name and ensure locks are in place for * rename. * * On success the found dentry is stored in @rd.new_dentry and * @rd.old_parent is confirmed to be the parent of @old_dentry. If it * was originally %NULL, it is set. In either case a reference is taken * so that end_renaming() can have a stable reference to unlock. * * References and the lock can be dropped with end_renaming() * * The passed in qstr need not have the hash calculated, and basic * eXecute permission checking is performed against @rd.mnt_idmap. * * Returns: zero or an error. */ int start_renaming_dentry(struct renamedata *rd, int lookup_flags, struct dentry *old_dentry, struct qstr *new_last) { int err; err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent); if (err) return err; return __start_renaming_dentry(rd, lookup_flags, old_dentry, new_last); } EXPORT_SYMBOL(start_renaming_dentry); /** * start_renaming_two_dentries - Lock to dentries in given parents for rename * @rd: rename data containing parent * @old_dentry: dentry of name to move * @new_dentry: dentry to move to * * Ensure locks are in place for rename and check parentage is still correct. * * On success the two dentries are stored in @rd.old_dentry and * @rd.new_dentry and @rd.old_parent and @rd.new_parent are confirmed to * be the parents of the dentries. * * References and the lock can be dropped with end_renaming() * * Returns: zero or an error. */ int start_renaming_two_dentries(struct renamedata *rd, struct dentry *old_dentry, struct dentry *new_dentry) { struct dentry *trap; int err; /* Already have the dentry - need to be sure to lock the correct parent */ trap = lock_rename_child(old_dentry, rd->new_parent); if (IS_ERR(trap)) return PTR_ERR(trap); err = -EINVAL; if (d_unhashed(old_dentry) || (rd->old_parent && rd->old_parent != old_dentry->d_parent)) /* old_dentry was removed, or moved and explicit parent requested */ goto out_unlock; if (d_unhashed(new_dentry) || rd->new_parent != new_dentry->d_parent) /* new_dentry was removed or moved */ goto out_unlock; if (old_dentry == trap) /* source is an ancestor of target */ goto out_unlock; if (new_dentry == trap) { /* target is an ancestor of source */ if (rd->flags & RENAME_EXCHANGE) err = -EINVAL; else err = -ENOTEMPTY; goto out_unlock; } err = -EEXIST; if (d_is_positive(new_dentry) && (rd->flags & RENAME_NOREPLACE)) goto out_unlock; rd->old_dentry = dget(old_dentry); rd->new_dentry = dget(new_dentry); rd->old_parent = dget(old_dentry->d_parent); return 0; out_unlock: unlock_rename(old_dentry->d_parent, rd->new_parent); return err; } EXPORT_SYMBOL(start_renaming_two_dentries); void end_renaming(struct renamedata *rd) { unlock_rename(rd->old_parent, rd->new_parent); dput(rd->old_dentry); dput(rd->new_dentry); dput(rd->old_parent); } EXPORT_SYMBOL(end_renaming); /** * vfs_prepare_mode - prepare the mode to be used for a new inode * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs * @type: type of file to be created * * This helper consolidates and enforces vfs restrictions on the @mode of a new * object to be created. * * Umask stripping depends on whether the filesystem supports POSIX ACLs (see * the kernel documentation for mode_strip_umask()). Moving umask stripping * after setgid stripping allows the same ordering for both non-POSIX ACL and * POSIX ACL supporting filesystems. * * Returns: mode to be passed to the filesystem */ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { mode = mode_strip_sgid(idmap, dir, mode); mode = mode_strip_umask(dir, mode); /* * Apply the vfs mandated allowed permission mask and set the type of * file to be created before we call into the filesystem. */ mode &= (mask_perms & ~S_IFMT); mode |= (type & S_IFMT); return mode; } /** * vfs_create - create new file * @idmap: idmap of the mount the inode was found from * @dentry: dentry of the child file * @mode: mode of the child file * @di: returns parent inode, if the inode is delegated. * * Create a new file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode, struct delegated_inode *di) { struct inode *dir = d_inode(dentry->d_parent); int error; error = may_create_dentry(idmap, dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di); if (error) return error; error = dir->i_op->create(idmap, dir, dentry, mode); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_create); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { struct inode *dir = dentry->d_parent->d_inode; int error = may_create_dentry(&nop_mnt_idmap, dir, dentry); if (error) return error; mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = f(dentry, mode, arg); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkobj); bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } static int may_open(struct mnt_idmap *idmap, const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; if (!inode) return -ENOENT; switch (inode->i_mode & S_IFMT) { case S_IFLNK: return -ELOOP; case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; if (acc_mode & MAY_EXEC) return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; fallthrough; case S_IFIFO: case S_IFSOCK: if (acc_mode & MAY_EXEC) return -EACCES; flag &= ~O_TRUNC; break; case S_IFREG: if ((acc_mode & MAY_EXEC) && path_noexec(path)) return -EACCES; break; default: VFS_BUG_ON_INODE(!IS_ANON_FILE(inode), inode); } error = inode_permission(idmap, inode, MAY_OPEN | acc_mode); if (error) return error; /* * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME && !inode_owner_or_capable(idmap, inode)) return -EPERM; return 0; } static int handle_truncate(struct mnt_idmap *idmap, struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; error = security_file_truncate(filp); if (!error) { error = do_truncate(idmap, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } put_write_access(inode); return error; } static inline int open_to_namei_flags(int flag) { if ((flag & O_ACCMODE) == 3) flag--; return flag; } static int may_o_create(struct mnt_idmap *idmap, const struct path *dir, struct dentry *dentry, umode_t mode) { int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; if (!fsuidgid_has_mapping(dir->dentry->d_sb, idmap)) return -EOVERFLOW; error = inode_permission(idmap, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; return security_inode_create(dir->dentry->d_inode, dentry, mode); } /** * atomic_open() - atomically look up, create and open a file * @path: parent directory path * @dentry: child to ->atomic_open() * @file: file to attach child to * @open_flag: open flags * @mode: create mode * @create_error: return value from may_o_create() * * Attempt to look up, create and open @dentry, which must be negative, in a * single call into the filesystem. * * If a non-error dentry is returned then: when FMODE_OPENED is set, * the file will have been attached to @file by the filesystem calling * finish_open(). If FMODE_OPENED isn't set, the filesystem instead called * finish_no_open() and the caller will need to perform the open themselves. * * FMODE_CREATED is set when the call to ->atomic_open() actually created * the file. * * Returns: the opened or looked-up dentry, or ERR_PTR() on failure. The * reference to @dentry is consumed in either case. */ static struct dentry *atomic_open(const struct path *path, struct dentry *dentry, struct file *file, int open_flag, umode_t mode, int create_error) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir_inode = path->dentry->d_inode; int error; file->__f_path.dentry = DENTRY_NOT_SET; file->__f_path.mnt = path->mnt; error = dir_inode->i_op->atomic_open(dir_inode, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { /* finish_open() called */ struct dentry *opened = file->f_path.dentry; if (unlikely(opened != dentry)) { dput(dentry); dentry = dget(opened); } } else if (likely(file->f_path.dentry != DENTRY_NOT_SET)) { /* finish_no_open() called */ struct dentry *replaced = file->f_path.dentry; if (replaced) { dput(dentry); dentry = replaced; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; } else { const char *fsname = dentry->d_sb->s_type->name; WARN(1, "%s: ->atomic_open() left file->f_path.dentry unset!\n", fsname); error = -EIO; } } if (error) { if (unlikely(create_error) && error == -ENOENT) { /* * Should have done a create, but errored before. * Some filesystems return -ENOENT directly instead of * calling finish_no_open() with a negative dentry; * either way it should only mean the child doesn't exist, * so a refused create is safe to record here. */ audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); error = create_error; } dput(dentry); dentry = ERR_PTR(error); } return dentry; } /* * Look up and maybe create and open the last component. * * Takes the parent inode lock itself, exclusive if O_CREAT was requested and * shared otherwise, and drops it again before returning. The caller must not * hold it. * * On success returns the dentry of the last component. If FMODE_OPENED is set * on file->f_mode the file was also opened and attached to @file; otherwise * only lookup and creation were performed and the caller has to open it. In * the latter case the dentry may be negative if O_CREAT hadn't been specified. * * Returns ERR_PTR() on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct delegated_inode delegated_inode = { }; struct mnt_idmap *idmap; struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag; struct dentry *dentry; int error, create_error; umode_t mode; bool got_write; retry: open_flag = op->open_flag; got_write = false; mode = op->mode; create_error = 0; if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; we'll be dropping this one anyway. */ } if (open_flag & O_CREAT) inode_lock(dir_inode); else inode_lock_shared(dir_inode); if (unlikely(IS_DEADDIR(dir_inode))) { dentry = ERR_PTR(-ENOENT); goto out; } file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last); if (IS_ERR(dentry)) goto out; } if (d_in_lookup(dentry)) break; error = d_revalidate(dir_inode, &nd->last, dentry, nd->flags); if (likely(error > 0)) break; if (error) goto out_dput; d_invalidate(dentry); dput(dentry); dentry = NULL; } if (dentry->d_inode) { /* Cached positive dentry: will open in do_open(). */ goto out; } if (open_flag & O_CREAT) audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the * file exists. But checking existence breaks atomicity. The trick is * to check access and if not granted clear O_CREAT from the flags. * * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; mode = vfs_prepare_mode(idmap, dir_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(idmap, &nd->path, dentry, mode); else create_error = -EROFS; } if (create_error) open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; dentry = atomic_open(&nd->path, dentry, file, open_flag, mode, create_error); goto out; } if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) { error = PTR_ERR(res); goto out_dput; } dput(dentry); dentry = res; } } if (dentry->d_inode || !(op->open_flag & O_CREAT)) { /* * No need to create a file. If lookup returned a positive * dentry, the file will be opened in do_open(). */ goto out; } /* Negative dentry with O_CREAT flag set */ audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (unlikely(create_error)) { /* should have done a create, but we already errored */ error = create_error; goto out_dput; } error = try_break_deleg(dir_inode, LEASE_BREAK_DIR_CREATE, &delegated_inode); if (error) goto out_dput; file->f_mode |= FMODE_CREATED; if (!dir_inode->i_op->create) { error = -EACCES; goto out_dput; } error = dir_inode->i_op->create(idmap, dir_inode, dentry, mode); if (error) goto out_dput; out: if (!IS_ERR(dentry)) { if (file->f_mode & FMODE_CREATED) fsnotify_create(dir_inode, dentry); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); } if ((open_flag & O_CREAT) || create_error) inode_unlock(dir_inode); else inode_unlock_shared(dir_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (is_delegated(&delegated_inode)) { /* Must have come through out_dput: dentry is an ERR_PTR() */ error = break_deleg_wait(&delegated_inode); if (!error) goto retry; dentry = ERR_PTR(error); } return dentry; out_dput: dput(dentry); dentry = ERR_PTR(error); goto out; } /** * vfs_lookup_open - open and possibly create a regular file * @parent: directory to contain file * @last: final component of file name * @open_flag: O_flags * @mode: initial permissions for file * * Open a file after lookup and/or create. This provides similar * functionality to open_last_lookups() for non-VFS users, particularly * nfsd. * It uses ->atomic_open or ->lookup / ->create / ->open as appropriate. * * If the fs object found is not a regular file then an error is returned. * In some cases, related errors are repurposed so that the caller can * determine the type of file found from the error. * -EISDIR : a directory was found * -ELOOP : a symlink was found * -ENODEV : a block or character device special file was found * -EFTYPE : any other non-regular file was found, such as FIFO or SOCK. * or ->atomic_open responded to __O_REGULAR. * * Returns: the opened struct file, or an error. */ struct file *vfs_lookup_open(struct path *parent, struct qstr *last, int open_flag, umode_t mode) { struct file *file __free(fput) = NULL; struct nameidata nd = {}; struct open_flags op = {}; struct dentry *dentry; int error = 0; WARN_ONCE(mode & ~S_IALLUGO, "mode must only have permission bits"); WARN_ONCE(open_flag & ~(O_ACCMODE|O_CREAT|O_EXCL|O_TRUNC|__O_REGULAR), "open_flag has unsupported flags"); mode |= S_IFREG; open_flag |= __O_REGULAR; error = lookup_noperm_common(last, parent->dentry); if (error) return ERR_PTR(error); file = alloc_empty_file(open_flag, current_cred()); if (IS_ERR(file)) return file; nd.path = *parent; nd.last = *last; nd.flags = LOOKUP_OPEN; if (open_flag & O_CREAT) { nd.flags |= LOOKUP_CREATE; if (open_flag & O_EXCL) nd.flags |= LOOKUP_EXCL; } op.open_flag = open_flag; op.mode = mode; dentry = lookup_open(&nd, file, &op); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (d_really_is_negative(dentry)) { error = -ENOENT; } else if (!(file->f_mode & FMODE_CREATED) && (open_flag & O_EXCL)) { error = -EEXIST; } else if ((dentry->d_inode->i_mode & S_IFMT) != S_IFREG) { switch (dentry->d_inode->i_mode & S_IFMT) { case S_IFDIR: error = -EISDIR; break; case S_IFLNK: error = -ELOOP; break; case S_IFBLK: case S_IFCHR: error = -ENODEV; break; case S_IFIFO: case S_IFSOCK: default: error = -EFTYPE; break; } } else if (!(file->f_mode & FMODE_OPENED)) { nd.path.dentry = dentry; error = vfs_open(&nd.path, file); } dput(dentry); if (error) return ERR_PTR(error); return no_free_ptr(file); } EXPORT_SYMBOL_FOR_MODULES(vfs_lookup_open, "nfsd"); static inline bool trailing_slashes(struct nameidata *nd) { return (bool)nd->last.name[nd->last.len]; } static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag) { struct dentry *dentry; if (open_flag & O_CREAT) { if (trailing_slashes(nd)) return ERR_PTR(-EISDIR); /* Don't bother on an O_EXCL create */ if (open_flag & O_EXCL) return NULL; } if (trailing_slashes(nd)) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; dentry = lookup_fast(nd); if (IS_ERR_OR_NULL(dentry)) return dentry; if (open_flag & O_CREAT) { /* Discard negative dentries. Need inode_lock to do the create */ if (!dentry->d_inode) { if (!(nd->flags & LOOKUP_RCU)) dput(dentry); dentry = NULL; } } return dentry; } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { int open_flag = op->open_flag; struct dentry *dentry; const char *res; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { if (nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } /* We _can_ be in RCU mode here */ dentry = lookup_fast_for_open(nd, open_flag); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (likely(dentry)) goto finish_lookup; if (!(open_flag & O_CREAT)) { if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU)) return ERR_PTR(-ECHILD); } else { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } } dentry = lookup_open(nd, file, op); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); nd->path.dentry = dentry; return NULL; } finish_lookup: if (nd->depth) put_link(nd); res = step_into(nd, WALK_TRAILING, dentry); if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); return res; } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct mnt_idmap *idmap; int open_flag = op->open_flag; bool do_truncate; int acc_mode; int error; if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { error = complete_walk(nd); if (error) return error; } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; error = may_create_in_sticky(idmap, nd, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; } if ((open_flag & __O_REGULAR) && !d_is_reg(nd->path.dentry)) return -EFTYPE; if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; do_truncate = false; acc_mode = op->acc_mode; if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; acc_mode = 0; } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) return error; do_truncate = true; } error = may_open(idmap, &nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = security_file_post_open(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(idmap, file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } /** * vfs_tmpfile - create tmpfile * @idmap: idmap of the mount the inode was found from * @parentpath: pointer to the path of the base directory * @file: file descriptor of the new tmpfile * @mode: mode of the new tmpfile * * Create a temporary file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode) { struct dentry *child; struct inode *dir = d_inode(parentpath->dentry); struct inode *inode; int error; int open_flag = file->f_flags; /* A tmpfile is I_LINKABLE, so guard its owner like may_o_create(). */ if (!fsuidgid_has_mapping(dir->i_sb, idmap)) return -EOVERFLOW; /* we want directory to be writable */ error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (!dir->i_op->tmpfile) return -EOPNOTSUPP; child = d_alloc(parentpath->dentry, &slash_name); if (unlikely(!child)) return -ENOMEM; file->__f_path.mnt = parentpath->mnt; file->__f_path.dentry = child; mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); error = dir->i_op->tmpfile(idmap, dir, file, mode); dput(child); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); if (error) return error; /* Don't check for other permissions, the inode was just created */ error = may_open(idmap, &file->f_path, 0, file->f_flags); if (error) return error; inode = file_inode(file); if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode_state_set(inode, I_LINKABLE); spin_unlock(&inode->i_lock); } security_inode_post_create_tmpfile(idmap, inode); return 0; } /** * kernel_tmpfile_open - open a tmpfile for kernel internal use * @idmap: idmap of the mount the inode was found from * @parentpath: path of the base directory * @mode: mode of the new tmpfile * @open_flag: flags * @cred: credentials for open * * Create and open a temporary file. The file is not accounted in nr_files, * hence this is only for kernel internal use, and must not be installed into * file tables or such. */ struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred) { struct file *file; int error; file = alloc_empty_file_noaccount(open_flag, cred); if (IS_ERR(file)) return file; error = vfs_tmpfile(idmap, parentpath, file, mode); if (error) { fput(file); file = ERR_PTR(error); } return file; } EXPORT_SYMBOL(kernel_tmpfile_open); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; error = vfs_tmpfile(mnt_idmap(path.mnt), &path, file, op->mode); if (error) goto out2; audit_inode(nd->name, file->f_path.dentry, 0); out2: mnt_drop_write(path.mnt); out: path_put(&path); return error; } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { struct path path; int error = path_lookupat(nd, flags, &path); if (!error) { audit_inode(nd->name, path.dentry, 0); error = vfs_open(&path, file); path_put(&path); } return error; } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { struct file *file; int error; file = alloc_empty_file(op->open_flag, current_cred()); if (IS_ERR(file)) return file; if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(nd, flags, op, file); } else if (unlikely(file->f_flags & O_PATH)) { error = do_o_path(nd, flags, file); } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL) ; if (!error) error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED)) return file; WARN_ON(1); error = -EINVAL; } fput_close(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; else error = -ESTALE; } return ERR_PTR(error); } struct file *do_file_open(int dfd, struct filename *pathname, const struct open_flags *op) { struct nameidata nd; int flags = op->lookup_flags; struct file *filp; if (IS_ERR(pathname)) return ERR_CAST(pathname); set_nameidata(&nd, dfd, pathname, NULL); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return filp; } struct file *do_file_open_root(const struct path *root, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; int flags = op->lookup_flags; if (d_is_symlink(root->dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); CLASS(filename_kernel, filename)(name); if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename, root); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); if (unlikely(file == ERR_PTR(-ESTALE))) file = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return file; } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; bool want_dir = lookup_flags & LOOKUP_DIRECTORY; unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; enum last_type type; int error; error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) */ if (unlikely(type != LAST_NORM)) goto out; /* don't fail immediately if it's r/o, at least try to report other errors */ error = mnt_want_write(path->mnt); /* * Do the final lookup. Suppress 'create' if there is a trailing * '/', and a directory wasn't requested. */ if (last.name[last.len] && !want_dir) create_flags &= ~LOOKUP_CREATE; dentry = start_dirop(path->dentry, &last, reval_flag | create_flags); if (IS_ERR(dentry)) goto out_drop_write; if (unlikely(error)) goto fail; return dentry; fail: end_dirop(dentry); dentry = ERR_PTR(error); out_drop_write: if (!error) mnt_drop_write(path->mnt); out: path_put(path); return dentry; } struct dentry *start_creating_path(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { CLASS(filename_kernel, filename)(pathname); return filename_create(dfd, filename, path, lookup_flags); } EXPORT_SYMBOL(start_creating_path); /** * end_creating_path - finish a code section started by start_creating_path() * @path: the path instantiated by start_creating_path() * @dentry: the dentry returned by start_creating_path() * * end_creating_path() will unlock and locks taken by start_creating_path() * and drop an references that were taken. It should only be called * if start_creating_path() returned a non-error. * If vfs_mkdir() was called and it returned an error, that error *should* * be passed to end_creating_path() together with the path. */ void end_creating_path(const struct path *path, struct dentry *dentry) { end_creating(dentry); mnt_drop_write(path->mnt); path_put(path); } EXPORT_SYMBOL(end_creating_path); inline struct dentry *start_creating_user_path( int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { CLASS(filename, filename)(pathname); return filename_create(dfd, filename, path, lookup_flags); } EXPORT_SYMBOL(start_creating_user_path); /** * dentry_create - Create and open a file * @path: path to create * @flags: O\_ flags * @mode: mode bits for new file * @cred: credentials to use * * Caller must hold the parent directory's lock, and have prepared * a negative dentry, placed in @path->dentry, for the new file. * * Caller sets @path->mnt to the vfsmount of the filesystem where * the new file is to be created. The parent directory and the * negative dentry must reside on the same filesystem instance. * * On success, returns a ``struct file *``. Otherwise an ERR_PTR * is returned. */ struct file *dentry_create(struct path *path, int flags, umode_t mode, const struct cred *cred) { struct file *file __free(fput) = NULL; struct dentry *dentry = path->dentry; struct dentry *orig_dentry = dentry; struct dentry *dir = dentry->d_parent; struct inode *dir_inode = d_inode(dir); struct mnt_idmap *idmap; int error, create_error; file = alloc_empty_file(flags, cred); if (IS_ERR(file)) return file; idmap = mnt_idmap(path->mnt); if (dir_inode->i_op->atomic_open) { path->dentry = dir; mode = vfs_prepare_mode(idmap, dir_inode, mode, S_IALLUGO, S_IFREG); create_error = may_o_create(idmap, path, dentry, mode); if (create_error) flags &= ~O_CREAT; /* atomic_open will dput(dentry) on error */ dget(orig_dentry); dentry = atomic_open(path, dentry, file, flags, mode, create_error); error = PTR_ERR_OR_ZERO(dentry); if (IS_ERR(dentry)) /* keep the original */ dentry = orig_dentry; else /* Drop the extra reference */ dput(orig_dentry); if (!error) { if (file->f_mode & FMODE_CREATED) fsnotify_create(dir->d_inode, dentry); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); } path->dentry = dentry; } else { error = vfs_create(mnt_idmap(path->mnt), path->dentry, mode, NULL); if (!error) error = vfs_open(path, file); } if (unlikely(error)) return ERR_PTR(error); return no_free_ptr(file); } EXPORT_SYMBOL(dentry_create); /** * vfs_mknod - create device node or file * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child device node * @mode: mode of the child device node * @dev: device number of device to create * @delegated_inode: returns parent inode, if the inode is delegated. * * Create a device node or file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev, struct delegated_inode *delegated_inode) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create_dentry(idmap, dir, dentry); if (error) return error; if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; error = security_inode_mknod(dir, dentry, mode, dev); if (error) return error; error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode); if (error) return error; error = dir->i_op->mknod(idmap, dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: case 0: /* zero mode translates to S_IFREG */ return 0; case S_IFDIR: return -EPERM; default: return -EINVAL; } } int filename_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev) { struct delegated_inode di = { }; struct mnt_idmap *idmap; struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = 0; error = may_mknod(mode); if (error) return error; retry: dentry = filename_create(dfd, name, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mknod(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out2; idmap = mnt_idmap(path.mnt); switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(idmap, dentry, mode, &di); if (!error) security_path_post_mknod(idmap, dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, new_decode_dev(dev), &di); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, 0, &di); break; } out2: end_creating_path(&path, dentry); if (is_delegated(&di)) { error = break_deleg_wait(&di); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { CLASS(filename, name)(filename); return filename_mknodat(dfd, name, mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { CLASS(filename, name)(filename); return filename_mknodat(AT_FDCWD, name, mode, dev); } /** * vfs_mkdir - create directory returning correct dentry if possible * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * @mode: mode of the child directory * @delegated_inode: returns parent inode, if the inode is delegated. * * Create a directory. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * In the event that the filesystem does not use the *@dentry but leaves it * negative or unhashes it and possibly splices a different one returning it, * the original dentry is dput() and the alternate is returned. * * In case of an error the dentry is dput() and an ERR_PTR() is returned. */ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, struct delegated_inode *delegated_inode) { int error; unsigned max_links = dir->i_sb->s_max_links; struct dentry *de; error = may_create_dentry(idmap, dir, dentry); if (error) goto err; error = -EPERM; if (!dir->i_op->mkdir) goto err; mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, S_IFDIR); error = security_inode_mkdir(dir, dentry, mode); if (error) goto err; error = -EMLINK; if (max_links && dir->i_nlink >= max_links) goto err; error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode); if (error) goto err; de = dir->i_op->mkdir(idmap, dir, dentry, mode); error = PTR_ERR(de); if (IS_ERR(de)) goto err; if (de) { dput(dentry); dentry = de; } fsnotify_mkdir(dir, dentry); return dentry; err: end_creating(dentry); return ERR_PTR(error); } EXPORT_SYMBOL(vfs_mkdir); int filename_mkdirat(int dfd, struct filename *name, umode_t mode) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; struct delegated_inode delegated_inode = { }; retry: dentry = filename_create(dfd, name, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, mode, &delegated_inode); if (IS_ERR(dentry)) error = PTR_ERR(dentry); } end_creating_path(&path, dentry); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { CLASS(filename, name)(pathname); return filename_mkdirat(dfd, name, mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { CLASS(filename, name)(pathname); return filename_mkdirat(AT_FDCWD, name, mode); } /** * vfs_rmdir - remove directory * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * @delegated_inode: returns parent inode, if it's delegated. * * Remove a directory. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct delegated_inode *delegated_inode) { int error = may_delete_dentry(idmap, dir, dentry, true); if (error) return error; if (!dir->i_op->rmdir) return -EPERM; dget(dentry); inode_lock(dentry->d_inode); error = -EBUSY; if (is_local_mountpoint(dentry) || (dentry->d_inode->i_flags & S_KERNEL_FILE)) goto out; error = security_inode_rmdir(dir, dentry); if (error) goto out; error = try_break_deleg(dir, LEASE_BREAK_DIR_DELETE, delegated_inode); if (error) goto out; error = dir->i_op->rmdir(dir, dentry); if (error) goto out; shrink_dcache_parent(dentry); dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); int filename_rmdir(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; enum last_type type; unsigned int lookup_flags = 0; struct delegated_inode delegated_inode = { }; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) return error; switch (type) { case LAST_NORM: break; case LAST_DOTDOT: error = -ENOTEMPTY; goto exit2; case LAST_DOT: error = -EINVAL; goto exit2; case LAST_ROOT: error = -EBUSY; goto exit2; } error = mnt_want_write(path.mnt); if (error) goto exit2; dentry = start_dirop(path.dentry, &last, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit3; error = security_path_rmdir(&path, dentry); if (error) goto exit4; error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, &delegated_inode); exit4: end_dirop(dentry); exit3: mnt_drop_write(path.mnt); exit2: path_put(&path); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { CLASS(filename, name)(pathname); return filename_rmdir(AT_FDCWD, name); } /** * vfs_unlink - unlink a filesystem object * @idmap: idmap of the mount the inode was found from * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_rwsem exclusively. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_rwsem before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct delegated_inode *delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete_dentry(idmap, dir, dentry, false); if (error) return error; if (!dir->i_op->unlink) return -EPERM; inode_lock(target); if (IS_SWAPFILE(target)) error = -EPERM; else if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); if (!error) { error = try_break_deleg(dir, LEASE_BREAK_DIR_DELETE, delegated_inode); if (error) goto out; error = try_break_deleg(target, 0, delegated_inode); if (error) goto out; error = dir->i_op->unlink(dir, dentry); if (!error) { dont_mount(dentry); detach_mounts(dentry); } } } out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { fsnotify_unlink(dir, dentry); } else if (!error) { fsnotify_link_count(target); d_delete_notify(dir, dentry); } return error; } EXPORT_SYMBOL(vfs_unlink); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_rwsem. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ int filename_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; enum last_type type; struct inode *inode; struct delegated_inode delegated_inode = { }; unsigned int lookup_flags = 0; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) return error; error = -EISDIR; if (type != LAST_NORM) goto exit_path_put; error = mnt_want_write(path.mnt); if (error) goto exit_path_put; retry_deleg: dentry = start_dirop(path.dentry, &last, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit_drop_write; /* Why not before? Because we want correct error value */ if (unlikely(last.name[last.len])) { if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; end_dirop(dentry); goto exit_drop_write; } inode = dentry->d_inode; ihold(inode); error = security_path_unlink(&path, dentry); if (error) goto exit_end_dirop; error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, &delegated_inode); exit_end_dirop: end_dirop(dentry); iput(inode); /* truncate the inode here */ if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } exit_drop_write: mnt_drop_write(path.mnt); exit_path_put: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { if ((flag & ~AT_REMOVEDIR) != 0) return -EINVAL; CLASS(filename, name)(pathname); if (flag & AT_REMOVEDIR) return filename_rmdir(dfd, name); return filename_unlinkat(dfd, name); } SYSCALL_DEFINE1(unlink, const char __user *, pathname) { CLASS(filename, name)(pathname); return filename_unlinkat(AT_FDCWD, name); } /** * vfs_symlink - create symlink * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child symlink file * @oldname: name of the file to link to * @delegated_inode: returns victim inode, if the inode is delegated. * * Create a symlink. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *oldname, struct delegated_inode *delegated_inode) { int error; error = may_create_dentry(idmap, dir, dentry); if (error) return error; if (!dir->i_op->symlink) return -EPERM; error = security_inode_symlink(dir, dentry, oldname); if (error) return error; error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode); if (error) return error; error = dir->i_op->symlink(idmap, dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_symlink); int filename_symlinkat(struct filename *from, int newdfd, struct filename *to) { int error; struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; struct delegated_inode delegated_inode = { }; if (IS_ERR(from)) return PTR_ERR(from); retry: dentry = filename_create(newdfd, to, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_symlink(&path, dentry, from->name); if (!error) error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, from->name, &delegated_inode); end_creating_path(&path, dentry); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_symlinkat(old, newdfd, new); } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_symlinkat(old, AT_FDCWD, new); } /** * vfs_link - create a new link * @old_dentry: object to be linked * @idmap: idmap of the mount * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break * * The caller must hold dir->i_rwsem exclusively. * * If vfs_link discovers a delegation on the to-be-linked file in need * of breaking, it will return -EWOULDBLOCK and return a reference to the * inode in delegated_inode. The caller should then break the delegation * and retry. Because breaking a delegation may take a long time, the * caller should drop the i_rwsem before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, struct inode *dir, struct dentry *new_dentry, struct delegated_inode *delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; int error; if (!inode) return -ENOENT; error = may_create_dentry(idmap, dir, new_dentry); if (error) return error; if (dir->i_sb != inode->i_sb) return -EXDEV; /* * A link to an append-only or immutable file cannot be created. */ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; /* * Updating the link count will likely cause i_uid and i_gid to * be written back improperly if their true value is unknown to * the vfs. */ if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; if (S_ISDIR(inode->i_mode)) return -EPERM; error = security_inode_link(old_dentry, dir, new_dentry); if (error) return error; inode_lock(inode); /* Make sure we don't allow creating hardlink to an unlinked file */ if (inode->i_nlink == 0 && !(inode_state_read_once(inode) & I_LINKABLE)) error = -ENOENT; else if (max_links && inode->i_nlink >= max_links) error = -EMLINK; else { error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode); if (!error) error = try_break_deleg(inode, 0, delegated_inode); if (!error) error = dir->i_op->link(old_dentry, dir, new_dentry); } if (!error && (inode_state_read_once(inode) & I_LINKABLE)) { spin_lock(&inode->i_lock); inode_state_clear(inode, I_LINKABLE); spin_unlock(&inode->i_lock); } inode_unlock(inode); if (!error) fsnotify_link(dir, inode, new_dentry); return error; } EXPORT_SYMBOL(vfs_link); /* * Hardlinks are often used in delicate situations. We avoid * security-related surprises by not following symlinks on the * newname. --KAB * * We don't follow them on the oldname either to be compatible * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ int filename_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags) { struct mnt_idmap *idmap; struct dentry *new_dentry; struct path old_path, new_path; struct delegated_inode delegated_inode = { }; int how = 0; int error; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; /* * To use null names we require CAP_DAC_READ_SEARCH or * that the open-time creds of the dfd matches current. * This ensures that not everyone will be able to create * a hardlink using the passed file descriptor. */ if (flags & AT_EMPTY_PATH) how |= LOOKUP_LINKAT_EMPTY; if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: error = filename_lookup(olddfd, old, how, &old_path, NULL); if (error) return error; new_dentry = filename_create(newdfd, new, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto out_putpath; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; idmap = mnt_idmap(new_path.mnt); error = may_linkat(idmap, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; error = vfs_link(old_path.dentry, idmap, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: end_creating_path(&new_path, new_dentry); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) { path_put(&old_path); goto retry; } } if (retry_estale(error, how)) { path_put(&old_path); how |= LOOKUP_REVAL; goto retry; } out_putpath: path_put(&old_path); return error; } SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { CLASS(filename_uflags, old)(oldname, flags); CLASS(filename, new)(newname); return filename_linkat(olddfd, old, newdfd, new, flags); } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_linkat(AT_FDCWD, old, AT_FDCWD, new, 0); } /** * vfs_rename - rename a filesystem object * @rd: pointer to &struct renamedata info * * The caller must hold multiple mutexes--see lock_rename()). * * If vfs_rename discovers a delegation in need of breaking at either * the source or destination, it will return -EWOULDBLOCK and return a * reference to the inode in delegated_inode. The caller should then * break the delegation and retry. Because breaking a delegation may * take a long time, the caller should drop all locks before doing * so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we may have to lock up to _four_ objects - parents and victim (if it exists), * and source (if it's a non-directory or a subdirectory that moves to * different parent). * And that - after we got ->i_rwsem on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change * only under ->s_vfs_rename_mutex _and_ that parent of the object we * move will be locked. Thus we can rank directories by the tree * (ancestors first) and rank all non-directories after them. * That works since everybody except rename does "lock parent, lookup, * lock child" and rename is under ->s_vfs_rename_mutex. * HOWEVER, it relies on the assumption that any object with ->lookup() * has no more than 1 dentry. If "hybrid" objects will ever appear, * we'd better make sure that there's no link(2) for them. * d) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_rwsem * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on * ->i_rwsem on parents, which works but leads to some truly excessive * locking]. */ int vfs_rename(struct renamedata *rd) { int error; struct inode *old_dir = d_inode(rd->old_parent); struct inode *new_dir = d_inode(rd->new_parent); struct dentry *old_dentry = rd->old_dentry; struct dentry *new_dentry = rd->new_dentry; struct delegated_inode *delegated_inode = rd->delegated_inode; unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; error = may_delete_dentry(rd->mnt_idmap, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { error = may_create_dentry(rd->mnt_idmap, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) error = may_delete_dentry(rd->mnt_idmap, new_dir, new_dentry, is_dir); else error = may_delete_dentry(rd->mnt_idmap, new_dir, new_dentry, new_is_dir); } if (error) return error; if (!old_dir->i_op->rename) return -EPERM; /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { if (is_dir) { error = inode_permission(rd->mnt_idmap, source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { error = inode_permission(rd->mnt_idmap, target, MAY_WRITE); if (error) return error; } } error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) return error; take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* * Lock children. * The source subdirectory needs to be locked on cross-directory * rename or cross-directory exchange since its parent changes. * The target subdirectory needs to be locked on cross-directory * exchange due to parent change and on any rename due to becoming * a victim. * Non-directories need locking in all cases (for NFS reasons); * they get locked after any subdirectories (in inode address order). * * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ lock_old_subdir = new_dir != old_dir; lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); if (is_dir) { if (lock_old_subdir) inode_lock_nested(source, I_MUTEX_CHILD); if (target && (!new_is_dir || lock_new_subdir)) inode_lock(target); } else if (new_is_dir) { if (lock_new_subdir) inode_lock_nested(target, I_MUTEX_CHILD); inode_lock(source); } else { lock_two_nondirectories(source, target); } error = -EPERM; if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target))) goto out; error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; if (max_links && new_dir != old_dir) { error = -EMLINK; if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) goto out; if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && old_dir->i_nlink >= max_links) goto out; } error = try_break_deleg(old_dir, old_dir == new_dir ? LEASE_BREAK_DIR_RENAME : LEASE_BREAK_DIR_DELETE, delegated_inode); if (error) goto out; if (new_dir != old_dir) { error = try_break_deleg(new_dir, LEASE_BREAK_DIR_CREATE, delegated_inode); if (error) goto out; } if (!is_dir) { error = try_break_deleg(source, 0, delegated_inode); if (error) goto out; } if (target && !new_is_dir) { error = try_break_deleg(target, 0, delegated_inode); if (error) goto out; } error = old_dir->i_op->rename(rd->mnt_idmap, old_dir, old_dentry, new_dir, new_dentry, flags); if (error) goto out; if (!(flags & RENAME_EXCHANGE) && target) { if (is_dir) { shrink_dcache_parent(new_dentry); target->i_flags |= S_DEAD; } dont_mount(new_dentry); detach_mounts(new_dentry); } if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { if (!(flags & RENAME_EXCHANGE)) d_move(old_dentry, new_dentry); else d_exchange(old_dentry, new_dentry); } out: if (!is_dir || lock_old_subdir) inode_unlock(source); if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { fsnotify_move(old_dir, new_dir, &old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, &old_dentry->d_name, new_is_dir, NULL, new_dentry); } } release_dentry_name_snapshot(&old_name); return error; } EXPORT_SYMBOL(vfs_rename); int filename_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { struct renamedata rd; struct path old_path, new_path; struct qstr old_last, new_last; enum last_type old_type, new_type; struct delegated_inode delegated_inode = { }; unsigned int lookup_flags = 0; bool should_retry = false; int error; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) return -EINVAL; retry: error = filename_parentat(olddfd, from, lookup_flags, &old_path, &old_last, &old_type); if (error) return error; error = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, &new_type); if (error) goto exit1; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto exit2; error = -EBUSY; if (old_type != LAST_NORM) goto exit2; if (flags & RENAME_NOREPLACE) error = -EEXIST; if (new_type != LAST_NORM) goto exit2; error = mnt_want_write(old_path.mnt); if (error) goto exit2; retry_deleg: rd.old_parent = old_path.dentry; rd.mnt_idmap = mnt_idmap(old_path.mnt); rd.new_parent = new_path.dentry; rd.delegated_inode = &delegated_inode; rd.flags = flags; error = __start_renaming(&rd, lookup_flags, &old_last, &new_last); if (error) goto exit_lock_rename; if (flags & RENAME_EXCHANGE) { if (!d_is_dir(rd.new_dentry)) { error = -ENOTDIR; if (new_last.name[new_last.len]) goto exit_unlock; } } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(rd.old_dentry)) { error = -ENOTDIR; if (old_last.name[old_last.len]) goto exit_unlock; if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len]) goto exit_unlock; } error = security_path_rename(&old_path, rd.old_dentry, &new_path, rd.new_dentry, flags); if (error) goto exit_unlock; error = vfs_rename(&rd); exit_unlock: end_renaming(&rd); exit_lock_rename: if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(old_path.mnt); exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); exit1: path_put(&old_path); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_renameat2(olddfd, old, newdfd, new, flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_renameat2(olddfd, old, newdfd, new, 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_renameat2(AT_FDCWD, old, AT_FDCWD, new, 0); } int readlink_copy(char __user *buffer, int buflen, const char *link, int linklen) { int copylen; copylen = linklen; if (unlikely(copylen > (unsigned) buflen)) copylen = buflen; if (copy_to_user(buffer, link, copylen)) copylen = -EFAULT; return copylen; } /** * vfs_readlink - copy symlink body into userspace buffer * @dentry: dentry on which to get symbolic link * @buffer: user memory pointer * @buflen: size of buffer * * Does not touch atime. That's up to the caller if necessary * * Does not call security hook. */ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); DEFINE_DELAYED_CALL(done); const char *link; int res; if (inode->i_opflags & IOP_CACHED_LINK) return readlink_copy(buffer, buflen, inode->i_link, inode->i_linklen); if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); if (!d_is_symlink(dentry)) return -EINVAL; spin_lock(&inode->i_lock); inode->i_opflags |= IOP_DEFAULT_READLINK; spin_unlock(&inode->i_lock); } link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(vfs_readlink); /** * vfs_get_link - get symlink body * @dentry: dentry on which to get symbolic link * @done: caller needs to free returned data with this * * Calls security hook and i_op->get_link() on the supplied inode. * * It does not touch atime. That's up to the caller if necessary. * * Does not work on "special" symlinks like /proc/$$/fd/N */ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) { const char *res = ERR_PTR(-EINVAL); struct inode *inode = d_inode(dentry); if (d_is_symlink(dentry)) { res = ERR_PTR(security_inode_readlink(dentry)); if (!res) res = inode->i_op->get_link(dentry, inode, done); } return res; } EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ static char *__page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { struct folio *folio; struct address_space *mapping = inode->i_mapping; if (!dentry) { folio = filemap_get_folio(mapping, 0); if (IS_ERR(folio)) return ERR_PTR(-ECHILD); if (!folio_test_uptodate(folio)) { folio_put(folio); return ERR_PTR(-ECHILD); } } else { folio = read_mapping_folio(mapping, 0, NULL); if (IS_ERR(folio)) return ERR_CAST(folio); } set_delayed_call(callback, page_put_link, folio); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); return folio_address(folio); } const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { return __page_get_link(dentry, inode, callback); } EXPORT_SYMBOL_GPL(page_get_link_raw); /** * page_get_link() - An implementation of the get_link inode_operation. * @dentry: The directory entry which is the symlink. * @inode: The inode for the symlink. * @callback: Used to drop the reference to the symlink. * * Filesystems which store their symlinks in the page cache should use * this to implement the get_link() member of their inode_operations. * * Return: A pointer to the NUL-terminated symlink. */ const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { char *kaddr = __page_get_link(dentry, inode, callback); if (!IS_ERR(kaddr)) nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } EXPORT_SYMBOL(page_get_link); /** * page_put_link() - Drop the reference to the symlink. * @arg: The folio which contains the symlink. * * This is used internally by page_get_link(). It is exported for use * by filesystems which need to implement a variant of page_get_link() * themselves. Despite the apparent symmetry, filesystems which use * page_get_link() do not need to call page_put_link(). * * The argument, while it has a void pointer type, must be a pointer to * the folio which was retrieved from the page cache. The delayed_call * infrastructure is used to drop the reference count once the caller * is done with the symlink. */ void page_put_link(void *arg) { folio_put(arg); } EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { const char *link; int res; DEFINE_DELAYED_CALL(done); link = page_get_link(dentry, d_inode(dentry), &done); res = PTR_ERR(link); if (!IS_ERR(link)) res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(page_readlink); int page_symlink(struct inode *inode, const char *symname, int len) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS); struct folio *folio; void *fsdata = NULL; int err; unsigned int flags; retry: if (nofs) flags = memalloc_nofs_save(); err = aops->write_begin(NULL, mapping, 0, len-1, &folio, &fsdata); if (nofs) memalloc_nofs_restore(flags); if (err) goto fail; memcpy(folio_address(folio), symname, len - 1); err = aops->write_end(NULL, mapping, 0, len - 1, len - 1, folio, fsdata); if (err < 0) goto fail; if (err < len-1) goto retry; mark_inode_dirty(inode); return 0; fail: return err; } EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); |
| 4 4 4 4 4 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 4 4 2 4 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Digital Audio (PCM) abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/nospec.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/pcm.h> #include <sound/timer.h> #include <sound/control.h> #include <sound/info.h> #include "pcm_local.h" MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Abramo Bagnara <abramo@alsa-project.org>"); MODULE_DESCRIPTION("Midlevel PCM code for ALSA."); MODULE_LICENSE("GPL"); static LIST_HEAD(snd_pcm_devices); static DEFINE_MUTEX(register_mutex); #if IS_ENABLED(CONFIG_SND_PCM_OSS) static LIST_HEAD(snd_pcm_notify_list); #endif static int snd_pcm_free(struct snd_pcm *pcm); static int snd_pcm_dev_free(struct snd_device *device); static int snd_pcm_dev_register(struct snd_device *device); static int snd_pcm_dev_disconnect(struct snd_device *device); static struct snd_pcm *snd_pcm_get(struct snd_card *card, int device) { struct snd_pcm *pcm; list_for_each_entry(pcm, &snd_pcm_devices, list) { if (pcm->card == card && pcm->device == device) return pcm; } return NULL; } static int snd_pcm_next(struct snd_card *card, int device) { struct snd_pcm *pcm; list_for_each_entry(pcm, &snd_pcm_devices, list) { if (pcm->card == card && pcm->device > device) return pcm->device; else if (pcm->card->number > card->number) return -1; } return -1; } static int snd_pcm_add(struct snd_pcm *newpcm) { struct snd_pcm *pcm; if (newpcm->internal) return 0; list_for_each_entry(pcm, &snd_pcm_devices, list) { if (pcm->card == newpcm->card && pcm->device == newpcm->device) return -EBUSY; if (pcm->card->number > newpcm->card->number || (pcm->card == newpcm->card && pcm->device > newpcm->device)) { list_add(&newpcm->list, pcm->list.prev); return 0; } } list_add_tail(&newpcm->list, &snd_pcm_devices); return 0; } static int snd_pcm_control_ioctl(struct snd_card *card, struct snd_ctl_file *control, unsigned int cmd, unsigned long arg) { switch (cmd) { case SNDRV_CTL_IOCTL_PCM_NEXT_DEVICE: { int device; if (get_user(device, (int __user *)arg)) return -EFAULT; scoped_guard(mutex, ®ister_mutex) device = snd_pcm_next(card, device); if (put_user(device, (int __user *)arg)) return -EFAULT; return 0; } case SNDRV_CTL_IOCTL_PCM_INFO: { struct snd_pcm_info __user *info; unsigned int device, subdevice; int stream; struct snd_pcm *pcm; struct snd_pcm_str *pstr; struct snd_pcm_substream *substream; info = (struct snd_pcm_info __user *)arg; if (get_user(device, &info->device)) return -EFAULT; if (get_user(stream, &info->stream)) return -EFAULT; if (stream < 0 || stream > 1) return -EINVAL; stream = array_index_nospec(stream, 2); if (get_user(subdevice, &info->subdevice)) return -EFAULT; guard(mutex)(®ister_mutex); pcm = snd_pcm_get(card, device); if (pcm == NULL) return -ENXIO; pstr = &pcm->streams[stream]; if (pstr->substream_count == 0) return -ENOENT; if (subdevice >= pstr->substream_count) return -ENXIO; for (substream = pstr->substream; substream; substream = substream->next) if (substream->number == (int)subdevice) break; if (substream == NULL) return -ENXIO; guard(mutex)(&pcm->open_mutex); return snd_pcm_info_user(substream, info); } case SNDRV_CTL_IOCTL_PCM_PREFER_SUBDEVICE: { int val; if (get_user(val, (int __user *)arg)) return -EFAULT; control->preferred_subdevice[SND_CTL_SUBDEV_PCM] = val; return 0; } } return -ENOIOCTLCMD; } #define FORMAT(v) [SNDRV_PCM_FORMAT_##v] = #v static const char * const snd_pcm_format_names[] = { FORMAT(S8), FORMAT(U8), FORMAT(S16_LE), FORMAT(S16_BE), FORMAT(U16_LE), FORMAT(U16_BE), FORMAT(S24_LE), FORMAT(S24_BE), FORMAT(U24_LE), FORMAT(U24_BE), FORMAT(S32_LE), FORMAT(S32_BE), FORMAT(U32_LE), FORMAT(U32_BE), FORMAT(FLOAT_LE), FORMAT(FLOAT_BE), FORMAT(FLOAT64_LE), FORMAT(FLOAT64_BE), FORMAT(IEC958_SUBFRAME_LE), FORMAT(IEC958_SUBFRAME_BE), FORMAT(MU_LAW), FORMAT(A_LAW), FORMAT(IMA_ADPCM), FORMAT(MPEG), FORMAT(GSM), FORMAT(SPECIAL), FORMAT(S24_3LE), FORMAT(S24_3BE), FORMAT(U24_3LE), FORMAT(U24_3BE), FORMAT(S20_3LE), FORMAT(S20_3BE), FORMAT(U20_3LE), FORMAT(U20_3BE), FORMAT(S18_3LE), FORMAT(S18_3BE), FORMAT(U18_3LE), FORMAT(U18_3BE), FORMAT(G723_24), FORMAT(G723_24_1B), FORMAT(G723_40), FORMAT(G723_40_1B), FORMAT(DSD_U8), FORMAT(DSD_U16_LE), FORMAT(DSD_U32_LE), FORMAT(DSD_U16_BE), FORMAT(DSD_U32_BE), FORMAT(S20_LE), FORMAT(S20_BE), FORMAT(U20_LE), FORMAT(U20_BE), }; /** * snd_pcm_format_name - Return a name string for the given PCM format * @format: PCM format * * Return: the format name string */ const char *snd_pcm_format_name(snd_pcm_format_t format) { unsigned int format_num = (__force unsigned int)format; if (format_num >= ARRAY_SIZE(snd_pcm_format_names) || !snd_pcm_format_names[format_num]) return "Unknown"; return snd_pcm_format_names[format_num]; } EXPORT_SYMBOL_GPL(snd_pcm_format_name); #ifdef CONFIG_SND_VERBOSE_PROCFS #define STATE(v) [SNDRV_PCM_STATE_##v] = #v #define STREAM(v) [SNDRV_PCM_STREAM_##v] = #v #define READY(v) [SNDRV_PCM_READY_##v] = #v #define XRUN(v) [SNDRV_PCM_XRUN_##v] = #v #define SILENCE(v) [SNDRV_PCM_SILENCE_##v] = #v #define TSTAMP(v) [SNDRV_PCM_TSTAMP_##v] = #v #define ACCESS(v) [SNDRV_PCM_ACCESS_##v] = #v #define START(v) [SNDRV_PCM_START_##v] = #v #define SUBFORMAT(v) [SNDRV_PCM_SUBFORMAT_##v] = #v static const char * const snd_pcm_stream_names[] = { STREAM(PLAYBACK), STREAM(CAPTURE), }; static const char * const snd_pcm_state_names[] = { STATE(OPEN), STATE(SETUP), STATE(PREPARED), STATE(RUNNING), STATE(XRUN), STATE(DRAINING), STATE(PAUSED), STATE(SUSPENDED), STATE(DISCONNECTED), }; static const char * const snd_pcm_access_names[] = { ACCESS(MMAP_INTERLEAVED), ACCESS(MMAP_NONINTERLEAVED), ACCESS(MMAP_COMPLEX), ACCESS(RW_INTERLEAVED), ACCESS(RW_NONINTERLEAVED), }; static const char * const snd_pcm_subformat_names[] = { SUBFORMAT(STD), SUBFORMAT(MSBITS_MAX), SUBFORMAT(MSBITS_20), SUBFORMAT(MSBITS_24), }; static const char * const snd_pcm_tstamp_mode_names[] = { TSTAMP(NONE), TSTAMP(ENABLE), }; static const char *snd_pcm_stream_name(int stream) { return snd_pcm_stream_names[stream]; } static const char *snd_pcm_access_name(snd_pcm_access_t access) { return snd_pcm_access_names[(__force int)access]; } static const char *snd_pcm_subformat_name(snd_pcm_subformat_t subformat) { return snd_pcm_subformat_names[(__force int)subformat]; } static const char *snd_pcm_tstamp_mode_name(int mode) { return snd_pcm_tstamp_mode_names[mode]; } static const char *snd_pcm_state_name(snd_pcm_state_t state) { return snd_pcm_state_names[(__force int)state]; } #if IS_ENABLED(CONFIG_SND_PCM_OSS) #include <linux/soundcard.h> static const char *snd_pcm_oss_format_name(int format) { switch (format) { case AFMT_MU_LAW: return "MU_LAW"; case AFMT_A_LAW: return "A_LAW"; case AFMT_IMA_ADPCM: return "IMA_ADPCM"; case AFMT_U8: return "U8"; case AFMT_S16_LE: return "S16_LE"; case AFMT_S16_BE: return "S16_BE"; case AFMT_S8: return "S8"; case AFMT_U16_LE: return "U16_LE"; case AFMT_U16_BE: return "U16_BE"; case AFMT_MPEG: return "MPEG"; default: return "unknown"; } } #endif static void snd_pcm_proc_info_read(struct snd_pcm_substream *substream, struct snd_info_buffer *buffer) { int err; if (! substream) return; struct snd_pcm_info *info __free(kfree) = kmalloc_obj(*info); if (!info) return; err = snd_pcm_info(substream, info); if (err < 0) { snd_iprintf(buffer, "error %d\n", err); return; } snd_iprintf(buffer, "card: %d\n", info->card); snd_iprintf(buffer, "device: %d\n", info->device); snd_iprintf(buffer, "subdevice: %d\n", info->subdevice); snd_iprintf(buffer, "stream: %s\n", snd_pcm_stream_name(info->stream)); snd_iprintf(buffer, "id: %s\n", info->id); snd_iprintf(buffer, "name: %s\n", info->name); snd_iprintf(buffer, "subname: %s\n", info->subname); snd_iprintf(buffer, "class: %d\n", info->dev_class); snd_iprintf(buffer, "subclass: %d\n", info->dev_subclass); snd_iprintf(buffer, "subdevices_count: %d\n", info->subdevices_count); snd_iprintf(buffer, "subdevices_avail: %d\n", info->subdevices_avail); } static void snd_pcm_stream_proc_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { snd_pcm_proc_info_read(((struct snd_pcm_str *)entry->private_data)->substream, buffer); } static void snd_pcm_substream_proc_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { snd_pcm_proc_info_read(entry->private_data, buffer); } static void snd_pcm_substream_proc_hw_params_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; struct snd_pcm_runtime *runtime; guard(mutex)(&substream->pcm->open_mutex); runtime = substream->runtime; if (!runtime) { snd_iprintf(buffer, "closed\n"); return; } if (runtime->state == SNDRV_PCM_STATE_OPEN) { snd_iprintf(buffer, "no setup\n"); return; } snd_iprintf(buffer, "access: %s\n", snd_pcm_access_name(runtime->access)); snd_iprintf(buffer, "format: %s\n", snd_pcm_format_name(runtime->format)); snd_iprintf(buffer, "subformat: %s\n", snd_pcm_subformat_name(runtime->subformat)); snd_iprintf(buffer, "channels: %u\n", runtime->channels); snd_iprintf(buffer, "rate: %u (%u/%u)\n", runtime->rate, runtime->rate_num, runtime->rate_den); snd_iprintf(buffer, "period_size: %lu\n", runtime->period_size); snd_iprintf(buffer, "buffer_size: %lu\n", runtime->buffer_size); #if IS_ENABLED(CONFIG_SND_PCM_OSS) if (substream->oss.oss) { snd_iprintf(buffer, "OSS format: %s\n", snd_pcm_oss_format_name(runtime->oss.format)); snd_iprintf(buffer, "OSS channels: %u\n", runtime->oss.channels); snd_iprintf(buffer, "OSS rate: %u\n", runtime->oss.rate); snd_iprintf(buffer, "OSS period bytes: %lu\n", (unsigned long)runtime->oss.period_bytes); snd_iprintf(buffer, "OSS periods: %u\n", runtime->oss.periods); snd_iprintf(buffer, "OSS period frames: %lu\n", (unsigned long)runtime->oss.period_frames); } #endif } static void snd_pcm_substream_proc_sw_params_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; struct snd_pcm_runtime *runtime; guard(mutex)(&substream->pcm->open_mutex); runtime = substream->runtime; if (!runtime) { snd_iprintf(buffer, "closed\n"); return; } if (runtime->state == SNDRV_PCM_STATE_OPEN) { snd_iprintf(buffer, "no setup\n"); return; } snd_iprintf(buffer, "tstamp_mode: %s\n", snd_pcm_tstamp_mode_name(runtime->tstamp_mode)); snd_iprintf(buffer, "period_step: %u\n", runtime->period_step); snd_iprintf(buffer, "avail_min: %lu\n", runtime->control->avail_min); snd_iprintf(buffer, "start_threshold: %lu\n", runtime->start_threshold); snd_iprintf(buffer, "stop_threshold: %lu\n", runtime->stop_threshold); snd_iprintf(buffer, "silence_threshold: %lu\n", runtime->silence_threshold); snd_iprintf(buffer, "silence_size: %lu\n", runtime->silence_size); snd_iprintf(buffer, "boundary: %lu\n", runtime->boundary); } static void snd_pcm_substream_proc_status_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; struct snd_pcm_runtime *runtime; struct snd_pcm_status64 status; int err; guard(mutex)(&substream->pcm->open_mutex); runtime = substream->runtime; if (!runtime) { snd_iprintf(buffer, "closed\n"); return; } memset(&status, 0, sizeof(status)); err = snd_pcm_status64(substream, &status); if (err < 0) { snd_iprintf(buffer, "error %d\n", err); return; } snd_iprintf(buffer, "state: %s\n", snd_pcm_state_name(status.state)); snd_iprintf(buffer, "owner_pid : %d\n", pid_vnr(substream->pid)); snd_iprintf(buffer, "trigger_time: %lld.%09lld\n", status.trigger_tstamp_sec, status.trigger_tstamp_nsec); snd_iprintf(buffer, "tstamp : %lld.%09lld\n", status.tstamp_sec, status.tstamp_nsec); snd_iprintf(buffer, "delay : %ld\n", status.delay); snd_iprintf(buffer, "avail : %ld\n", status.avail); snd_iprintf(buffer, "avail_max : %ld\n", status.avail_max); snd_iprintf(buffer, "-----\n"); snd_iprintf(buffer, "hw_ptr : %ld\n", runtime->status->hw_ptr); snd_iprintf(buffer, "appl_ptr : %ld\n", runtime->control->appl_ptr); #ifdef CONFIG_SND_PCM_XRUN_DEBUG snd_iprintf(buffer, "xrun_counter: %d\n", substream->xrun_counter); #endif } #ifdef CONFIG_SND_PCM_XRUN_DEBUG static void snd_pcm_xrun_injection_write(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_substream *substream = entry->private_data; snd_pcm_stop_xrun(substream); } static void snd_pcm_xrun_debug_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_str *pstr = entry->private_data; snd_iprintf(buffer, "%d\n", pstr->xrun_debug); } static void snd_pcm_xrun_debug_write(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm_str *pstr = entry->private_data; char line[64]; if (!snd_info_get_line(buffer, line, sizeof(line))) pstr->xrun_debug = simple_strtoul(line, NULL, 10); } #endif static int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr) { struct snd_pcm *pcm = pstr->pcm; struct snd_info_entry *entry; char name[16]; sprintf(name, "pcm%i%c", pcm->device, pstr->stream == SNDRV_PCM_STREAM_PLAYBACK ? 'p' : 'c'); entry = snd_info_create_card_entry(pcm->card, name, pcm->card->proc_root); if (!entry) return -ENOMEM; entry->mode = S_IFDIR | 0555; pstr->proc_root = entry; entry = snd_info_create_card_entry(pcm->card, "info", pstr->proc_root); if (entry) snd_info_set_text_ops(entry, pstr, snd_pcm_stream_proc_info_read); #ifdef CONFIG_SND_PCM_XRUN_DEBUG entry = snd_info_create_card_entry(pcm->card, "xrun_debug", pstr->proc_root); if (entry) { snd_info_set_text_ops(entry, pstr, snd_pcm_xrun_debug_read); entry->c.text.write = snd_pcm_xrun_debug_write; entry->mode |= 0200; } #endif return 0; } static int snd_pcm_stream_proc_done(struct snd_pcm_str *pstr) { snd_info_free_entry(pstr->proc_root); pstr->proc_root = NULL; return 0; } static struct snd_info_entry * create_substream_info_entry(struct snd_pcm_substream *substream, const char *name, void (*read)(struct snd_info_entry *, struct snd_info_buffer *)) { struct snd_info_entry *entry; entry = snd_info_create_card_entry(substream->pcm->card, name, substream->proc_root); if (entry) snd_info_set_text_ops(entry, substream, read); return entry; } static int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream) { struct snd_info_entry *entry; struct snd_card *card; char name[16]; card = substream->pcm->card; sprintf(name, "sub%i", substream->number); entry = snd_info_create_card_entry(card, name, substream->pstr->proc_root); if (!entry) return -ENOMEM; entry->mode = S_IFDIR | 0555; substream->proc_root = entry; create_substream_info_entry(substream, "info", snd_pcm_substream_proc_info_read); create_substream_info_entry(substream, "hw_params", snd_pcm_substream_proc_hw_params_read); create_substream_info_entry(substream, "sw_params", snd_pcm_substream_proc_sw_params_read); create_substream_info_entry(substream, "status", snd_pcm_substream_proc_status_read); #ifdef CONFIG_SND_PCM_XRUN_DEBUG entry = create_substream_info_entry(substream, "xrun_injection", NULL); if (entry) { entry->c.text.write = snd_pcm_xrun_injection_write; entry->mode = S_IFREG | 0200; } #endif /* CONFIG_SND_PCM_XRUN_DEBUG */ return 0; } #else /* !CONFIG_SND_VERBOSE_PROCFS */ static inline int snd_pcm_stream_proc_init(struct snd_pcm_str *pstr) { return 0; } static inline int snd_pcm_stream_proc_done(struct snd_pcm_str *pstr) { return 0; } static inline int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream) { return 0; } #endif /* CONFIG_SND_VERBOSE_PROCFS */ static const struct attribute_group *pcm_dev_attr_groups[]; /* * PM callbacks: we need to deal only with suspend here, as the resume is * triggered either from user-space or the driver's resume callback */ static int do_pcm_suspend(struct device *dev) { struct snd_pcm_str *pstr = dev_get_drvdata(dev); if (!pstr->pcm->no_device_suspend) snd_pcm_suspend_all(pstr->pcm); return 0; } static const struct dev_pm_ops pcm_dev_pm_ops = { SYSTEM_SLEEP_PM_OPS(do_pcm_suspend, NULL) }; /* device type for PCM -- basically only for passing PM callbacks */ static const struct device_type pcm_dev_type = { .name = "pcm", .pm = &pcm_dev_pm_ops, }; /** * snd_pcm_new_stream - create a new PCM stream * @pcm: the pcm instance * @stream: the stream direction, SNDRV_PCM_STREAM_XXX * @substream_count: the number of substreams * * Creates a new stream for the pcm. * The corresponding stream on the pcm must have been empty before * calling this, i.e. zero must be given to the argument of * snd_pcm_new(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count) { int idx, err; struct snd_pcm_str *pstr = &pcm->streams[stream]; struct snd_pcm_substream *substream, *prev; #if IS_ENABLED(CONFIG_SND_PCM_OSS) mutex_init(&pstr->oss.setup_mutex); #endif pstr->stream = stream; pstr->pcm = pcm; pstr->substream_count = substream_count; if (!substream_count) return 0; err = snd_device_alloc(&pstr->dev, pcm->card); if (err < 0) return err; dev_set_name(pstr->dev, "pcmC%iD%i%c", pcm->card->number, pcm->device, stream == SNDRV_PCM_STREAM_PLAYBACK ? 'p' : 'c'); pstr->dev->groups = pcm_dev_attr_groups; pstr->dev->type = &pcm_dev_type; dev_set_drvdata(pstr->dev, pstr); if (!pcm->internal) { err = snd_pcm_stream_proc_init(pstr); if (err < 0) { pcm_err(pcm, "Error in snd_pcm_stream_proc_init\n"); return err; } } prev = NULL; for (idx = 0, prev = NULL; idx < substream_count; idx++) { substream = kzalloc_obj(*substream); if (!substream) return -ENOMEM; substream->pcm = pcm; substream->pstr = pstr; substream->number = idx; substream->stream = stream; sprintf(substream->name, "subdevice #%i", idx); substream->buffer_bytes_max = UINT_MAX; if (prev == NULL) pstr->substream = substream; else prev->next = substream; if (!pcm->internal) { err = snd_pcm_substream_proc_init(substream); if (err < 0) { pcm_err(pcm, "Error in snd_pcm_stream_proc_init\n"); if (prev == NULL) pstr->substream = NULL; else prev->next = NULL; kfree(substream); return err; } } substream->group = &substream->self_group; snd_pcm_group_init(&substream->self_group); list_add_tail(&substream->link_list, &substream->self_group.substreams); atomic_set(&substream->mmap_count, 0); prev = substream; } return 0; } EXPORT_SYMBOL(snd_pcm_new_stream); static int _snd_pcm_new(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, bool internal, struct snd_pcm **rpcm) { struct snd_pcm *pcm; int err; static const struct snd_device_ops ops = { .dev_free = snd_pcm_dev_free, .dev_register = snd_pcm_dev_register, .dev_disconnect = snd_pcm_dev_disconnect, }; static const struct snd_device_ops internal_ops = { .dev_free = snd_pcm_dev_free, }; if (snd_BUG_ON(!card)) return -ENXIO; if (rpcm) *rpcm = NULL; pcm = kzalloc_obj(*pcm); if (!pcm) return -ENOMEM; pcm->card = card; pcm->device = device; pcm->internal = internal; mutex_init(&pcm->open_mutex); init_waitqueue_head(&pcm->open_wait); INIT_LIST_HEAD(&pcm->list); if (id) strscpy(pcm->id, id, sizeof(pcm->id)); err = snd_pcm_new_stream(pcm, SNDRV_PCM_STREAM_PLAYBACK, playback_count); if (err < 0) goto free_pcm; err = snd_pcm_new_stream(pcm, SNDRV_PCM_STREAM_CAPTURE, capture_count); if (err < 0) goto free_pcm; err = snd_device_new(card, SNDRV_DEV_PCM, pcm, internal ? &internal_ops : &ops); if (err < 0) goto free_pcm; if (rpcm) *rpcm = pcm; return 0; free_pcm: snd_pcm_free(pcm); return err; } /** * snd_pcm_new - create a new PCM instance * @card: the card instance * @id: the id string * @device: the device index (zero based) * @playback_count: the number of substreams for playback * @capture_count: the number of substreams for capture * @rpcm: the pointer to store the new pcm instance * * Creates a new PCM instance. * * The pcm operators have to be set afterwards to the new instance * via snd_pcm_set_ops(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_pcm_new(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm) { return _snd_pcm_new(card, id, device, playback_count, capture_count, false, rpcm); } EXPORT_SYMBOL(snd_pcm_new); /** * snd_pcm_new_internal - create a new internal PCM instance * @card: the card instance * @id: the id string * @device: the device index (zero based - shared with normal PCMs) * @playback_count: the number of substreams for playback * @capture_count: the number of substreams for capture * @rpcm: the pointer to store the new pcm instance * * Creates a new internal PCM instance with no userspace device or procfs * entries. This is used by ASoC Back End PCMs in order to create a PCM that * will only be used internally by kernel drivers. i.e. it cannot be opened * by userspace. It provides existing ASoC components drivers with a substream * and access to any private data. * * The pcm operators have to be set afterwards to the new instance * via snd_pcm_set_ops(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_pcm_new_internal(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm) { return _snd_pcm_new(card, id, device, playback_count, capture_count, true, rpcm); } EXPORT_SYMBOL(snd_pcm_new_internal); static void free_chmap(struct snd_pcm_str *pstr) { if (pstr->chmap_kctl) { struct snd_card *card = pstr->pcm->card; snd_ctl_remove(card, pstr->chmap_kctl); pstr->chmap_kctl = NULL; } } static void snd_pcm_free_stream(struct snd_pcm_str * pstr) { struct snd_pcm_substream *substream, *substream_next; #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_oss_setup *setup, *setupn; #endif /* free all proc files under the stream */ snd_pcm_stream_proc_done(pstr); substream = pstr->substream; while (substream) { substream_next = substream->next; snd_pcm_timer_done(substream); kfree(substream); substream = substream_next; } #if IS_ENABLED(CONFIG_SND_PCM_OSS) for (setup = pstr->oss.setup_list; setup; setup = setupn) { setupn = setup->next; kfree(setup->task_name); kfree(setup); } #endif free_chmap(pstr); if (pstr->substream_count) put_device(pstr->dev); } #if IS_ENABLED(CONFIG_SND_PCM_OSS) #define pcm_call_notify(pcm, call) \ do { \ struct snd_pcm_notify *_notify; \ list_for_each_entry(_notify, &snd_pcm_notify_list, list) \ _notify->call(pcm); \ } while (0) #else #define pcm_call_notify(pcm, call) do {} while (0) #endif static int snd_pcm_free(struct snd_pcm *pcm) { if (!pcm) return 0; if (!pcm->internal) pcm_call_notify(pcm, n_unregister); if (pcm->private_free) pcm->private_free(pcm); snd_pcm_lib_preallocate_free_for_all(pcm); snd_pcm_free_stream(&pcm->streams[SNDRV_PCM_STREAM_PLAYBACK]); snd_pcm_free_stream(&pcm->streams[SNDRV_PCM_STREAM_CAPTURE]); kfree(pcm); return 0; } static int snd_pcm_dev_free(struct snd_device *device) { struct snd_pcm *pcm = device->device_data; return snd_pcm_free(pcm); } int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream, struct file *file, struct snd_pcm_substream **rsubstream) { struct snd_pcm_str * pstr; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; struct snd_card *card; int prefer_subdevice; size_t size; if (snd_BUG_ON(!pcm || !rsubstream)) return -ENXIO; if (snd_BUG_ON(stream != SNDRV_PCM_STREAM_PLAYBACK && stream != SNDRV_PCM_STREAM_CAPTURE)) return -EINVAL; *rsubstream = NULL; pstr = &pcm->streams[stream]; if (pstr->substream == NULL || pstr->substream_count == 0) return -ENODEV; card = pcm->card; prefer_subdevice = snd_ctl_get_preferred_subdevice(card, SND_CTL_SUBDEV_PCM); if (pcm->info_flags & SNDRV_PCM_INFO_HALF_DUPLEX) { int opposite = !stream; for (substream = pcm->streams[opposite].substream; substream; substream = substream->next) { if (SUBSTREAM_BUSY(substream)) return -EAGAIN; } } if (file->f_flags & O_APPEND) { if (prefer_subdevice < 0) { if (pstr->substream_count > 1) return -EINVAL; /* must be unique */ substream = pstr->substream; } else { for (substream = pstr->substream; substream; substream = substream->next) if (substream->number == prefer_subdevice) break; } if (! substream) return -ENODEV; if (! SUBSTREAM_BUSY(substream)) return -EBADFD; substream->ref_count++; *rsubstream = substream; return 0; } for (substream = pstr->substream; substream; substream = substream->next) { if (!SUBSTREAM_BUSY(substream) && (prefer_subdevice == -1 || substream->number == prefer_subdevice)) break; } if (substream == NULL) return -EAGAIN; runtime = kzalloc_obj(*runtime); if (runtime == NULL) return -ENOMEM; size = PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status)); runtime->status = alloc_pages_exact(size, GFP_KERNEL); if (runtime->status == NULL) { kfree(runtime); return -ENOMEM; } memset(runtime->status, 0, size); size = PAGE_ALIGN(sizeof(struct snd_pcm_mmap_control)); runtime->control = alloc_pages_exact(size, GFP_KERNEL); if (runtime->control == NULL) { free_pages_exact(runtime->status, PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status))); kfree(runtime); return -ENOMEM; } memset(runtime->control, 0, size); init_waitqueue_head(&runtime->sleep); init_waitqueue_head(&runtime->tsleep); __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_OPEN); mutex_init(&runtime->buffer_mutex); atomic_set(&runtime->buffer_accessing, 0); substream->runtime = runtime; substream->private_data = pcm->private_data; substream->ref_count = 1; substream->f_flags = file->f_flags; substream->pid = get_pid(task_pid(current)); pstr->substream_opened++; *rsubstream = substream; #ifdef CONFIG_SND_PCM_XRUN_DEBUG substream->xrun_counter = 0; #endif /* CONFIG_SND_PCM_XRUN_DEBUG */ return 0; } void snd_pcm_detach_substream(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime; if (PCM_RUNTIME_CHECK(substream)) return; runtime = substream->runtime; if (runtime->private_free != NULL) runtime->private_free(runtime); free_pages_exact(runtime->status, PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status))); free_pages_exact(runtime->control, PAGE_ALIGN(sizeof(struct snd_pcm_mmap_control))); kfree(runtime->hw_constraints.rules); /* Avoid concurrent access to runtime via PCM timer interface */ if (substream->timer) { scoped_guard(spinlock_irq, &substream->timer->lock) substream->runtime = NULL; } else { substream->runtime = NULL; } mutex_destroy(&runtime->buffer_mutex); snd_fasync_free(runtime->fasync); kfree(runtime); put_pid(substream->pid); substream->pid = NULL; substream->pstr->substream_opened--; } static ssize_t pcm_class_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_pcm_str *pstr = dev_get_drvdata(dev); struct snd_pcm *pcm = pstr->pcm; const char *str; static const char *strs[SNDRV_PCM_CLASS_LAST + 1] = { [SNDRV_PCM_CLASS_GENERIC] = "generic", [SNDRV_PCM_CLASS_MULTI] = "multi", [SNDRV_PCM_CLASS_MODEM] = "modem", [SNDRV_PCM_CLASS_DIGITIZER] = "digitizer", }; if (pcm->dev_class > SNDRV_PCM_CLASS_LAST) str = "none"; else str = strs[pcm->dev_class]; return sysfs_emit(buf, "%s\n", str); } static DEVICE_ATTR_RO(pcm_class); static struct attribute *pcm_dev_attrs[] = { &dev_attr_pcm_class.attr, NULL }; static const struct attribute_group pcm_dev_attr_group = { .attrs = pcm_dev_attrs, }; static const struct attribute_group *pcm_dev_attr_groups[] = { &pcm_dev_attr_group, NULL }; static int snd_pcm_dev_register(struct snd_device *device) { int cidx, err; struct snd_pcm_substream *substream; struct snd_pcm *pcm; if (snd_BUG_ON(!device || !device->device_data)) return -ENXIO; pcm = device->device_data; guard(mutex)(®ister_mutex); err = snd_pcm_add(pcm); if (err) return err; for (cidx = 0; cidx < 2; cidx++) { int devtype = -1; if (pcm->streams[cidx].substream == NULL) continue; switch (cidx) { case SNDRV_PCM_STREAM_PLAYBACK: devtype = SNDRV_DEVICE_TYPE_PCM_PLAYBACK; break; case SNDRV_PCM_STREAM_CAPTURE: devtype = SNDRV_DEVICE_TYPE_PCM_CAPTURE; break; } /* register pcm */ err = snd_register_device(devtype, pcm->card, pcm->device, &snd_pcm_f_ops[cidx], pcm, pcm->streams[cidx].dev); if (err < 0) { list_del_init(&pcm->list); return err; } for (substream = pcm->streams[cidx].substream; substream; substream = substream->next) snd_pcm_timer_init(substream); } pcm_call_notify(pcm, n_register); return err; } static int snd_pcm_dev_disconnect(struct snd_device *device) { struct snd_pcm *pcm = device->device_data; struct snd_pcm_substream *substream; int cidx; guard(mutex)(®ister_mutex); guard(mutex)(&pcm->open_mutex); wake_up(&pcm->open_wait); list_del_init(&pcm->list); for_each_pcm_substream(pcm, cidx, substream) { snd_pcm_stream_lock_irq(substream); if (substream->runtime) { if (snd_pcm_running(substream)) snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED); /* to be sure, set the state unconditionally */ __snd_pcm_set_state(substream->runtime, SNDRV_PCM_STATE_DISCONNECTED); wake_up(&substream->runtime->sleep); wake_up(&substream->runtime->tsleep); } snd_pcm_stream_unlock_irq(substream); } for_each_pcm_substream(pcm, cidx, substream) snd_pcm_sync_stop(substream, false); pcm_call_notify(pcm, n_disconnect); for (cidx = 0; cidx < 2; cidx++) { if (pcm->streams[cidx].dev) snd_unregister_device(pcm->streams[cidx].dev); free_chmap(&pcm->streams[cidx]); } return 0; } #if IS_ENABLED(CONFIG_SND_PCM_OSS) /** * snd_pcm_notify - Add/remove the notify list * @notify: PCM notify list * @nfree: 0 = register, 1 = unregister * * This adds the given notifier to the global list so that the callback is * called for each registered PCM devices. This exists only for PCM OSS * emulation, so far. * * Return: zero if successful, or a negative error code */ int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree) { struct snd_pcm *pcm; if (snd_BUG_ON(!notify || !notify->n_register || !notify->n_unregister || !notify->n_disconnect)) return -EINVAL; guard(mutex)(®ister_mutex); if (nfree) { list_del(¬ify->list); list_for_each_entry(pcm, &snd_pcm_devices, list) notify->n_unregister(pcm); } else { list_add_tail(¬ify->list, &snd_pcm_notify_list); list_for_each_entry(pcm, &snd_pcm_devices, list) notify->n_register(pcm); } return 0; } EXPORT_SYMBOL(snd_pcm_notify); #endif /* CONFIG_SND_PCM_OSS */ #ifdef CONFIG_SND_PROC_FS /* * Info interface */ static void snd_pcm_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_pcm *pcm; guard(mutex)(®ister_mutex); list_for_each_entry(pcm, &snd_pcm_devices, list) { snd_iprintf(buffer, "%02i-%02i: %s : %s", pcm->card->number, pcm->device, pcm->id, pcm->name); if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) snd_iprintf(buffer, " : playback %i", pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream_count); if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) snd_iprintf(buffer, " : capture %i", pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream_count); snd_iprintf(buffer, "\n"); } } static struct snd_info_entry *snd_pcm_proc_entry; static void snd_pcm_proc_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "pcm", NULL); if (entry) { snd_info_set_text_ops(entry, NULL, snd_pcm_proc_read); if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } } snd_pcm_proc_entry = entry; } static void snd_pcm_proc_done(void) { snd_info_free_entry(snd_pcm_proc_entry); } #else /* !CONFIG_SND_PROC_FS */ #define snd_pcm_proc_init() #define snd_pcm_proc_done() #endif /* CONFIG_SND_PROC_FS */ /* * ENTRY functions */ static int __init alsa_pcm_init(void) { snd_ctl_register_ioctl(snd_pcm_control_ioctl); snd_ctl_register_ioctl_compat(snd_pcm_control_ioctl); snd_pcm_proc_init(); return 0; } static void __exit alsa_pcm_exit(void) { snd_ctl_unregister_ioctl(snd_pcm_control_ioctl); snd_ctl_unregister_ioctl_compat(snd_pcm_control_ioctl); snd_pcm_proc_done(); } module_init(alsa_pcm_init) module_exit(alsa_pcm_exit) |
| 89 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Internal header to deal with irq_desc->status which will be renamed * to irq_desc->settings. */ enum { _IRQ_DEFAULT_INIT_FLAGS = IRQ_DEFAULT_INIT_FLAGS, _IRQ_PER_CPU = IRQ_PER_CPU, _IRQ_LEVEL = IRQ_LEVEL, _IRQ_NOPROBE = IRQ_NOPROBE, _IRQ_NOREQUEST = IRQ_NOREQUEST, _IRQ_NOTHREAD = IRQ_NOTHREAD, _IRQ_NOAUTOEN = IRQ_NOAUTOEN, _IRQ_NO_BALANCING = IRQ_NO_BALANCING, _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, _IRQ_IS_POLLED = IRQ_IS_POLLED, _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, _IRQ_HIDDEN = IRQ_HIDDEN, _IRQ_NO_DEBUG = IRQ_NO_DEBUG, _IRQ_PROC_VALID = IRQ_RESERVED, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; #define IRQ_PER_CPU GOT_YOU_MORON #define IRQ_NO_BALANCING GOT_YOU_MORON #define IRQ_LEVEL GOT_YOU_MORON #define IRQ_NOPROBE GOT_YOU_MORON #define IRQ_NOREQUEST GOT_YOU_MORON #define IRQ_NOTHREAD GOT_YOU_MORON #define IRQ_NOAUTOEN GOT_YOU_MORON #define IRQ_NESTED_THREAD GOT_YOU_MORON #define IRQ_PER_CPU_DEVID GOT_YOU_MORON #define IRQ_IS_POLLED GOT_YOU_MORON #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON #define IRQ_HIDDEN GOT_YOU_MORON #define IRQ_NO_DEBUG GOT_YOU_MORON #define IRQ_RESERVED GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON static inline void irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) { desc->status_use_accessors &= ~(clr & _IRQF_MODIFY_MASK); desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); } static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU; } static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU_DEVID; } static inline void irq_settings_set_per_cpu(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_PER_CPU; } static inline void irq_settings_set_no_balancing(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NO_BALANCING; } static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NO_BALANCING; } static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc) { return desc->status_use_accessors & IRQ_TYPE_SENSE_MASK; } static inline void irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask) { desc->status_use_accessors &= ~IRQ_TYPE_SENSE_MASK; desc->status_use_accessors |= mask & IRQ_TYPE_SENSE_MASK; } static inline bool irq_settings_is_level(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_LEVEL; } static inline void irq_settings_clr_level(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_LEVEL; } static inline void irq_settings_set_level(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_LEVEL; } static inline bool irq_settings_can_request(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOREQUEST); } static inline void irq_settings_clr_norequest(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOREQUEST; } static inline void irq_settings_set_norequest(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOREQUEST; } static inline bool irq_settings_can_thread(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOTHREAD); } static inline void irq_settings_clr_nothread(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOTHREAD; } static inline void irq_settings_set_nothread(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOTHREAD; } static inline bool irq_settings_can_probe(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOPROBE); } static inline void irq_settings_clr_noprobe(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOPROBE; } static inline void irq_settings_set_noprobe(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOPROBE; } static inline bool irq_settings_can_autoenable(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOAUTOEN); } static inline bool irq_settings_is_nested_thread(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NESTED_THREAD; } static inline bool irq_settings_is_polled(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_IS_POLLED; } static inline bool irq_settings_disable_unlazy(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_DISABLE_UNLAZY; } static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY; } static inline bool irq_settings_is_hidden(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_HIDDEN; } static inline void irq_settings_set_no_debug(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NO_DEBUG; } static inline bool irq_settings_no_debug(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NO_DEBUG; } static inline bool irq_settings_proc_valid(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PROC_VALID; } static inline void irq_settings_update_proc_valid(struct irq_desc *desc, u32 set) { desc->status_use_accessors &= ~_IRQ_PROC_VALID; desc->status_use_accessors |= (set & _IRQ_PROC_VALID); } |
| 11 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 | /* IPv6-specific defines for netfilter. * (C)1998 Rusty Russell -- This code is GPL. * (C)1999 David Jeffery * this header was blatantly ripped from netfilter_ipv4.h * it's amazing what adding a bunch of 6s can do =8^) */ #ifndef __LINUX_IP6_NETFILTER_H #define __LINUX_IP6_NETFILTER_H #include <uapi/linux/netfilter_ipv6.h> #include <net/tcp.h> /* Check for an extension */ static inline int nf_ip6_ext_hdr(u8 nexthdr) { return (nexthdr == IPPROTO_HOPOPTS) || (nexthdr == IPPROTO_ROUTING) || (nexthdr == IPPROTO_FRAGMENT) || (nexthdr == IPPROTO_ESP) || (nexthdr == IPPROTO_AH) || (nexthdr == IPPROTO_NONE) || (nexthdr == IPPROTO_DSTOPTS); } /* Extra routing may needed on local out, as the QUEUE target never returns * control to the table. */ struct ip6_rt_info { struct in6_addr daddr; struct in6_addr saddr; u_int32_t mark; }; struct nf_queue_entry; struct nf_bridge_frag_data; #ifdef CONFIG_NETFILTER #include <net/addrconf.h> static inline int nf_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict) { #if IS_ENABLED(CONFIG_IPV6) return ipv6_chk_addr(net, addr, dev, strict); #else return 1; #endif } int __nf_ip6_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict) { #if IS_ENABLED(CONFIG_IPV6) return __nf_ip6_route(net, dst, fl, strict); #else return -EHOSTUNREACH; #endif } #include <net/netfilter/ipv6/nf_defrag_ipv6.h> int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, const struct nf_bridge_frag_data *data, struct sk_buff *)); static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, const struct nf_bridge_frag_data *data, struct sk_buff *)) { #if IS_ENABLED(CONFIG_IPV6) return br_ip6_fragment(net, sk, skb, data, output); #else return 1; #endif } int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) return ip6_route_me_harder(net, sk, skb); #else return -EHOSTUNREACH; #endif } static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp) { #if IS_ENABLED(CONFIG_IPV6) && IS_ENABLED(CONFIG_SYN_COOKIES) return __cookie_v6_init_sequence(iph, th, mssp); #endif return 0; } static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th) { #if IS_ENABLED(CONFIG_IPV6) && IS_ENABLED(CONFIG_SYN_COOKIES) return __cookie_v6_check(iph, th); #endif return 0; } __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); int nf_ip6_check_hbh_len(struct sk_buff *skb, u32 *plen); #endif /* CONFIG_NETFILTER */ #endif /*__LINUX_IP6_NETFILTER_H*/ |
| 1 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * RSA internal helpers * * Copyright (c) 2015, Intel Corporation * Authors: Tadeusz Struk <tadeusz.struk@intel.com> */ #ifndef _RSA_HELPER_ #define _RSA_HELPER_ #include <linux/types.h> #include <crypto/akcipher.h> /** * rsa_key - RSA key structure * @n : RSA modulus raw byte stream * @e : RSA public exponent raw byte stream * @d : RSA private exponent raw byte stream * @p : RSA prime factor p of n raw byte stream * @q : RSA prime factor q of n raw byte stream * @dp : RSA exponent d mod (p - 1) raw byte stream * @dq : RSA exponent d mod (q - 1) raw byte stream * @qinv : RSA CRT coefficient q^(-1) mod p raw byte stream * @n_sz : length in bytes of RSA modulus n * @e_sz : length in bytes of RSA public exponent * @d_sz : length in bytes of RSA private exponent * @p_sz : length in bytes of p field * @q_sz : length in bytes of q field * @dp_sz : length in bytes of dp field * @dq_sz : length in bytes of dq field * @qinv_sz : length in bytes of qinv field */ struct rsa_key { const u8 *n; const u8 *e; const u8 *d; const u8 *p; const u8 *q; const u8 *dp; const u8 *dq; const u8 *qinv; size_t n_sz; size_t e_sz; size_t d_sz; size_t p_sz; size_t q_sz; size_t dp_sz; size_t dq_sz; size_t qinv_sz; }; int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key, unsigned int key_len); int rsa_parse_priv_key(struct rsa_key *rsa_key, const void *key, unsigned int key_len); #define RSA_PUB (true) #define RSA_PRIV (false) static inline int rsa_set_key(struct crypto_akcipher *child, unsigned int *key_size, bool is_pubkey, const void *key, unsigned int keylen) { int err; *key_size = 0; if (is_pubkey) err = crypto_akcipher_set_pub_key(child, key, keylen); else err = crypto_akcipher_set_priv_key(child, key, keylen); if (err) return err; /* Find out new modulus size from rsa implementation */ err = crypto_akcipher_maxsize(child); if (err > PAGE_SIZE) return -ENOTSUPP; *key_size = err; return 0; } extern struct crypto_template rsa_pkcs1pad_tmpl; extern struct crypto_template rsassa_pkcs1_tmpl; #endif |
| 4322 4319 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. * * Copyright (C) 2004 Paul Mackerras, IBM Corp. */ #include <linux/bsearch.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> #include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) #else static inline unsigned long ex_to_insn(const struct exception_table_entry *x) { return (unsigned long)&x->insn + x->insn; } #endif #ifndef ARCH_HAS_RELATIVE_EXTABLE #define swap_ex NULL #else static void swap_ex(void *a, void *b, int size) { struct exception_table_entry *x = a, *y = b, tmp; int delta = b - a; tmp = *x; x->insn = y->insn + delta; y->insn = tmp.insn - delta; #ifdef swap_ex_entry_fixup swap_ex_entry_fixup(x, y, tmp, delta); #else x->fixup = y->fixup + delta; y->fixup = tmp.fixup - delta; #endif } #endif /* ARCH_HAS_RELATIVE_EXTABLE */ /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. * This is used both for the kernel exception table and for * the exception tables of modules that get loaded. */ static int cmp_ex_sort(const void *a, const void *b) { const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ if (ex_to_insn(x) > ex_to_insn(y)) return 1; if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), cmp_ex_sort, swap_ex); } #ifdef CONFIG_MODULES /* * If the exception table is sorted, any referring to the module init * will be at the beginning or the end. */ void trim_init_extable(struct module *m) { /*trim the beginning*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ static int cmp_ex_search(const void *key, const void *elt) { const struct exception_table_entry *_elt = elt; unsigned long _key = *(unsigned long *)key; /* avoid overflow */ if (_key > ex_to_insn(_elt)) return 1; if (_key < ex_to_insn(_elt)) return -1; return 0; } /* * Search one exception table for an entry corresponding to the * given instruction address, and return the address of the entry, * or NULL if none is found. * We use a binary search, and thus we assume that the table is * already sorted. */ const struct exception_table_entry * search_extable(const struct exception_table_entry *base, const size_t num, unsigned long value) { return bsearch(&value, base, num, sizeof(struct exception_table_entry), cmp_ex_search); } |
| 1 1 29 29 28 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 2015 Red Hat GmbH * Author: Florian Westphal <fw@strlen.de> */ #include <linux/module.h> #include <linux/static_key.h> #include <linux/hash.h> #include <linux/siphash.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #define NFT_TRACETYPE_LL_HSIZE 20 #define NFT_TRACETYPE_NETWORK_HSIZE 40 #define NFT_TRACETYPE_TRANSPORT_HSIZE 20 DEFINE_STATIC_KEY_FALSE(nft_trace_enabled); EXPORT_SYMBOL_GPL(nft_trace_enabled); static int trace_fill_header(struct sk_buff *nlskb, u16 type, const struct sk_buff *skb, int off, unsigned int len) { struct nlattr *nla; if (len == 0) return 0; nla = nla_reserve(nlskb, type, len); if (!nla || skb_copy_bits(skb, off, nla_data(nla), len)) return -1; return 0; } static int nf_trace_fill_ll_header(struct sk_buff *nlskb, const struct sk_buff *skb) { struct vlan_ethhdr veth; int off; BUILD_BUG_ON(sizeof(veth) > NFT_TRACETYPE_LL_HSIZE); off = skb_mac_header(skb) - skb->data; if (off != -ETH_HLEN) return -1; if (skb_copy_bits(skb, off, &veth, ETH_HLEN)) return -1; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); veth.h_vlan_encapsulated_proto = skb->protocol; return nla_put(nlskb, NFTA_TRACE_LL_HEADER, sizeof(veth), &veth); } static int nf_trace_fill_dev_info(struct sk_buff *nlskb, const struct net_device *indev, const struct net_device *outdev) { if (indev) { if (nla_put_be32(nlskb, NFTA_TRACE_IIF, htonl(indev->ifindex))) return -1; if (nla_put_be16(nlskb, NFTA_TRACE_IIFTYPE, htons(indev->type))) return -1; } if (outdev) { if (nla_put_be32(nlskb, NFTA_TRACE_OIF, htonl(outdev->ifindex))) return -1; if (nla_put_be16(nlskb, NFTA_TRACE_OIFTYPE, htons(outdev->type))) return -1; } return 0; } static int nf_trace_fill_ct_info(struct sk_buff *nlskb, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; u32 state; ct_hook = rcu_dereference(nf_ct_hook); if (!ct_hook) return 0; ct = nf_ct_get(skb, &ctinfo); if (!ct) { if (ctinfo != IP_CT_UNTRACKED) /* not seen by conntrack or invalid */ return 0; state = NF_CT_STATE_UNTRACKED_BIT; } else { state = NF_CT_STATE_BIT(ctinfo); } if (nla_put_be32(nlskb, NFTA_TRACE_CT_STATE, htonl(state))) return -1; if (ct) { u32 id = ct_hook->get_id(&ct->ct_general); u32 status = READ_ONCE(ct->status); u8 dir = CTINFO2DIR(ctinfo); if (nla_put_u8(nlskb, NFTA_TRACE_CT_DIRECTION, dir)) return -1; if (nla_put_be32(nlskb, NFTA_TRACE_CT_ID, (__force __be32)id)) return -1; /* Kernel implementation detail, withhold this from userspace for now */ status &= ~IPS_NAT_CLASH; if (status && nla_put_be32(nlskb, NFTA_TRACE_CT_STATUS, htonl(status))) return -1; } return 0; } static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, const struct nft_pktinfo *pkt) { const struct sk_buff *skb = pkt->skb; int off = skb_network_offset(skb); unsigned int len, nh_end; nh_end = pkt->flags & NFT_PKTINFO_L4PROTO ? nft_thoff(pkt) : skb->len; len = min_t(unsigned int, nh_end - skb_network_offset(skb), NFT_TRACETYPE_NETWORK_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) return -1; if (pkt->flags & NFT_PKTINFO_L4PROTO) { len = min_t(unsigned int, skb->len - nft_thoff(pkt), NFT_TRACETYPE_TRANSPORT_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, nft_thoff(pkt), len)) return -1; } if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_get(skb)) return nf_trace_fill_ll_header(nlskb, skb); off = skb_mac_header(skb) - skb->data; len = min_t(unsigned int, -off, NFT_TRACETYPE_LL_HSIZE); return trace_fill_header(nlskb, NFTA_TRACE_LL_HEADER, skb, off, len); } static int nf_trace_fill_rule_info(struct sk_buff *nlskb, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, const struct nft_traceinfo *info) { if (!rule || rule->is_last) return 0; /* a continue verdict with ->type == RETURN means that this is * an implicit return (end of chain reached). * * Since no rule matched, the ->rule pointer is invalid. */ if (info->type == NFT_TRACETYPE_RETURN && verdict->code == NFT_CONTINUE) return 0; return nla_put_be64(nlskb, NFTA_TRACE_RULE_HANDLE, cpu_to_be64(rule->handle), NFTA_TRACE_PAD); } static bool nft_trace_have_verdict_chain(const struct nft_verdict *verdict, struct nft_traceinfo *info) { switch (info->type) { case NFT_TRACETYPE_RETURN: case NFT_TRACETYPE_RULE: break; default: return false; } switch (verdict->code) { case NFT_JUMP: case NFT_GOTO: break; default: return false; } return true; } static const struct nft_chain *nft_trace_get_chain(const struct nft_rule_dp *rule, const struct nft_traceinfo *info) { const struct nft_rule_dp_last *last; if (!rule) return &info->basechain->chain; while (!rule->is_last) rule = nft_rule_next(rule); last = (const struct nft_rule_dp_last *)rule; if (unlikely(!last->chain)) { DEBUG_NET_WARN_ON_ONCE(1); return &info->basechain->chain; } return last->chain; } void nft_trace_notify(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, struct nft_traceinfo *info) { const struct nft_chain *chain; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int size; u32 mark = 0; u16 event; if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE)) return; chain = nft_trace_get_chain(rule, info); size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(strlen(chain->table->name)) + nla_total_size(strlen(chain->name)) + nla_total_size_64bit(sizeof(__be64)) + /* rule handle */ nla_total_size(sizeof(__be32)) + /* trace type */ nla_total_size(0) + /* VERDICT, nested */ nla_total_size(sizeof(u32)) + /* verdict code */ nla_total_size(sizeof(u32)) + /* ct id */ nla_total_size(sizeof(u8)) + /* ct direction */ nla_total_size(sizeof(u32)) + /* ct state */ nla_total_size(sizeof(u32)) + /* ct status */ nla_total_size(sizeof(u32)) + /* trace id */ nla_total_size(NFT_TRACETYPE_LL_HSIZE) + nla_total_size(NFT_TRACETYPE_NETWORK_HSIZE) + nla_total_size(NFT_TRACETYPE_TRANSPORT_HSIZE) + nla_total_size(sizeof(u32)) + /* iif */ nla_total_size(sizeof(__be16)) + /* iiftype */ nla_total_size(sizeof(u32)) + /* oif */ nla_total_size(sizeof(__be16)) + /* oiftype */ nla_total_size(sizeof(u32)) + /* mark */ nla_total_size(sizeof(u32)) + /* nfproto */ nla_total_size(sizeof(u32)); /* policy */ if (nft_trace_have_verdict_chain(verdict, info)) size += nla_total_size(strlen(verdict->chain->name)); /* jump target */ skb = nlmsg_new(size, GFP_ATOMIC); if (!skb) return; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_TRACE); nlh = nfnl_msg_put(skb, 0, 0, event, 0, info->basechain->type->family, NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(nft_pf(pkt)))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type))) goto nla_put_failure; if (nla_put_u32(skb, NFTA_TRACE_ID, info->skbid)) goto nla_put_failure; if (nla_put_string(skb, NFTA_TRACE_CHAIN, chain->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_TRACE_TABLE, chain->table->name)) goto nla_put_failure; if (nf_trace_fill_rule_info(skb, verdict, rule, info)) goto nla_put_failure; switch (info->type) { case NFT_TRACETYPE_UNSPEC: case __NFT_TRACETYPE_MAX: break; case NFT_TRACETYPE_RETURN: case NFT_TRACETYPE_RULE: { unsigned int v; if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, verdict)) goto nla_put_failure; /* pkt->skb undefined iff NF_STOLEN, disable dump */ v = verdict->code & NF_VERDICT_MASK; if (v == NF_STOLEN) info->packet_dumped = true; else mark = pkt->skb->mark; break; } case NFT_TRACETYPE_POLICY: mark = pkt->skb->mark; if (nla_put_be32(skb, NFTA_TRACE_POLICY, htonl(info->basechain->policy))) goto nla_put_failure; break; } if (mark && nla_put_be32(skb, NFTA_TRACE_MARK, htonl(mark))) goto nla_put_failure; if (!info->packet_dumped) { if (nf_trace_fill_dev_info(skb, nft_in(pkt), nft_out(pkt))) goto nla_put_failure; if (nf_trace_fill_pkt_info(skb, pkt)) goto nla_put_failure; if (nf_trace_fill_ct_info(skb, pkt->skb)) goto nla_put_failure; info->packet_dumped = true; } nlmsg_end(skb, nlh); nfnetlink_send(skb, nft_net(pkt), 0, NFNLGRP_NFTRACE, 0, GFP_ATOMIC); return; nla_put_failure: DEBUG_NET_WARN_ON_ONCE(1); kfree_skb(skb); } void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, const struct nft_chain *chain) { static siphash_key_t trace_key __read_mostly; struct sk_buff *skb = pkt->skb; info->basechain = nft_base_chain(chain); info->trace = true; info->nf_trace = pkt->skb->nf_trace; info->packet_dumped = false; net_get_random_once(&trace_key, sizeof(trace_key)); info->skbid = (u32)siphash_3u32(hash32_ptr(skb), skb_get_hash_net(nft_net(pkt), skb), skb->skb_iif, &trace_key); } |
| 4 10 10 10 3 6 4 10 10 4 2 1 1 12 1 1 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 | // SPDX-License-Identifier: GPL-2.0-only /* * vsock sock_diag(7) module * * Copyright (C) 2017 Red Hat, Inc. * Author: Stefan Hajnoczi <stefanha@redhat.com> */ #include <linux/module.h> #include <linux/sock_diag.h> #include <linux/vm_sockets_diag.h> #include <net/af_vsock.h> static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u32 flags) { struct vsock_sock *vsk = vsock_sk(sk); struct vsock_diag_msg *rep; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), flags); if (!nlh) return -EMSGSIZE; rep = nlmsg_data(nlh); rep->vdiag_family = AF_VSOCK; /* Lock order dictates that sk_lock is acquired before * vsock_table_lock, so we cannot lock here. Simply don't take * sk_lock; sk is guaranteed to stay alive since vsock_table_lock is * held. */ rep->vdiag_type = sk->sk_type; rep->vdiag_state = sk->sk_state; rep->vdiag_shutdown = sk->sk_shutdown; rep->vdiag_src_cid = vsk->local_addr.svm_cid; rep->vdiag_src_port = vsk->local_addr.svm_port; rep->vdiag_dst_cid = vsk->remote_addr.svm_cid; rep->vdiag_dst_port = vsk->remote_addr.svm_port; rep->vdiag_ino = sock_i_ino(sk); sock_diag_save_cookie(sk, rep->vdiag_cookie); return 0; } static int vsock_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct vsock_diag_req *req; struct vsock_sock *vsk; unsigned int bucket; unsigned int last_i; unsigned int table; struct net *net; unsigned int i; req = nlmsg_data(cb->nlh); net = sock_net(skb->sk); /* State saved between calls: */ table = cb->args[0]; bucket = cb->args[1]; i = last_i = cb->args[2]; /* TODO VMCI pending sockets? */ spin_lock_bh(&vsock_table_lock); /* Bind table (locally created sockets) */ if (table == 0) { while (bucket < ARRAY_SIZE(vsock_bind_table)) { struct list_head *head = &vsock_bind_table[bucket]; i = 0; list_for_each_entry(vsk, head, bound_table) { struct sock *sk = sk_vsock(vsk); if (!net_eq(sock_net(sk), net)) continue; if (i < last_i) goto next_bind; if (!(req->vdiag_states & (1 << sk->sk_state))) goto next_bind; if (sk_diag_fill(sk, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) goto done; next_bind: i++; } last_i = 0; bucket++; } table++; bucket = 0; } /* Connected table (accepted connections) */ while (bucket < ARRAY_SIZE(vsock_connected_table)) { struct list_head *head = &vsock_connected_table[bucket]; i = 0; list_for_each_entry(vsk, head, connected_table) { struct sock *sk = sk_vsock(vsk); /* Skip sockets we've already seen above */ if (__vsock_in_bound_table(vsk)) continue; if (!net_eq(sock_net(sk), net)) continue; if (i < last_i) goto next_connected; if (!(req->vdiag_states & (1 << sk->sk_state))) goto next_connected; if (sk_diag_fill(sk, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) goto done; next_connected: i++; } last_i = 0; bucket++; } done: spin_unlock_bh(&vsock_table_lock); cb->args[0] = table; cb->args[1] = bucket; cb->args[2] = i; return skb->len; } static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct vsock_diag_req); struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = vsock_diag_dump, }; return netlink_dump_start(net->diag_nlsk, skb, h, &c); } return -EOPNOTSUPP; } static const struct sock_diag_handler vsock_diag_handler = { .owner = THIS_MODULE, .family = AF_VSOCK, .dump = vsock_diag_handler_dump, }; static int __init vsock_diag_init(void) { return sock_diag_register(&vsock_diag_handler); } static void __exit vsock_diag_exit(void) { sock_diag_unregister(&vsock_diag_handler); } module_init(vsock_diag_init); module_exit(vsock_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VMware Virtual Sockets monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 40 /* AF_VSOCK */); |
| 9 5 5 5 5 5 3 4 6 3 6 3 8 1 7 2 2 1 1 1 1 1 19 5 16 4 4 4 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/phy.h> #include <linux/ethtool_netlink.h> #include <net/netdev_lock.h> #include "common.h" #include "netlink.h" /* 802.3 standard allows 100 meters for BaseT cables. However longer * cables might work, depending on the quality of the cables and the * PHY. So allow testing for up to 150 meters. */ #define MAX_CABLE_LENGTH_CM (150 * 100) const struct nla_policy ethnl_cable_test_act_policy[] = { [ETHTOOL_A_CABLE_TEST_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int ethnl_cable_test_started(struct phy_device *phydev, u8 cmd) { struct sk_buff *skb; int err = -ENOMEM; void *ehdr; skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto out; ehdr = ethnl_bcastmsg_put(skb, cmd); if (!ehdr) { err = -EMSGSIZE; goto out; } err = ethnl_fill_reply_header(skb, phydev->attached_dev, ETHTOOL_A_CABLE_TEST_NTF_HEADER); if (err) goto out; err = nla_put_u8(skb, ETHTOOL_A_CABLE_TEST_NTF_STATUS, ETHTOOL_A_CABLE_TEST_NTF_STATUS_STARTED); if (err) goto out; genlmsg_end(skb, ehdr); return ethnl_multicast(skb, phydev->attached_dev); out: nlmsg_free(skb); phydev_err(phydev, "%s: Error %pe\n", __func__, ERR_PTR(err)); return err; } int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) { struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_device *phydev; struct net_device *dev; int ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_CABLE_TEST_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; netdev_lock_ops_compat(dev); phydev = ethnl_req_get_phydev(&req_info, tb, ETHTOOL_A_CABLE_TEST_HEADER, info->extack); if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out_unlock; } ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test) { ret = -EOPNOTSUPP; goto out_unlock; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out_unlock; ret = ops->start_cable_test(phydev, info->extack); ethnl_ops_complete(dev); if (!ret) ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_NTF); out_unlock: netdev_unlock_ops_compat(dev); ethnl_parse_header_dev_put(&req_info); return ret; } int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) { int err = -ENOMEM; /* One TDR sample occupies 20 bytes. For a 150 meter cable, * with four pairs, around 12K is needed. */ phydev->skb = genlmsg_new(SZ_16K, GFP_KERNEL); if (!phydev->skb) goto out; phydev->ehdr = ethnl_bcastmsg_put(phydev->skb, cmd); if (!phydev->ehdr) { err = -EMSGSIZE; goto out; } err = ethnl_fill_reply_header(phydev->skb, phydev->attached_dev, ETHTOOL_A_CABLE_TEST_NTF_HEADER); if (err) goto out; err = nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_TEST_NTF_STATUS, ETHTOOL_A_CABLE_TEST_NTF_STATUS_COMPLETED); if (err) goto out; phydev->nest = nla_nest_start(phydev->skb, ETHTOOL_A_CABLE_TEST_NTF_NEST); if (!phydev->nest) { err = -EMSGSIZE; goto out; } return 0; out: nlmsg_free(phydev->skb); phydev->skb = NULL; return err; } EXPORT_SYMBOL_GPL(ethnl_cable_test_alloc); void ethnl_cable_test_free(struct phy_device *phydev) { nlmsg_free(phydev->skb); phydev->skb = NULL; } EXPORT_SYMBOL_GPL(ethnl_cable_test_free); void ethnl_cable_test_finished(struct phy_device *phydev) { nla_nest_end(phydev->skb, phydev->nest); genlmsg_end(phydev->skb, phydev->ehdr); ethnl_multicast(phydev->skb, phydev->attached_dev); } EXPORT_SYMBOL_GPL(ethnl_cable_test_finished); int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, u8 result, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; nest = nla_nest_start(phydev->skb, ETHTOOL_A_CABLE_NEST_RESULT); if (!nest) return -EMSGSIZE; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_RESULT_PAIR, pair)) goto err; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_RESULT_CODE, result)) goto err; if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_RESULT_SRC, src)) goto err; } nla_nest_end(phydev->skb, nest); return 0; err: nla_nest_cancel(phydev->skb, nest); return ret; } EXPORT_SYMBOL_GPL(ethnl_cable_test_result_with_src); int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, u32 cm, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; nest = nla_nest_start(phydev->skb, ETHTOOL_A_CABLE_NEST_FAULT_LENGTH); if (!nest) return -EMSGSIZE; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR, pair)) goto err; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_CM, cm)) goto err; if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, src)) goto err; } nla_nest_end(phydev->skb, nest); return 0; err: nla_nest_cancel(phydev->skb, nest); return ret; } EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length_with_src); static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .type = NLA_U32 }, [ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST] = { .type = NLA_U32 }, [ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP] = { .type = NLA_U32 }, [ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR] = { .type = NLA_U8 }, }; const struct nla_policy ethnl_cable_test_tdr_act_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .type = NLA_NESTED }, }; /* CABLE_TEST_TDR_ACT */ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, struct genl_info *info, struct phy_tdr_config *cfg) { struct nlattr *tb[ARRAY_SIZE(cable_test_tdr_act_cfg_policy)]; int ret; cfg->first = 100; cfg->step = 100; cfg->last = MAX_CABLE_LENGTH_CM; cfg->pair = PHY_PAIR_ALL; if (!nest) return 0; ret = nla_parse_nested(tb, ARRAY_SIZE(cable_test_tdr_act_cfg_policy) - 1, nest, cable_test_tdr_act_cfg_policy, info->extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]) cfg->first = nla_get_u32( tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]); if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]) cfg->last = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]); if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]) cfg->step = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]); if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]) { cfg->pair = nla_get_u8(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]); if (cfg->pair > ETHTOOL_A_CABLE_PAIR_D) { NL_SET_ERR_MSG_ATTR( info->extack, tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR], "invalid pair parameter"); return -EINVAL; } } if (cfg->first > MAX_CABLE_LENGTH_CM) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST], "invalid first parameter"); return -EINVAL; } if (cfg->last > MAX_CABLE_LENGTH_CM) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST], "invalid last parameter"); return -EINVAL; } if (cfg->first > cfg->last) { NL_SET_ERR_MSG(info->extack, "invalid first/last parameter"); return -EINVAL; } if (!cfg->step) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP], "invalid step parameter"); return -EINVAL; } if (cfg->step > (cfg->last - cfg->first)) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP], "step parameter too big"); return -EINVAL; } return 0; } int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) { struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_device *phydev; struct phy_tdr_config cfg; struct net_device *dev; int ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; ret = ethnl_act_cable_test_tdr_cfg(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG], info, &cfg); if (ret) goto out_dev_put; netdev_lock_ops_compat(dev); phydev = ethnl_req_get_phydev(&req_info, tb, ETHTOOL_A_CABLE_TEST_TDR_HEADER, info->extack); if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out_unlock; } ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test_tdr) { ret = -EOPNOTSUPP; goto out_unlock; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out_unlock; ret = ops->start_cable_test_tdr(phydev, info->extack, &cfg); ethnl_ops_complete(dev); if (!ret) ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_TDR_NTF); out_unlock: netdev_unlock_ops_compat(dev); out_dev_put: ethnl_parse_header_dev_put(&req_info); return ret; } int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV) { struct nlattr *nest; int ret = -EMSGSIZE; nest = nla_nest_start(phydev->skb, ETHTOOL_A_CABLE_TDR_NEST_AMPLITUDE); if (!nest) return -EMSGSIZE; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_AMPLITUDE_PAIR, pair)) goto err; if (nla_put_u16(phydev->skb, ETHTOOL_A_CABLE_AMPLITUDE_mV, mV)) goto err; nla_nest_end(phydev->skb, nest); return 0; err: nla_nest_cancel(phydev->skb, nest); return ret; } EXPORT_SYMBOL_GPL(ethnl_cable_test_amplitude); int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV) { struct nlattr *nest; int ret = -EMSGSIZE; nest = nla_nest_start(phydev->skb, ETHTOOL_A_CABLE_TDR_NEST_PULSE); if (!nest) return -EMSGSIZE; if (nla_put_u16(phydev->skb, ETHTOOL_A_CABLE_PULSE_mV, mV)) goto err; nla_nest_end(phydev->skb, nest); return 0; err: nla_nest_cancel(phydev->skb, nest); return ret; } EXPORT_SYMBOL_GPL(ethnl_cable_test_pulse); int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last, u32 step) { struct nlattr *nest; int ret = -EMSGSIZE; nest = nla_nest_start(phydev->skb, ETHTOOL_A_CABLE_TDR_NEST_STEP); if (!nest) return -EMSGSIZE; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_STEP_FIRST_DISTANCE, first)) goto err; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_STEP_LAST_DISTANCE, last)) goto err; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_STEP_STEP_DISTANCE, step)) goto err; nla_nest_end(phydev->skb, nest); return 0; err: nla_nest_cancel(phydev->skb, nest); return ret; } EXPORT_SYMBOL_GPL(ethnl_cable_test_step); |
| 26 13 13 13 13 26 13 13 13 30 11 11 30 11 26 11 30 5 26 18 5 5 11 5 30 5 10 11 23 1 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /******************************************************************************* * * Module Name: utdelete - object deletion and reference count utilities * ******************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #include "acinterp.h" #include "acnamesp.h" #include "acevents.h" #define _COMPONENT ACPI_UTILITIES ACPI_MODULE_NAME("utdelete") /* Local prototypes */ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object); static void acpi_ut_update_ref_count(union acpi_operand_object *object, u32 action); /******************************************************************************* * * FUNCTION: acpi_ut_delete_internal_obj * * PARAMETERS: object - Object to be deleted * * RETURN: None * * DESCRIPTION: Low level object deletion, after reference counts have been * updated (All reference counts, including sub-objects!) * ******************************************************************************/ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object) { void *obj_pointer = NULL; union acpi_operand_object *handler_desc; union acpi_operand_object *second_desc; union acpi_operand_object *next_desc; union acpi_operand_object *start_desc; union acpi_operand_object **last_obj_ptr; ACPI_FUNCTION_TRACE_PTR(ut_delete_internal_obj, object); if (!object) { return_VOID; } /* * Must delete or free any pointers within the object that are not * actual ACPI objects (for example, a raw buffer pointer). */ switch (object->common.type) { case ACPI_TYPE_STRING: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "**** String %p, ptr %p\n", object, object->string.pointer)); /* Free the actual string buffer */ if (!(object->common.flags & AOPOBJ_STATIC_POINTER)) { /* But only if it is NOT a pointer into an ACPI table */ obj_pointer = object->string.pointer; } break; case ACPI_TYPE_BUFFER: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "**** Buffer %p, ptr %p\n", object, object->buffer.pointer)); /* Free the actual buffer */ if (!(object->common.flags & AOPOBJ_STATIC_POINTER)) { /* But only if it is NOT a pointer into an ACPI table */ obj_pointer = object->buffer.pointer; } break; case ACPI_TYPE_PACKAGE: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, " **** Package of count %X\n", object->package.count)); /* * Elements of the package are not handled here, they are deleted * separately */ /* Free the (variable length) element pointer array */ obj_pointer = object->package.elements; break; /* * These objects have a possible list of notify handlers. * Device object also may have a GPE block. */ case ACPI_TYPE_DEVICE: if (object->device.gpe_block) { (void)acpi_ev_delete_gpe_block(object->device. gpe_block); } ACPI_FALLTHROUGH; case ACPI_TYPE_PROCESSOR: case ACPI_TYPE_THERMAL: /* Walk the address handler list for this object */ handler_desc = object->common_notify.handler; while (handler_desc) { next_desc = handler_desc->address_space.next; acpi_ut_remove_reference(handler_desc); handler_desc = next_desc; } break; case ACPI_TYPE_MUTEX: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "***** Mutex %p, OS Mutex %p\n", object, object->mutex.os_mutex)); if (object == acpi_gbl_global_lock_mutex) { /* Global Lock has extra semaphore */ (void) acpi_os_delete_semaphore (acpi_gbl_global_lock_semaphore); acpi_gbl_global_lock_semaphore = ACPI_SEMAPHORE_NULL; acpi_os_delete_mutex(object->mutex.os_mutex); acpi_gbl_global_lock_mutex = NULL; } else { acpi_ex_unlink_mutex(object); acpi_os_delete_mutex(object->mutex.os_mutex); } break; case ACPI_TYPE_EVENT: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "***** Event %p, OS Semaphore %p\n", object, object->event.os_semaphore)); (void)acpi_os_delete_semaphore(object->event.os_semaphore); object->event.os_semaphore = ACPI_SEMAPHORE_NULL; break; case ACPI_TYPE_METHOD: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "***** Method %p\n", object)); /* Delete the method mutex if it exists */ if (object->method.mutex) { acpi_os_delete_mutex(object->method.mutex->mutex. os_mutex); acpi_ut_delete_object_desc(object->method.mutex); object->method.mutex = NULL; } if (object->method.node) { object->method.node = NULL; } break; case ACPI_TYPE_REGION: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "***** Region %p\n", object)); /* * Update address_range list. However, only permanent regions * are installed in this list. (Not created within a method) */ if (!(object->region.node->flags & ANOBJ_TEMPORARY)) { acpi_ut_remove_address_range(object->region.space_id, object->region.node); } second_desc = acpi_ns_get_secondary_object(object); if (second_desc) { /* * Free the region_context if and only if the handler is one of the * default handlers -- and therefore, we created the context object * locally, it was not created by an external caller. */ handler_desc = object->region.handler; if (handler_desc) { next_desc = handler_desc->address_space.region_list; start_desc = next_desc; last_obj_ptr = &handler_desc->address_space.region_list; /* Remove the region object from the handler list */ while (next_desc) { if (next_desc == object) { *last_obj_ptr = next_desc->region.next; break; } /* Walk the linked list of handlers */ last_obj_ptr = &next_desc->region.next; next_desc = next_desc->region.next; /* Prevent infinite loop if list is corrupted */ if (next_desc == start_desc) { ACPI_ERROR((AE_INFO, "Circular region list in address handler object %p", handler_desc)); return_VOID; } } if (handler_desc->address_space.handler_flags & ACPI_ADDR_HANDLER_DEFAULT_INSTALLED) { /* Deactivate region and free region context */ if (handler_desc->address_space.setup) { (void)handler_desc-> address_space.setup(object, ACPI_REGION_DEACTIVATE, handler_desc-> address_space. context, &second_desc-> extra. region_context); } } acpi_ut_remove_reference(handler_desc); } /* Now we can free the Extra object */ acpi_ut_delete_object_desc(second_desc); } if (object->field.internal_pcc_buffer) { ACPI_FREE(object->field.internal_pcc_buffer); } break; case ACPI_TYPE_BUFFER_FIELD: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "***** Buffer Field %p\n", object)); second_desc = acpi_ns_get_secondary_object(object); if (second_desc) { acpi_ut_delete_object_desc(second_desc); } break; case ACPI_TYPE_LOCAL_BANK_FIELD: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "***** Bank Field %p\n", object)); second_desc = acpi_ns_get_secondary_object(object); if (second_desc) { acpi_ut_delete_object_desc(second_desc); } break; case ACPI_TYPE_LOCAL_ADDRESS_HANDLER: ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "***** Address handler %p\n", object)); acpi_os_delete_mutex(object->address_space.context_mutex); break; default: break; } /* Free any allocated memory (pointer within the object) found above */ if (obj_pointer) { ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "Deleting Object Subptr %p\n", obj_pointer)); ACPI_FREE(obj_pointer); } /* Now the object can be safely deleted */ ACPI_DEBUG_PRINT_RAW((ACPI_DB_ALLOCATIONS, "%s: Deleting Object %p [%s]\n", ACPI_GET_FUNCTION_NAME, object, acpi_ut_get_object_type_name(object))); acpi_ut_delete_object_desc(object); return_VOID; } /******************************************************************************* * * FUNCTION: acpi_ut_delete_internal_object_list * * PARAMETERS: obj_list - Pointer to the list to be deleted * * RETURN: None * * DESCRIPTION: This function deletes an internal object list, including both * simple objects and package objects * ******************************************************************************/ void acpi_ut_delete_internal_object_list(union acpi_operand_object **obj_list) { union acpi_operand_object **internal_obj; ACPI_FUNCTION_ENTRY(); /* Walk the null-terminated internal list */ for (internal_obj = obj_list; *internal_obj; internal_obj++) { acpi_ut_remove_reference(*internal_obj); } /* Free the combined parameter pointer list and object array */ ACPI_FREE(obj_list); return; } /******************************************************************************* * * FUNCTION: acpi_ut_update_ref_count * * PARAMETERS: object - Object whose ref count is to be updated * action - What to do (REF_INCREMENT or REF_DECREMENT) * * RETURN: None. Sets new reference count within the object * * DESCRIPTION: Modify the reference count for an internal acpi object * ******************************************************************************/ static void acpi_ut_update_ref_count(union acpi_operand_object *object, u32 action) { u16 original_count; u16 new_count = 0; acpi_cpu_flags lock_flags; char *message; ACPI_FUNCTION_NAME(ut_update_ref_count); if (!object) { return; } /* * Always get the reference count lock. Note: Interpreter and/or * Namespace is not always locked when this function is called. */ lock_flags = acpi_os_acquire_lock(acpi_gbl_reference_count_lock); original_count = object->common.reference_count; /* Perform the reference count action (increment, decrement) */ switch (action) { case REF_INCREMENT: new_count = original_count + 1; object->common.reference_count = new_count; acpi_os_release_lock(acpi_gbl_reference_count_lock, lock_flags); /* The current reference count should never be zero here */ if (!original_count) { ACPI_WARNING((AE_INFO, "Obj %p, Reference Count was zero before increment\n", object)); } ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "Obj %p Type %.2X [%s] Refs %.2X [Incremented]\n", object, object->common.type, acpi_ut_get_object_type_name(object), new_count)); message = "Increment"; break; case REF_DECREMENT: /* The current reference count must be non-zero */ if (original_count) { new_count = original_count - 1; object->common.reference_count = new_count; } acpi_os_release_lock(acpi_gbl_reference_count_lock, lock_flags); if (!original_count) { ACPI_WARNING((AE_INFO, "Obj %p, Reference Count is already zero, cannot decrement\n", object)); return; } ACPI_DEBUG_PRINT_RAW((ACPI_DB_ALLOCATIONS, "%s: Obj %p Type %.2X Refs %.2X [Decremented]\n", ACPI_GET_FUNCTION_NAME, object, object->common.type, new_count)); /* Actually delete the object on a reference count of zero */ if (new_count == 0) { acpi_ut_delete_internal_obj(object); } message = "Decrement"; break; default: acpi_os_release_lock(acpi_gbl_reference_count_lock, lock_flags); ACPI_ERROR((AE_INFO, "Unknown Reference Count action (0x%X)", action)); return; } /* * Sanity check the reference count, for debug purposes only. * (A deleted object will have a huge reference count) */ if (new_count > ACPI_MAX_REFERENCE_COUNT) { ACPI_WARNING((AE_INFO, "Large Reference Count (0x%X) in object %p, Type=0x%.2X Operation=%s", new_count, object, object->common.type, message)); } } /******************************************************************************* * * FUNCTION: acpi_ut_update_object_reference * * PARAMETERS: object - Increment or decrement the ref count for * this object and all sub-objects * action - Either REF_INCREMENT or REF_DECREMENT * * RETURN: Status * * DESCRIPTION: Increment or decrement the object reference count * * Object references are incremented when: * 1) An object is attached to a Node (namespace object) * 2) An object is copied (all subobjects must be incremented) * * Object references are decremented when: * 1) An object is detached from an Node * ******************************************************************************/ acpi_status acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action) { acpi_status status = AE_OK; union acpi_generic_state *state_list = NULL; union acpi_operand_object *next_object = NULL; union acpi_operand_object *prev_object; union acpi_generic_state *state; u32 i; ACPI_FUNCTION_NAME(ut_update_object_reference); while (object) { /* Make sure that this isn't a namespace handle */ if (ACPI_GET_DESCRIPTOR_TYPE(object) == ACPI_DESC_TYPE_NAMED) { ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "Object %p is NS handle\n", object)); return (AE_OK); } /* * All sub-objects must have their reference count updated * also. Different object types have different subobjects. */ switch (object->common.type) { case ACPI_TYPE_DEVICE: case ACPI_TYPE_PROCESSOR: case ACPI_TYPE_POWER: case ACPI_TYPE_THERMAL: /* * Update the notify objects for these types (if present) * Two lists, system and device notify handlers. */ for (i = 0; i < ACPI_NUM_NOTIFY_TYPES; i++) { prev_object = object->common_notify.notify_list[i]; while (prev_object) { next_object = prev_object->notify.next[i]; acpi_ut_update_ref_count(prev_object, action); prev_object = next_object; } } break; case ACPI_TYPE_PACKAGE: /* * We must update all the sub-objects of the package, * each of whom may have their own sub-objects. */ for (i = 0; i < object->package.count; i++) { /* * Null package elements are legal and can be simply * ignored. */ next_object = object->package.elements[i]; if (!next_object) { continue; } switch (next_object->common.type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_BUFFER: /* * For these very simple sub-objects, we can just * update the reference count here and continue. * Greatly increases performance of this operation. */ acpi_ut_update_ref_count(next_object, action); break; default: /* * For complex sub-objects, push them onto the stack * for later processing (this eliminates recursion.) */ status = acpi_ut_create_update_state_and_push (next_object, action, &state_list); if (ACPI_FAILURE(status)) { goto error_exit; } break; } } next_object = NULL; break; case ACPI_TYPE_BUFFER_FIELD: next_object = object->buffer_field.buffer_obj; break; case ACPI_TYPE_LOCAL_BANK_FIELD: next_object = object->bank_field.bank_obj; status = acpi_ut_create_update_state_and_push(object-> bank_field. region_obj, action, &state_list); if (ACPI_FAILURE(status)) { goto error_exit; } break; case ACPI_TYPE_LOCAL_INDEX_FIELD: next_object = object->index_field.index_obj; status = acpi_ut_create_update_state_and_push(object-> index_field. data_obj, action, &state_list); if (ACPI_FAILURE(status)) { goto error_exit; } break; case ACPI_TYPE_LOCAL_REFERENCE: /* * The target of an Index (a package, string, or buffer) or a named * reference must track changes to the ref count of the index or * target object. */ if ((object->reference.class == ACPI_REFCLASS_INDEX) || (object->reference.class == ACPI_REFCLASS_NAME)) { next_object = object->reference.object; } break; case ACPI_TYPE_LOCAL_REGION_FIELD: case ACPI_TYPE_REGION: default: break; /* No subobjects for all other types */ } /* * Now we can update the count in the main object. This can only * happen after we update the sub-objects in case this causes the * main object to be deleted. */ acpi_ut_update_ref_count(object, action); object = NULL; /* Move on to the next object to be updated */ if (next_object) { object = next_object; next_object = NULL; } else if (state_list) { state = acpi_ut_pop_generic_state(&state_list); object = state->update.object; acpi_ut_delete_generic_state(state); } } return (AE_OK); error_exit: ACPI_EXCEPTION((AE_INFO, status, "Could not update object reference count")); /* Free any stacked Update State objects */ while (state_list) { state = acpi_ut_pop_generic_state(&state_list); acpi_ut_delete_generic_state(state); } return (status); } /******************************************************************************* * * FUNCTION: acpi_ut_add_reference * * PARAMETERS: object - Object whose reference count is to be * incremented * * RETURN: None * * DESCRIPTION: Add one reference to an ACPI object * ******************************************************************************/ void acpi_ut_add_reference(union acpi_operand_object *object) { ACPI_FUNCTION_NAME(ut_add_reference); /* Ensure that we have a valid object */ if (!acpi_ut_valid_internal_object(object)) { return; } ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS, "Obj %p Current Refs=%X [To Be Incremented]\n", object, object->common.reference_count)); /* Increment the reference count */ (void)acpi_ut_update_object_reference(object, REF_INCREMENT); return; } /******************************************************************************* * * FUNCTION: acpi_ut_remove_reference * * PARAMETERS: object - Object whose ref count will be decremented * * RETURN: None * * DESCRIPTION: Decrement the reference count of an ACPI internal object * ******************************************************************************/ void acpi_ut_remove_reference(union acpi_operand_object *object) { ACPI_FUNCTION_NAME(ut_remove_reference); /* * Allow a NULL pointer to be passed in, just ignore it. This saves * each caller from having to check. Also, ignore NS nodes. */ if (!object || (ACPI_GET_DESCRIPTOR_TYPE(object) == ACPI_DESC_TYPE_NAMED)) { return; } /* Ensure that we have a valid object */ if (!acpi_ut_valid_internal_object(object)) { return; } ACPI_DEBUG_PRINT_RAW((ACPI_DB_ALLOCATIONS, "%s: Obj %p Current Refs=%X [To Be Decremented]\n", ACPI_GET_FUNCTION_NAME, object, object->common.reference_count)); /* * Decrement the reference count, and only actually delete the object * if the reference count becomes 0. (Must also decrement the ref count * of all subobjects!) */ (void)acpi_ut_update_object_reference(object, REF_DECREMENT); return; } |
| 81 1 82 83 8 6 6 6 6 6 3 4 78 1 1 83 82 1 48 36 42 82 82 82 5 78 3 3 2 3 78 73 4 72 1 12 87 2 2 6 1 78 1 12 12 12 12 261 262 121 123 122 71 1 312 312 12 2 1 314 1 1 314 313 396 41 7 7 352 120 242 41 35 253 265 206 13 208 193 19 197 11 7 4 315 312 209 209 26 11 7 12 2 28 29 1 10 28 4 10 24 5 16 8 23 17 1 23 95 7 3 11 76 3 78 18 9 9 9 182 182 103 49 32 206 196 23 4 36 172 61 160 160 37 183 121 15 4 3 109 2 1 106 98 11 3 2 86 3 2 50 32 81 15 5 3 2 6 6 61 57 1 5 5 5 5 6 30 30 97 6 97 1 7 103 7 2 95 23 2 75 84 20 35 296 4 42 1 4 106 75 26 26 10 13 111 316 37 1 1 314 314 300 332 1 17 45 318 3 273 43 320 22 8 1 6 2 4 3 7 49 50 22 2 29 30 24 24 23 33 32 22 9 2 1 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * An async IO implementation for Linux * Written by Benjamin LaHaise <bcrl@kvack.org> * * Implements an efficient asynchronous io interface. * * Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved. * Copyright 2018 Christoph Hellwig. * * See ../COPYING for licensing terms. */ #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/aio_abi.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/backing-dev.h> #include <linux/refcount.h> #include <linux/uio.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/aio.h> #include <linux/highmem.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/eventfd.h> #include <linux/blkdev.h> #include <linux/compat.h> #include <linux/migrate.h> #include <linux/ramfs.h> #include <linux/percpu-refcount.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> #include <linux/nospec.h> #include "internal.h" #define KIOCB_KEY 0 #define AIO_RING_MAGIC 0xa10a10a1 #define AIO_RING_COMPAT_FEATURES 1 #define AIO_RING_INCOMPAT_FEATURES 0 struct aio_ring { unsigned id; /* kernel internal index number */ unsigned nr; /* number of io_events */ unsigned head; /* Written to by userland or under ring_lock * mutex by aio_read_events_ring(). */ unsigned tail; unsigned magic; unsigned compat_features; unsigned incompat_features; unsigned header_length; /* size of aio_ring */ struct io_event io_events[]; }; /* 128 bytes + ring size */ /* * Plugging is meant to work with larger batches of IOs. If we don't * have more than the below, then don't bother setting up a plug. */ #define AIO_PLUG_THRESHOLD 2 #define AIO_RING_PAGES 8 struct kioctx_table { struct rcu_head rcu; unsigned nr; struct kioctx __rcu *table[] __counted_by(nr); }; struct kioctx_cpu { unsigned reqs_available; }; struct ctx_rq_wait { struct completion comp; atomic_t count; }; struct kioctx { struct percpu_ref users; atomic_t dead; struct percpu_ref reqs; unsigned long user_id; struct kioctx_cpu __percpu *cpu; /* * For percpu reqs_available, number of slots we move to/from global * counter at a time: */ unsigned req_batch; /* * This is what userspace passed to io_setup(), it's not used for * anything but counting against the global max_reqs quota. * * The real limit is nr_events - 1, which will be larger (see * aio_setup_ring()) */ unsigned max_reqs; /* Size of ringbuffer, in units of struct io_event */ unsigned nr_events; unsigned long mmap_base; unsigned long mmap_size; struct folio **ring_folios; long nr_pages; struct rcu_work free_rwork; /* see free_ioctx() */ /* * signals when all in-flight requests are done */ struct ctx_rq_wait *rq_wait; struct { /* * This counts the number of available slots in the ringbuffer, * so we avoid overflowing it: it's decremented (if positive) * when allocating a kiocb and incremented when the resulting * io_event is pulled off the ringbuffer. * * We batch accesses to it with a percpu version. */ atomic_t reqs_available; } ____cacheline_aligned_in_smp; struct { spinlock_t ctx_lock; struct list_head active_reqs; /* used for cancellation */ } ____cacheline_aligned_in_smp; struct { struct mutex ring_lock; wait_queue_head_t wait; } ____cacheline_aligned_in_smp; struct { unsigned tail; unsigned completed_events; spinlock_t completion_lock; } ____cacheline_aligned_in_smp; struct folio *internal_folios[AIO_RING_PAGES]; struct file *aio_ring_file; unsigned id; }; /* * First field must be the file pointer in all the * iocb unions! See also 'struct kiocb' in <linux/fs.h> */ struct fsync_iocb { struct file *file; struct work_struct work; bool datasync; struct cred *creds; }; struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; bool cancelled; bool work_scheduled; bool work_need_resched; struct wait_queue_entry wait; struct work_struct work; }; /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can * access the file pointer through any of the sub-structs, * or directly as just 'ki_filp' in this struct. */ struct aio_kiocb { union { struct file *ki_filp; struct kiocb rw; struct fsync_iocb fsync; struct poll_iocb poll; }; struct kioctx *ki_ctx; kiocb_cancel_fn *ki_cancel; struct io_event ki_res; struct list_head ki_list; /* the aio core uses this * for cancellation */ refcount_t ki_refcnt; /* * If the aio_resfd field of the userspace iocb is not zero, * this is the underlying eventfd context to deliver events to. */ struct eventfd_ctx *ki_eventfd; }; struct aio_inode_info { struct inode vfs_inode; spinlock_t migrate_lock; struct kioctx *ctx; }; static inline struct aio_inode_info *AIO_I(struct inode *inode) { return container_of(inode, struct aio_inode_info, vfs_inode); } /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); static unsigned long aio_nr; /* current system wide number of aio requests */ static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ #ifdef CONFIG_SYSCTL static const struct ctl_table aio_sysctls[] = { { .procname = "aio-nr", .data = &aio_nr, .maxlen = sizeof(aio_nr), .mode = 0444, .proc_handler = proc_doulongvec_minmax, }, { .procname = "aio-max-nr", .data = &aio_max_nr, .maxlen = sizeof(aio_max_nr), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; static void __init aio_sysctl_init(void) { register_sysctl_init("fs", aio_sysctls); } #else #define aio_sysctl_init() do { } while (0) #endif static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; static struct kmem_cache *aio_inode_cachep; static struct vfsmount *aio_mnt; static const struct file_operations aio_ring_fops; static const struct address_space_operations aio_ctx_aops; static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { struct file *file; struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb); if (IS_ERR(inode)) return ERR_CAST(inode); inode->i_mapping->a_ops = &aio_ctx_aops; AIO_I(inode)->ctx = ctx; inode->i_size = PAGE_SIZE * nr_pages; file = alloc_file_pseudo(inode, aio_mnt, "[aio]", O_RDWR, &aio_ring_fops); if (IS_ERR(file)) iput(inode); return file; } static struct inode *aio_alloc_inode(struct super_block *sb) { struct aio_inode_info *ai; ai = alloc_inode_sb(sb, aio_inode_cachep, GFP_KERNEL); if (!ai) return NULL; ai->ctx = NULL; return &ai->vfs_inode; } static void aio_free_inode(struct inode *inode) { kmem_cache_free(aio_inode_cachep, AIO_I(inode)); } static const struct super_operations aio_super_operations = { .alloc_inode = aio_alloc_inode, .free_inode = aio_free_inode, .statfs = simple_statfs, }; static int aio_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *pfc; pfc = init_pseudo(fc, AIO_RING_MAGIC); if (!pfc) return -ENOMEM; pfc->ops = &aio_super_operations; return 0; } static void init_once(void *obj) { struct aio_inode_info *ai = obj; inode_init_once(&ai->vfs_inode); spin_lock_init(&ai->migrate_lock); } /* aio_setup * Creates the slab caches used by the aio routines, panic on * failure as this is done early during the boot sequence. */ static int __init aio_setup(void) { static struct file_system_type aio_fs = { .name = "aio", .init_fs_context = aio_init_fs_context, .kill_sb = kill_anon_super, }; aio_inode_cachep = kmem_cache_create("aio_inode_cache", sizeof(struct aio_inode_info), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT), init_once); aio_mnt = kern_mount(&aio_fs); if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); aio_sysctl_init(); return 0; } __initcall(aio_setup); static void put_aio_ring_file(struct kioctx *ctx) { struct file *aio_ring_file = ctx->aio_ring_file; if (aio_ring_file) { struct inode *inode = file_inode(aio_ring_file); truncate_setsize(inode, 0); /* Prevent further access to the kioctx from migratepages */ spin_lock(&AIO_I(inode)->migrate_lock); AIO_I(inode)->ctx = NULL; ctx->aio_ring_file = NULL; spin_unlock(&AIO_I(inode)->migrate_lock); fput(aio_ring_file); } } static void aio_free_ring(struct kioctx *ctx) { int i; /* Disconnect the kiotx from the ring file. This prevents future * accesses to the kioctx from page migration. */ put_aio_ring_file(ctx); for (i = 0; i < ctx->nr_pages; i++) { struct folio *folio = ctx->ring_folios[i]; if (!folio) continue; pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i, folio_ref_count(folio)); ctx->ring_folios[i] = NULL; folio_put(folio); } if (ctx->ring_folios && ctx->ring_folios != ctx->internal_folios) { kfree(ctx->ring_folios); ctx->ring_folios = NULL; } } static int aio_ring_mremap(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct mm_struct *mm = vma->vm_mm; struct kioctx_table *table; int i, res = -EINVAL; spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); if (!table) goto out_unlock; for (i = 0; i < table->nr; i++) { struct kioctx *ctx; ctx = rcu_dereference(table->table[i]); if (ctx && ctx->aio_ring_file == file) { if (!atomic_read(&ctx->dead) && (ctx->mmap_size == (vma->vm_end - vma->vm_start))) { ctx->user_id = ctx->mmap_base = vma->vm_start; res = 0; } break; } } out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; } static const struct vm_operations_struct aio_ring_vm_ops = { .mremap = aio_ring_mremap, #if IS_ENABLED(CONFIG_MMU) .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, #endif }; static int aio_ring_mmap_prepare(struct vm_area_desc *desc) { vma_desc_set_flags(desc, VMA_DONTEXPAND_BIT, VMA_DONTCOPY_BIT); desc->vm_ops = &aio_ring_vm_ops; return 0; } static const struct file_operations aio_ring_fops = { .mmap_prepare = aio_ring_mmap_prepare, }; #if IS_ENABLED(CONFIG_MIGRATION) static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { struct kioctx *ctx; struct aio_inode_info *ai = AIO_I(mapping->host); unsigned long flags; pgoff_t idx; int rc = 0; /* ai->migrate_lock here protects against the kioctx teardown. */ spin_lock(&ai->migrate_lock); ctx = ai->ctx; if (!ctx) { rc = -EINVAL; goto out; } /* The ring_lock mutex. The prevents aio_read_events() from writing * to the ring's head, and prevents page migration from mucking in * a partially initialized kiotx. */ if (!mutex_trylock(&ctx->ring_lock)) { rc = -EAGAIN; goto out; } idx = src->index; if (idx < (pgoff_t)ctx->nr_pages) { /* Make sure the old folio hasn't already been changed */ if (ctx->ring_folios[idx] != src) rc = -EAGAIN; } else rc = -EINVAL; if (rc != 0) goto out_unlock; /* Writeback must be complete */ BUG_ON(folio_test_writeback(src)); folio_get(dst); rc = folio_migrate_mapping(mapping, dst, src, 1); if (rc) { folio_put(dst); goto out_unlock; } /* Take completion_lock to prevent other writes to the ring buffer * while the old folio is copied to the new. This prevents new * events from being lost. */ spin_lock_irqsave(&ctx->completion_lock, flags); folio_copy(dst, src); folio_migrate_flags(dst, src); BUG_ON(ctx->ring_folios[idx] != src); ctx->ring_folios[idx] = dst; spin_unlock_irqrestore(&ctx->completion_lock, flags); /* The old folio is no longer accessible. */ folio_put(src); out_unlock: mutex_unlock(&ctx->ring_lock); out: spin_unlock(&ai->migrate_lock); return rc; } #else #define aio_migrate_folio NULL #endif static const struct address_space_operations aio_ctx_aops = { .dirty_folio = noop_dirty_folio, .migrate_folio = aio_migrate_folio, }; static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) { struct aio_ring *ring; struct mm_struct *mm = current->mm; unsigned long size, unused; int nr_pages; int i; struct file *file; /* Compensate for the ring buffer's head/tail overlap entry */ nr_events += 2; /* 1 is required, 2 for good luck */ size = sizeof(struct aio_ring); size += sizeof(struct io_event) * nr_events; nr_pages = PFN_UP(size); if (nr_pages < 0) return -EINVAL; file = aio_private_file(ctx, nr_pages); if (IS_ERR(file)) { ctx->aio_ring_file = NULL; return -ENOMEM; } ctx->aio_ring_file = file; nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event); ctx->ring_folios = ctx->internal_folios; if (nr_pages > AIO_RING_PAGES) { ctx->ring_folios = kzalloc_objs(struct folio *, nr_pages); if (!ctx->ring_folios) { put_aio_ring_file(ctx); return -ENOMEM; } } for (i = 0; i < nr_pages; i++) { struct folio *folio; folio = __filemap_get_folio(file->f_mapping, i, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_USER | __GFP_ZERO); if (IS_ERR(folio)) break; pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i, folio_ref_count(folio)); folio_end_read(folio, true); ctx->ring_folios[i] = folio; } ctx->nr_pages = i; if (unlikely(i != nr_pages)) { aio_free_ring(ctx); return -ENOMEM; } ctx->mmap_size = nr_pages * PAGE_SIZE; pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size); if (mmap_write_lock_killable(mm)) { ctx->mmap_size = 0; aio_free_ring(ctx); return -EINTR; } ctx->mmap_base = do_mmap(ctx->aio_ring_file, 0, ctx->mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, 0, 0, &unused, NULL); mmap_write_unlock(mm); if (IS_ERR((void *)ctx->mmap_base)) { ctx->mmap_size = 0; aio_free_ring(ctx); return -ENOMEM; } pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); ctx->user_id = ctx->mmap_base; ctx->nr_events = nr_events; /* trusted copy */ ring = folio_address(ctx->ring_folios[0]); ring->nr = nr_events; /* user copy */ ring->id = ~0U; ring->head = ring->tail = 0; ring->magic = AIO_RING_MAGIC; ring->compat_features = AIO_RING_COMPAT_FEATURES; ring->incompat_features = AIO_RING_INCOMPAT_FEATURES; ring->header_length = sizeof(struct aio_ring); flush_dcache_folio(ctx->ring_folios[0]); return 0; } #define AIO_EVENTS_PER_PAGE (PAGE_SIZE / sizeof(struct io_event)) #define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event)) #define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { struct aio_kiocb *req; struct kioctx *ctx; unsigned long flags; /* * kiocb didn't come from aio or is neither a read nor a write, hence * ignore it. */ if (!(iocb->ki_flags & IOCB_AIO_RW)) return; req = container_of(iocb, struct aio_kiocb, rw); if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; ctx = req->ki_ctx; spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; spin_unlock_irqrestore(&ctx->ctx_lock, flags); } EXPORT_SYMBOL(kiocb_set_cancel_fn); /* * free_ioctx() should be RCU delayed to synchronize against the RCU * protected lookup_ioctx() and also needs process context to call * aio_free_ring(). Use rcu_work. */ static void free_ioctx(struct work_struct *work) { struct kioctx *ctx = container_of(to_rcu_work(work), struct kioctx, free_rwork); pr_debug("freeing %p\n", ctx); aio_free_ring(ctx); free_percpu(ctx->cpu); percpu_ref_exit(&ctx->reqs); percpu_ref_exit(&ctx->users); kmem_cache_free(kioctx_cachep, ctx); } static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); /* At this point we know that there are no any in-flight requests */ if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) complete(&ctx->rq_wait->comp); /* Synchronize against RCU protected table->table[] dereferences */ INIT_RCU_WORK(&ctx->free_rwork, free_ioctx); queue_rcu_work(system_percpu_wq, &ctx->free_rwork); } /* * When this function runs, the kioctx has been removed from the "hash table" * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - * now it's safe to cancel any that need to be. */ static void free_ioctx_users(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, users); struct aio_kiocb *req; spin_lock_irq(&ctx->ctx_lock); while (!list_empty(&ctx->active_reqs)) { req = list_first_entry(&ctx->active_reqs, struct aio_kiocb, ki_list); req->ki_cancel(&req->rw); list_del_init(&req->ki_list); } spin_unlock_irq(&ctx->ctx_lock); percpu_ref_kill(&ctx->reqs); percpu_ref_put(&ctx->reqs); } static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) { unsigned i, new_nr; struct kioctx_table *table, *old; struct aio_ring *ring; spin_lock(&mm->ioctx_lock); table = rcu_dereference_raw(mm->ioctx_table); while (1) { if (table) for (i = 0; i < table->nr; i++) if (!rcu_access_pointer(table->table[i])) { ctx->id = i; rcu_assign_pointer(table->table[i], ctx); spin_unlock(&mm->ioctx_lock); /* While kioctx setup is in progress, * we are protected from page migration * changes ring_folios by ->ring_lock. */ ring = folio_address(ctx->ring_folios[0]); ring->id = ctx->id; return 0; } new_nr = (table ? table->nr : 1) * 4; spin_unlock(&mm->ioctx_lock); table = kzalloc_flex(*table, table, new_nr); if (!table) return -ENOMEM; table->nr = new_nr; spin_lock(&mm->ioctx_lock); old = rcu_dereference_raw(mm->ioctx_table); if (!old) { rcu_assign_pointer(mm->ioctx_table, table); } else if (table->nr > old->nr) { memcpy(table->table, old->table, old->nr * sizeof(struct kioctx *)); rcu_assign_pointer(mm->ioctx_table, table); kfree_rcu(old, rcu); } else { kfree(table); table = old; } } } static void aio_nr_sub(unsigned nr) { spin_lock(&aio_nr_lock); if (WARN_ON(aio_nr - nr > aio_nr)) aio_nr = 0; else aio_nr -= nr; spin_unlock(&aio_nr_lock); } /* ioctx_alloc * Allocates and initializes an ioctx. Returns an ERR_PTR if it failed. */ static struct kioctx *ioctx_alloc(unsigned nr_events) { struct mm_struct *mm = current->mm; struct kioctx *ctx; int err = -ENOMEM; /* * Store the original nr_events -- what userspace passed to io_setup(), * for counting against the global limit -- before it changes. */ unsigned int max_reqs = nr_events; /* * We keep track of the number of available ringbuffer slots, to prevent * overflow (reqs_available), and we also use percpu counters for this. * * So since up to half the slots might be on other cpu's percpu counters * and unavailable, double nr_events so userspace sees what they * expected: additionally, we move req_batch slots to/from percpu * counters at a time, so make sure that isn't 0: */ nr_events = max(nr_events, num_possible_cpus() * 4); nr_events *= 2; /* Prevent overflows */ if (nr_events > (0x10000000U / sizeof(struct io_event))) { pr_debug("ENOMEM: nr_events too high\n"); return ERR_PTR(-EINVAL); } if (!nr_events || (unsigned long)max_reqs > aio_max_nr) return ERR_PTR(-EAGAIN); ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); ctx->max_reqs = max_reqs; spin_lock_init(&ctx->ctx_lock); spin_lock_init(&ctx->completion_lock); mutex_init(&ctx->ring_lock); /* Protect against page migration throughout kiotx setup by keeping * the ring_lock mutex held until setup is complete. */ mutex_lock(&ctx->ring_lock); init_waitqueue_head(&ctx->wait); INIT_LIST_HEAD(&ctx->active_reqs); if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL)) goto err; if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, 0, GFP_KERNEL)) goto err; ctx->cpu = alloc_percpu(struct kioctx_cpu); if (!ctx->cpu) goto err; err = aio_setup_ring(ctx, nr_events); if (err < 0) goto err; atomic_set(&ctx->reqs_available, ctx->nr_events - 1); ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4); if (ctx->req_batch < 1) ctx->req_batch = 1; /* limit the number of system wide aios */ spin_lock(&aio_nr_lock); if (aio_nr + ctx->max_reqs > aio_max_nr || aio_nr + ctx->max_reqs < aio_nr) { spin_unlock(&aio_nr_lock); err = -EAGAIN; goto err_ctx; } aio_nr += ctx->max_reqs; spin_unlock(&aio_nr_lock); percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */ percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */ err = ioctx_add_table(ctx, mm); if (err) goto err_cleanup; /* Release the ring_lock mutex now that all setup is complete. */ mutex_unlock(&ctx->ring_lock); pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", ctx, ctx->user_id, mm, ctx->nr_events); return ctx; err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: atomic_set(&ctx->dead, 1); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); free_percpu(ctx->cpu); percpu_ref_exit(&ctx->reqs); percpu_ref_exit(&ctx->users); kmem_cache_free(kioctx_cachep, ctx); pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); } /* kill_ioctx * Cancels all outstanding aio requests on an aio context. Used * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, struct ctx_rq_wait *wait) { struct kioctx_table *table; spin_lock(&mm->ioctx_lock); if (atomic_xchg(&ctx->dead, 1)) { spin_unlock(&mm->ioctx_lock); return -EINVAL; } table = rcu_dereference_raw(mm->ioctx_table); WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id])); RCU_INIT_POINTER(table->table[ctx->id], NULL); spin_unlock(&mm->ioctx_lock); /* free_ioctx_reqs() will do the necessary RCU synchronization */ wake_up_all(&ctx->wait); /* * It'd be more correct to do this in free_ioctx(), after all * the outstanding kiocbs have finished - but by then io_destroy * has already returned, so io_setup() could potentially return * -EAGAIN with no ioctxs actually in use (as far as userspace * could tell). */ aio_nr_sub(ctx->max_reqs); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); ctx->rq_wait = wait; percpu_ref_kill(&ctx->users); return 0; } /* * exit_aio: called when the last user of mm goes away. At this point, there is * no way for any new requests to be submited or any of the io_* syscalls to be * called on the context. * * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on * them. */ void exit_aio(struct mm_struct *mm) { struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table); struct ctx_rq_wait wait; int i, skipped; if (!table) return; atomic_set(&wait.count, table->nr); init_completion(&wait.comp); skipped = 0; for (i = 0; i < table->nr; ++i) { struct kioctx *ctx = rcu_dereference_protected(table->table[i], true); if (!ctx) { skipped++; continue; } /* * We don't need to bother with munmap() here - exit_mmap(mm) * is coming and it'll unmap everything. And we simply can't, * this is not necessarily our ->mm. * Since kill_ioctx() uses non-zero ->mmap_size as indicator * that it needs to unmap the area, just set it to 0. */ ctx->mmap_size = 0; kill_ioctx(mm, ctx, &wait); } if (!atomic_sub_and_test(skipped, &wait.count)) { /* Wait until all IO for the context are done. */ wait_for_completion(&wait.comp); } RCU_INIT_POINTER(mm->ioctx_table, NULL); kfree(table); } static void put_reqs_available(struct kioctx *ctx, unsigned nr) { struct kioctx_cpu *kcpu; unsigned long flags; local_irq_save(flags); kcpu = this_cpu_ptr(ctx->cpu); kcpu->reqs_available += nr; while (kcpu->reqs_available >= ctx->req_batch * 2) { kcpu->reqs_available -= ctx->req_batch; atomic_add(ctx->req_batch, &ctx->reqs_available); } local_irq_restore(flags); } static bool __get_reqs_available(struct kioctx *ctx) { struct kioctx_cpu *kcpu; bool ret = false; unsigned long flags; local_irq_save(flags); kcpu = this_cpu_ptr(ctx->cpu); if (!kcpu->reqs_available) { int avail = atomic_read(&ctx->reqs_available); do { if (avail < ctx->req_batch) goto out; } while (!atomic_try_cmpxchg(&ctx->reqs_available, &avail, avail - ctx->req_batch)); kcpu->reqs_available += ctx->req_batch; } ret = true; kcpu->reqs_available--; out: local_irq_restore(flags); return ret; } /* refill_reqs_available * Updates the reqs_available reference counts used for tracking the * number of free slots in the completion ring. This can be called * from aio_complete() (to optimistically update reqs_available) or * from aio_get_req() (the we're out of events case). It must be * called holding ctx->completion_lock. */ static void refill_reqs_available(struct kioctx *ctx, unsigned head, unsigned tail) { unsigned events_in_ring, completed; /* Clamp head since userland can write to it. */ head %= ctx->nr_events; if (head <= tail) events_in_ring = tail - head; else events_in_ring = ctx->nr_events - (head - tail); completed = ctx->completed_events; if (events_in_ring < completed) completed -= events_in_ring; else completed = 0; if (!completed) return; ctx->completed_events -= completed; put_reqs_available(ctx, completed); } /* user_refill_reqs_available * Called to refill reqs_available when aio_get_req() encounters an * out of space in the completion ring. */ static void user_refill_reqs_available(struct kioctx *ctx) { spin_lock_irq(&ctx->completion_lock); if (ctx->completed_events) { struct aio_ring *ring; unsigned head; /* Access of ring->head may race with aio_read_events_ring() * here, but that's okay since whether we read the old version * or the new version, and either will be valid. The important * part is that head cannot pass tail since we prevent * aio_complete() from updating tail by holding * ctx->completion_lock. Even if head is invalid, the check * against ctx->completed_events below will make sure we do the * safe/right thing. */ ring = folio_address(ctx->ring_folios[0]); head = ring->head; refill_reqs_available(ctx, head, ctx->tail); } spin_unlock_irq(&ctx->completion_lock); } static bool get_reqs_available(struct kioctx *ctx) { if (__get_reqs_available(ctx)) return true; user_refill_reqs_available(ctx); return __get_reqs_available(ctx); } /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. * * The refcount is initialized to 2 - one for the async op completion, * one for the synchronous code that does this. */ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { struct aio_kiocb *req; req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL); if (unlikely(!req)) return NULL; if (unlikely(!get_reqs_available(ctx))) { kmem_cache_free(kiocb_cachep, req); return NULL; } percpu_ref_get(&ctx->reqs); req->ki_ctx = ctx; INIT_LIST_HEAD(&req->ki_list); refcount_set(&req->ki_refcnt, 2); req->ki_eventfd = NULL; return req; } static struct kioctx *lookup_ioctx(unsigned long ctx_id) { struct aio_ring __user *ring = (void __user *)ctx_id; struct mm_struct *mm = current->mm; struct kioctx *ctx, *ret = NULL; struct kioctx_table *table; unsigned id; if (get_user(id, &ring->id)) return NULL; rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); if (!table || id >= table->nr) goto out; id = array_index_nospec(id, table->nr); ctx = rcu_dereference(table->table[id]); if (ctx && ctx->user_id == ctx_id) { if (percpu_ref_tryget_live(&ctx->users)) ret = ctx; } out: rcu_read_unlock(); return ret; } static inline void iocb_destroy(struct aio_kiocb *iocb) { if (iocb->ki_eventfd) eventfd_ctx_put(iocb->ki_eventfd); if (iocb->ki_filp) fput(iocb->ki_filp); percpu_ref_put(&iocb->ki_ctx->reqs); kmem_cache_free(kiocb_cachep, iocb); } struct aio_waiter { struct wait_queue_entry w; size_t min_nr; }; /* aio_complete * Called when the io request on the given iocb is complete. */ static void aio_complete(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; unsigned tail, pos, head, avail; unsigned long flags; /* * Add a completion event to the ring buffer. Must be done holding * ctx->completion_lock to prevent other code from messing with the tail * pointer since we might be called from irq context. */ spin_lock_irqsave(&ctx->completion_lock, flags); tail = ctx->tail; pos = tail + AIO_EVENTS_OFFSET; if (++tail >= ctx->nr_events) tail = 0; ev_page = folio_address(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; *event = iocb->ki_res; flush_dcache_folio(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]); pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, (void __user *)(unsigned long)iocb->ki_res.obj, iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2); /* after flagging the request as done, we * must never even look at it again */ smp_wmb(); /* make event visible before updating tail */ ctx->tail = tail; ring = folio_address(ctx->ring_folios[0]); head = ring->head; ring->tail = tail; flush_dcache_folio(ctx->ring_folios[0]); ctx->completed_events++; if (ctx->completed_events > 1) refill_reqs_available(ctx, head, tail); avail = tail > head ? tail - head : tail + ctx->nr_events - head; spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); /* * Check if the user asked us to deliver the result through an * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ if (iocb->ki_eventfd) eventfd_signal(iocb->ki_eventfd); /* * We have to order our ring_info tail store above and test * of the wait list below outside the wait lock. This is * like in wake_up_bit() where clearing a bit has to be * ordered with the unlocked test. */ smp_mb(); if (waitqueue_active(&ctx->wait)) { struct aio_waiter *curr, *next; unsigned long flags; spin_lock_irqsave(&ctx->wait.lock, flags); list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry) if (avail >= curr->min_nr) { wake_up_process(curr->w.private); list_del_init_careful(&curr->w.entry); } spin_unlock_irqrestore(&ctx->wait.lock, flags); } } static inline void iocb_put(struct aio_kiocb *iocb) { if (refcount_dec_and_test(&iocb->ki_refcnt)) { aio_complete(iocb); iocb_destroy(iocb); } } /* aio_read_events_ring * Pull an event off of the ioctx's event ring. Returns the number of * events fetched */ static long aio_read_events_ring(struct kioctx *ctx, struct io_event __user *event, long nr) { struct aio_ring *ring; unsigned head, tail, pos; long ret = 0; int copy_ret; /* * The mutex can block and wake us up and that will cause * wait_event_interruptible_hrtimeout() to schedule without sleeping * and repeat. This should be rare enough that it doesn't cause * peformance issues. See the comment in read_events() for more detail. */ sched_annotate_sleep(); mutex_lock(&ctx->ring_lock); /* Access to ->ring_folios here is protected by ctx->ring_lock. */ ring = folio_address(ctx->ring_folios[0]); head = ring->head; tail = ring->tail; /* * Ensure that once we've read the current tail pointer, that * we also see the events that were stored up to the tail. */ smp_rmb(); pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events); if (head == tail) goto out; head %= ctx->nr_events; tail %= ctx->nr_events; while (ret < nr) { long avail; struct io_event *ev; struct folio *folio; avail = (head <= tail ? tail : ctx->nr_events) - head; if (head == tail) break; pos = head + AIO_EVENTS_OFFSET; folio = ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]; pos %= AIO_EVENTS_PER_PAGE; avail = min(avail, nr - ret); avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos); ev = folio_address(folio); copy_ret = copy_to_user(event + ret, ev + pos, sizeof(*ev) * avail); if (unlikely(copy_ret)) { ret = -EFAULT; goto out; } ret += avail; head += avail; head %= ctx->nr_events; } ring = folio_address(ctx->ring_folios[0]); ring->head = head; flush_dcache_folio(ctx->ring_folios[0]); pr_debug("%li h%u t%u\n", ret, head, tail); out: mutex_unlock(&ctx->ring_lock); return ret; } static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event __user *event, long *i) { long ret = aio_read_events_ring(ctx, event + *i, nr - *i); if (ret > 0) *i += ret; if (unlikely(atomic_read(&ctx->dead))) ret = -EINVAL; if (!*i) *i = ret; return ret < 0 || *i >= min_nr; } static long read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event __user *event, ktime_t until) { struct hrtimer_sleeper t; struct aio_waiter w; long ret = 0, ret2 = 0; /* * Note that aio_read_events() is being called as the conditional - i.e. * we're calling it after prepare_to_wait() has set task state to * TASK_INTERRUPTIBLE. * * But aio_read_events() can block, and if it blocks it's going to flip * the task state back to TASK_RUNNING. * * This should be ok, provided it doesn't flip the state back to * TASK_RUNNING and return 0 too much - that causes us to spin. That * will only happen if the mutex_lock() call blocks, and we then find * the ringbuffer empty. So in practice we should be ok, but it's * something to be aware of when touching this code. */ aio_read_events(ctx, min_nr, nr, event, &ret); if (until == 0 || ret < 0 || ret >= min_nr) return ret; hrtimer_setup_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); if (until != KTIME_MAX) { hrtimer_set_expires_range_ns(&t.timer, until, current->timer_slack_ns); hrtimer_sleeper_start_expires(&t, HRTIMER_MODE_REL); } init_wait(&w.w); while (1) { unsigned long nr_got = ret; w.min_nr = min_nr - ret; ret2 = prepare_to_wait_event(&ctx->wait, &w.w, TASK_INTERRUPTIBLE); if (!ret2 && !t.task) ret2 = -ETIME; if (aio_read_events(ctx, min_nr, nr, event, &ret) || ret2) break; if (nr_got == ret) schedule(); } finish_wait(&ctx->wait, &w.w); hrtimer_cancel(&t.timer); destroy_hrtimer_on_stack(&t.timer); return ret; } /* sys_io_setup: * Create an aio_context capable of receiving at least nr_events. * ctxp must not point to an aio_context that already exists, and * must be initialized to 0 prior to the call. On successful * creation of the aio_context, *ctxp is filled in with the resulting * handle. May fail with -EINVAL if *ctxp is not initialized, * if the specified nr_events exceeds internal limits. May fail * with -EAGAIN if the specified nr_events exceeds the user's limit * of available events. May fail with -ENOMEM if insufficient kernel * resources are available. May fail with -EFAULT if an invalid * pointer is passed for ctxp. Will fail with -ENOSYS if not * implemented. */ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) { struct kioctx *ioctx = NULL; unsigned long ctx; long ret; ret = get_user(ctx, ctxp); if (unlikely(ret)) goto out; ret = -EINVAL; if (unlikely(ctx || nr_events == 0)) { pr_debug("EINVAL: ctx %lu nr_events %u\n", ctx, nr_events); goto out; } ioctx = ioctx_alloc(nr_events); ret = PTR_ERR(ioctx); if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } out: return ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_events, u32 __user *, ctx32p) { struct kioctx *ioctx = NULL; unsigned long ctx; long ret; ret = get_user(ctx, ctx32p); if (unlikely(ret)) goto out; ret = -EINVAL; if (unlikely(ctx || nr_events == 0)) { pr_debug("EINVAL: ctx %lu nr_events %u\n", ctx, nr_events); goto out; } ioctx = ioctx_alloc(nr_events); ret = PTR_ERR(ioctx); if (!IS_ERR(ioctx)) { /* truncating is ok because it's a user address */ ret = put_user((u32)ioctx->user_id, ctx32p); if (ret) kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } out: return ret; } #endif /* sys_io_destroy: * Destroy the aio_context specified. May cancel any outstanding * AIOs and block on completion. Will fail with -ENOSYS if not * implemented. May fail with -EINVAL if the context pointed to * is invalid. */ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { struct ctx_rq_wait wait; int ret; init_completion(&wait.comp); atomic_set(&wait.count, 1); /* Pass requests_done to kill_ioctx() where it can be set * in a thread-safe way. If we try to set it here then we have * a race condition if two io_destroy() called simultaneously. */ ret = kill_ioctx(current->mm, ioctx, &wait); percpu_ref_put(&ioctx->users); /* Wait until all IO for the context are done. Otherwise kernel * keep using user-space buffers even if user thinks the context * is destroyed. */ if (!ret) wait_for_completion(&wait.comp); return ret; } pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } static void aio_remove_iocb(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; unsigned long flags; spin_lock_irqsave(&ctx->ctx_lock, flags); list_del(&iocb->ki_list); spin_unlock_irqrestore(&ctx->ctx_lock, flags); } static void aio_complete_rw(struct kiocb *kiocb, long res) { struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw); if (!list_empty_careful(&iocb->ki_list)) aio_remove_iocb(iocb); if (kiocb->ki_flags & IOCB_WRITE) { struct inode *inode = file_inode(kiocb->ki_filp); if (S_ISREG(inode->i_mode)) kiocb_end_write(kiocb); } iocb->ki_res.res = res; iocb->ki_res.res2 = 0; iocb_put(iocb); } static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb, int rw_type) { int ret; req->ki_write_stream = 0; req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { /* * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then * aio_reqprio is interpreted as an I/O scheduling * class and priority. */ ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); return ret; } req->ki_ioprio = iocb->aio_reqprio; } else req->ki_ioprio = get_current_ioprio(); ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags, rw_type); if (unlikely(ret)) return ret; req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */ return 0; } static ssize_t aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec, bool vectored, bool compat, struct iov_iter *iter) { void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf; size_t len = iocb->aio_nbytes; if (!vectored) { ssize_t ret = import_ubuf(rw, buf, len, iter); *iovec = NULL; return ret; } return __import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter, compat); } static inline void aio_rw_done(struct kiocb *req, ssize_t ret) { switch (ret) { case -EIOCBQUEUED: break; case -ERESTARTSYS: case -ERESTARTNOINTR: case -ERESTARTNOHAND: case -ERESTART_RESTARTBLOCK: /* * There's no easy way to restart the syscall since other AIO's * may be already running. Just fail this IO with EINTR. */ ret = -EINTR; fallthrough; default: req->ki_complete(req, ret); } } static int aio_read(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; int ret; ret = aio_prep_rw(req, iocb, READ); if (ret) return ret; file = req->ki_filp; if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; if (unlikely(!file->f_op->read_iter)) return -EINVAL; ret = aio_setup_rw(ITER_DEST, iocb, &iovec, vectored, compat, &iter); if (ret < 0) return ret; ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) aio_rw_done(req, file->f_op->read_iter(req, &iter)); kfree(iovec); return ret; } static int aio_write(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; int ret; ret = aio_prep_rw(req, iocb, WRITE); if (ret) return ret; file = req->ki_filp; if (unlikely(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (unlikely(!file->f_op->write_iter)) return -EINVAL; ret = aio_setup_rw(ITER_SOURCE, iocb, &iovec, vectored, compat, &iter); if (ret < 0) return ret; ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) { if (S_ISREG(file_inode(file)->i_mode)) kiocb_start_write(req); req->ki_flags |= IOCB_WRITE; aio_rw_done(req, file->f_op->write_iter(req, &iter)); } kfree(iovec); return ret; } static void aio_fsync_work(struct work_struct *work) { struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); scoped_with_creds(iocb->fsync.creds) iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); put_cred(iocb->fsync.creds); iocb_put(iocb); } static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, bool datasync) { if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)) return -EINVAL; if (unlikely(!req->file->f_op->fsync)) return -EINVAL; req->creds = prepare_creds(); if (!req->creds) return -ENOMEM; req->datasync = datasync; INIT_WORK(&req->work, aio_fsync_work); schedule_work(&req->work); return 0; } static void aio_poll_put_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); iocb_put(iocb); } /* * Safely lock the waitqueue which the request is on, synchronizing with the * case where the ->poll() provider decides to free its waitqueue early. * * Returns true on success, meaning that req->head->lock was locked, req->wait * is on req->head, and an RCU read lock was taken. Returns false if the * request was already removed from its waitqueue (which might no longer exist). */ static bool poll_iocb_lock_wq(struct poll_iocb *req) { wait_queue_head_t *head; /* * While we hold the waitqueue lock and the waitqueue is nonempty, * wake_up_pollfree() will wait for us. However, taking the waitqueue * lock in the first place can race with the waitqueue being freed. * * We solve this as eventpoll does: by taking advantage of the fact that * all users of wake_up_pollfree() will RCU-delay the actual free. If * we enter rcu_read_lock() and see that the pointer to the queue is * non-NULL, we can then lock it without the memory being freed out from * under us, then check whether the request is still on the queue. * * Keep holding rcu_read_lock() as long as we hold the queue lock, in * case the caller deletes the entry from the queue, leaving it empty. * In that case, only RCU prevents the queue memory from being freed. */ rcu_read_lock(); head = smp_load_acquire(&req->head); if (head) { spin_lock(&head->lock); if (!list_empty(&req->wait.entry)) return true; spin_unlock(&head->lock); } rcu_read_unlock(); return false; } static void poll_iocb_unlock_wq(struct poll_iocb *req) { spin_unlock(&req->head->lock); rcu_read_unlock(); } static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); struct poll_table_struct pt = { ._key = req->events }; struct kioctx *ctx = iocb->ki_ctx; __poll_t mask = 0; if (!READ_ONCE(req->cancelled)) mask = vfs_poll(req->file, &pt) & req->events; /* * Note that ->ki_cancel callers also delete iocb from active_reqs after * calling ->ki_cancel. We need the ctx_lock roundtrip here to * synchronize with them. In the cancellation case the list_del_init * itself is not actually needed, but harmless so we keep it in to * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); if (poll_iocb_lock_wq(req)) { if (!mask && !READ_ONCE(req->cancelled)) { /* * The request isn't actually ready to be completed yet. * Reschedule completion if another wakeup came in. */ if (req->work_need_resched) { schedule_work(&req->work); req->work_need_resched = false; } else { req->work_scheduled = false; } poll_iocb_unlock_wq(req); spin_unlock_irq(&ctx->ctx_lock); return; } list_del_init(&req->wait.entry); poll_iocb_unlock_wq(req); } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); spin_unlock_irq(&ctx->ctx_lock); iocb_put(iocb); } /* assumes we are called with irqs disabled */ static int aio_poll_cancel(struct kiocb *iocb) { struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; if (poll_iocb_lock_wq(req)) { WRITE_ONCE(req->cancelled, true); if (!req->work_scheduled) { schedule_work(&aiocb->poll.work); req->work_scheduled = true; } poll_iocb_unlock_wq(req); } /* else, the request was force-cancelled by POLLFREE already */ return 0; } static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct poll_iocb *req = container_of(wait, struct poll_iocb, wait); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); __poll_t mask = key_to_poll(key); unsigned long flags; /* for instances that support it check for an event match first: */ if (mask && !(mask & req->events)) return 0; /* * Complete the request inline if possible. This requires that three * conditions be met: * 1. An event mask must have been passed. If a plain wakeup was done * instead, then mask == 0 and we have to call vfs_poll() to get * the events, so inline completion isn't possible. * 2. The completion work must not have already been scheduled. * 3. ctx_lock must not be busy. We have to use trylock because we * already hold the waitqueue lock, so this inverts the normal * locking order. Use irqsave/irqrestore because not all * filesystems (e.g. fuse) call this function with IRQs disabled, * yet IRQs have to be disabled before ctx_lock is obtained. */ if (mask && !req->work_scheduled && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { struct kioctx *ctx = iocb->ki_ctx; list_del_init(&req->wait.entry); list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); if (iocb->ki_eventfd && !eventfd_signal_allowed()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); schedule_work(&req->work); } spin_unlock_irqrestore(&ctx->ctx_lock, flags); if (iocb) iocb_put(iocb); } else { /* * Schedule the completion work if needed. If it was already * scheduled, record that another wakeup came in. * * Don't remove the request from the waitqueue here, as it might * not actually be complete yet (we won't know until vfs_poll() * is called), and we must not miss any wakeups. POLLFREE is an * exception to this; see below. */ if (req->work_scheduled) { req->work_need_resched = true; } else { schedule_work(&req->work); req->work_scheduled = true; } /* * If the waitqueue is being freed early but we can't complete * the request inline, we have to tear down the request as best * we can. That means immediately removing the request from its * waitqueue and preventing all further accesses to the * waitqueue via the request. We also need to schedule the * completion work (done above). Also mark the request as * cancelled, to potentially skip an unneeded call to ->poll(). */ if (mask & POLLFREE) { WRITE_ONCE(req->cancelled, true); list_del_init(&req->wait.entry); /* * Careful: this *must* be the last step, since as soon * as req->head is NULL'ed out, the request can be * completed and freed, since aio_poll_complete_work() * will no longer need to take the waitqueue lock. */ smp_store_release(&req->head, NULL); } } return 1; } struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; bool queued; int error; }; static void aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); } static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) { struct kioctx *ctx = aiocb->ki_ctx; struct poll_iocb *req = &aiocb->poll; struct aio_poll_table apt; bool cancel = false; __poll_t mask; /* reject any unknown events outside the normal event mask. */ if ((u16)iocb->aio_buf != iocb->aio_buf) return -EINVAL; /* reject fields that are not defined for poll */ if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags) return -EINVAL; INIT_WORK(&req->work, aio_poll_complete_work); req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; req->cancelled = false; req->work_scheduled = false; req->work_need_resched = false; apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ INIT_LIST_HEAD(&req->wait.entry); init_waitqueue_func_entry(&req->wait, aio_poll_wake); mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); if (likely(apt.queued)) { bool on_queue = poll_iocb_lock_wq(req); if (!on_queue || req->work_scheduled) { /* * aio_poll_wake() already either scheduled the async * completion work, or completed the request inline. */ if (apt.error) /* unsupported case: multiple queues */ cancel = true; apt.error = 0; mask = 0; } if (mask || apt.error) { /* Steal to complete synchronously. */ list_del_init(&req->wait.entry); } else if (cancel) { /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); } else if (on_queue) { /* * Actually waiting for an event, so add the request to * active_reqs so that it can be cancelled if needed. */ list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } if (on_queue) poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); apt.error = 0; } spin_unlock_irq(&ctx->ctx_lock); if (mask) iocb_put(aiocb); return apt.error; } static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, struct iocb __user *user_iocb, struct aio_kiocb *req, bool compat) { req->ki_filp = fget(iocb->aio_fildes); if (unlikely(!req->ki_filp)) return -EBADF; if (iocb->aio_flags & IOCB_FLAG_RESFD) { struct eventfd_ctx *eventfd; /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an * instance of the file* now. The file descriptor must be * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ eventfd = eventfd_ctx_fdget(iocb->aio_resfd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); req->ki_eventfd = eventfd; } if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) { pr_debug("EFAULT: aio_key\n"); return -EFAULT; } req->ki_res.obj = (u64)(unsigned long)user_iocb; req->ki_res.data = iocb->aio_data; req->ki_res.res = 0; req->ki_res.res2 = 0; switch (iocb->aio_lio_opcode) { case IOCB_CMD_PREAD: return aio_read(&req->rw, iocb, false, compat); case IOCB_CMD_PWRITE: return aio_write(&req->rw, iocb, false, compat); case IOCB_CMD_PREADV: return aio_read(&req->rw, iocb, true, compat); case IOCB_CMD_PWRITEV: return aio_write(&req->rw, iocb, true, compat); case IOCB_CMD_FSYNC: return aio_fsync(&req->fsync, iocb, false); case IOCB_CMD_FDSYNC: return aio_fsync(&req->fsync, iocb, true); case IOCB_CMD_POLL: return aio_poll(req, iocb); default: pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); return -EINVAL; } } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, bool compat) { struct aio_kiocb *req; struct iocb iocb; int err; if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb)))) return -EFAULT; /* enforce forwards compatibility on users */ if (unlikely(iocb.aio_reserved2)) { pr_debug("EINVAL: reserve field set\n"); return -EINVAL; } /* prevent overflows */ if (unlikely( (iocb.aio_buf != (unsigned long)iocb.aio_buf) || (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) || ((ssize_t)iocb.aio_nbytes < 0) )) { pr_debug("EINVAL: overflow check\n"); return -EINVAL; } req = aio_get_req(ctx); if (unlikely(!req)) return -EAGAIN; err = __io_submit_one(ctx, &iocb, user_iocb, req, compat); /* Done with the synchronous reference */ iocb_put(req); /* * If err is 0, we'd either done aio_complete() ourselves or have * arranged for that to be done asynchronously. Anything non-zero * means that we need to destroy req ourselves. */ if (unlikely(err)) { iocb_destroy(req); put_reqs_available(ctx, 1); } return err; } /* sys_io_submit: * Queue the nr iocbs pointed to by iocbpp for processing. Returns * the number of iocbs queued. May return -EINVAL if the aio_context * specified by ctx_id is invalid, if nr is < 0, if the iocb at * *iocbpp[0] is not properly initialized, if the operation specified * is invalid for the file descriptor in the iocb. May fail with * -EFAULT if any of the data structures point to invalid data. May * fail with -EBADF if the file descriptor specified in the first * iocb is invalid. May fail with -EAGAIN if insufficient resources * are available to queue any iocbs. Will return 0 if nr is 0. Will * fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, struct iocb __user * __user *, iocbpp) { struct kioctx *ctx; long ret = 0; int i = 0; struct blk_plug plug; if (unlikely(nr < 0)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } if (nr > ctx->nr_events) nr = ctx->nr_events; if (nr > AIO_PLUG_THRESHOLD) blk_start_plug(&plug); for (i = 0; i < nr; i++) { struct iocb __user *user_iocb; if (unlikely(get_user(user_iocb, iocbpp + i))) { ret = -EFAULT; break; } ret = io_submit_one(ctx, user_iocb, false); if (ret) break; } if (nr > AIO_PLUG_THRESHOLD) blk_finish_plug(&plug); percpu_ref_put(&ctx->users); return i ? i : ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, int, nr, compat_uptr_t __user *, iocbpp) { struct kioctx *ctx; long ret = 0; int i = 0; struct blk_plug plug; if (unlikely(nr < 0)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } if (nr > ctx->nr_events) nr = ctx->nr_events; if (nr > AIO_PLUG_THRESHOLD) blk_start_plug(&plug); for (i = 0; i < nr; i++) { compat_uptr_t user_iocb; if (unlikely(get_user(user_iocb, iocbpp + i))) { ret = -EFAULT; break; } ret = io_submit_one(ctx, compat_ptr(user_iocb), true); if (ret) break; } if (nr > AIO_PLUG_THRESHOLD) blk_finish_plug(&plug); percpu_ref_put(&ctx->users); return i ? i : ret; } #endif /* sys_io_cancel: * Attempts to cancel an iocb previously passed to io_submit. If * the operation is successfully cancelled, the resulting event is * copied into the memory pointed to by result without being placed * into the completion queue and 0 is returned. May fail with * -EFAULT if any of the data structures pointed to are invalid. * May fail with -EINVAL if aio_context specified by ctx_id is * invalid. May fail with -EAGAIN if the iocb specified was not * cancelled. Will fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) { struct kioctx *ctx; struct aio_kiocb *kiocb; int ret = -EINVAL; u32 key; u64 obj = (u64)(unsigned long)iocb; if (unlikely(get_user(key, &iocb->aio_key))) return -EFAULT; if (unlikely(key != KIOCB_KEY)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) return -EINVAL; spin_lock_irq(&ctx->ctx_lock); list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { if (kiocb->ki_res.obj == obj) { ret = kiocb->ki_cancel(&kiocb->rw); list_del_init(&kiocb->ki_list); break; } } spin_unlock_irq(&ctx->ctx_lock); if (!ret) { /* * The result argument is no longer used - the io_event is * always delivered via the ring buffer. -EINPROGRESS indicates * cancellation is progress: */ ret = -EINPROGRESS; } percpu_ref_put(&ctx->users); return ret; } static long do_io_getevents(aio_context_t ctx_id, long min_nr, long nr, struct io_event __user *events, struct timespec64 *ts) { ktime_t until = ts ? timespec64_to_ktime(*ts) : KTIME_MAX; struct kioctx *ioctx = lookup_ioctx(ctx_id); long ret = -EINVAL; if (likely(ioctx)) { if (likely(min_nr <= nr && min_nr >= 0)) ret = read_events(ioctx, min_nr, nr, events, until); percpu_ref_put(&ioctx->users); } return ret; } /* io_getevents: * Attempts to read at least min_nr events and up to nr events from * the completion queue for the aio_context specified by ctx_id. If * it succeeds, the number of read events is returned. May fail with * -EINVAL if ctx_id is invalid, if min_nr is out of range, if nr is * out of range, if timeout is out of range. May fail with -EFAULT * if any of the memory specified is invalid. May return 0 or * < min_nr if the timeout specified by timeout has elapsed * before sufficient events are available, where timeout == NULL * specifies an infinite timeout. Note that the timeout pointed to by * timeout is relative. Will fail with -ENOSYS if not implemented. */ #ifdef CONFIG_64BIT SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout) { struct timespec64 ts; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) return -EFAULT; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); if (!ret && signal_pending(current)) ret = -EINTR; return ret; } #endif struct __aio_sigset { const sigset_t __user *sigmask; size_t sigsetsize; }; SYSCALL_DEFINE6(io_pgetevents, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout, const struct __aio_sigset __user *, usig) { struct __aio_sigset ksig = { NULL, }; struct timespec64 ts; bool interrupted; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(io_pgetevents_time32, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout, const struct __aio_sigset __user *, usig) { struct __aio_sigset ksig = { NULL, }; struct timespec64 ts; bool interrupted; int ret; if (timeout && unlikely(get_old_timespec32(&ts, timeout))) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, __s32, min_nr, __s32, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); if (!ret && signal_pending(current)) ret = -EINTR; return ret; } #endif #ifdef CONFIG_COMPAT struct __compat_aio_sigset { compat_uptr_t sigmask; compat_size_t sigsetsize; }; #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(io_pgetevents, compat_aio_context_t, ctx_id, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout, const struct __compat_aio_sigset __user *, usig) { struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, compat_aio_context_t, ctx_id, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout, const struct __compat_aio_sigset __user *, usig) { struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; if (timeout && get_timespec64(&t, timeout)) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif |
| 18 16 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for rejecting packets. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/icmp.h> #include <net/icmp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_REJECT.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include <linux/netfilter_bridge.h> #endif #include <net/netfilter/ipv4/nf_reject.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv4"); static unsigned int reject_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_reject_info *reject = par->targinfo; int hook = xt_hooknum(par); switch (reject->with) { case IPT_ICMP_NET_UNREACHABLE: nf_send_unreach(skb, ICMP_NET_UNREACH, hook); break; case IPT_ICMP_HOST_UNREACHABLE: nf_send_unreach(skb, ICMP_HOST_UNREACH, hook); break; case IPT_ICMP_PROT_UNREACHABLE: nf_send_unreach(skb, ICMP_PROT_UNREACH, hook); break; case IPT_ICMP_PORT_UNREACHABLE: nf_send_unreach(skb, ICMP_PORT_UNREACH, hook); break; case IPT_ICMP_NET_PROHIBITED: nf_send_unreach(skb, ICMP_NET_ANO, hook); break; case IPT_ICMP_HOST_PROHIBITED: nf_send_unreach(skb, ICMP_HOST_ANO, hook); break; case IPT_ICMP_ADMIN_PROHIBITED: nf_send_unreach(skb, ICMP_PKT_FILTERED, hook); break; case IPT_TCP_RESET: nf_send_reset(xt_net(par), par->state->sk, skb, hook); break; case IPT_ICMP_ECHOREPLY: /* Doesn't happen. */ break; } return NF_DROP; } static int reject_tg_check(const struct xt_tgchk_param *par) { const struct ipt_reject_info *rejinfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; if (rejinfo->with == IPT_ICMP_ECHOREPLY) { pr_info_ratelimited("ECHOREPLY no longer supported.\n"); return -EINVAL; } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ if (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO)) { pr_info_ratelimited("TCP_RESET invalid for non-tcp\n"); return -EINVAL; } } return 0; } static struct xt_target reject_tg_reg __read_mostly = { .name = "REJECT", .family = NFPROTO_IPV4, .target = reject_tg, .targetsize = sizeof(struct ipt_reject_info), .table = "filter", .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT), .checkentry = reject_tg_check, .me = THIS_MODULE, }; static int __init reject_tg_init(void) { return xt_register_target(&reject_tg_reg); } static void __exit reject_tg_exit(void) { xt_unregister_target(&reject_tg_reg); } module_init(reject_tg_init); module_exit(reject_tg_exit); |
| 98 8 14 14 14 14 14 14 14 14 14 14 16 10 14 14 24 102 113 68 92 92 92 77 52 52 27 4 113 23 52 113 110 110 90 113 46 46 21 21 92 92 92 92 31 49 92 29 29 29 2 2 2 8 8 8 8 18 125 97 124 124 96 123 16 16 16 16 14 16 16 14 16 14 14 14 14 13 14 14 14 14 16 16 16 16 16 2520 2471 14 17 16 116 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (c) 2020 Facebook Inc. #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> enum udp_tunnel_nic_table_entry_flags { UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), UDP_TUNNEL_NIC_ENTRY_DEL = BIT(1), UDP_TUNNEL_NIC_ENTRY_OP_FAIL = BIT(2), UDP_TUNNEL_NIC_ENTRY_FROZEN = BIT(3), }; struct udp_tunnel_nic_table_entry { __be16 port; u8 type; u8 flags; u16 use_cnt; #define UDP_TUNNEL_NIC_USE_CNT_MAX U16_MAX u8 hw_priv; }; /** * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer * @lock: protects all fields * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded */ struct udp_tunnel_nic { struct delayed_work work; struct net_device *dev; struct mutex lock; u8 need_sync:1; u8 need_replay:1; unsigned int n_tables; unsigned long missed; struct udp_tunnel_nic_table_entry *entries[] __counted_by(n_tables); }; /* We ensure all work structs are done using driver state, but not the code. * We need a workqueue we can flush before module gets removed. */ static struct workqueue_struct *udp_tunnel_nic_workqueue; static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type) { switch (type) { case UDP_TUNNEL_TYPE_VXLAN: return "vxlan"; case UDP_TUNNEL_TYPE_GENEVE: return "geneve"; case UDP_TUNNEL_TYPE_VXLAN_GPE: return "vxlan-gpe"; default: return "unknown"; } } static bool udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt == 0 && !entry->flags; } static bool udp_tunnel_nic_entry_is_present(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt && !(entry->flags & ~UDP_TUNNEL_NIC_ENTRY_FROZEN); } static bool udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry) { if (!udp_tunnel_nic_entry_is_free(entry)) entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry) { entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN; } static bool udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD | UDP_TUNNEL_NIC_ENTRY_DEL); } static void udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, struct udp_tunnel_nic_table_entry *entry, unsigned int flag) { entry->flags |= flag; utn->need_sync = 1; } static void udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry, struct udp_tunnel_info *ti) { memset(ti, 0, sizeof(*ti)); ti->port = entry->port; ti->type = entry->type; ti->hw_priv = entry->hw_priv; } static bool udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return false; return true; } static bool udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; if (!utn->missed) return false; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!test_bit(i, &utn->missed)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return true; } return false; } static void __udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; entry = &utn->entries[table][idx]; if (entry->use_cnt) udp_tunnel_nic_ti_from_entry(entry, ti); } static void __udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv; } static void udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry, int err) { bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && (!err || (err == -EEXIST && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD; if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL && (!err || (err == -ENOENT && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL; if (!err) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL; else entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL; } static void udp_tunnel_nic_device_sync_one(struct net_device *dev, struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_info ti; int err; entry = &utn->entries[table][idx]; if (!udp_tunnel_nic_entry_is_queued(entry)) return; udp_tunnel_nic_ti_from_entry(entry, &ti); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD) err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti); else err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx, &ti); udp_tunnel_nic_entry_update_done(entry, err); if (err) netdev_warn(dev, "UDP tunnel port sync failed port %d type %s: %d\n", be16_to_cpu(entry->port), udp_tunnel_nic_tunnel_type_name(entry->type), err); } static void udp_tunnel_nic_device_sync_by_port(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_device_sync_one(dev, utn, i, j); } static void udp_tunnel_nic_device_sync_by_table(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; int err; for (i = 0; i < utn->n_tables; i++) { /* Find something that needs sync in this table */ for (j = 0; j < info->tables[i].n_entries; j++) if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j])) break; if (j == info->tables[i].n_entries) continue; err = info->sync_table(dev, i); if (err) netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n", i, err); for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (udp_tunnel_nic_entry_is_queued(entry)) udp_tunnel_nic_entry_update_done(entry, err); } } } static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; if (dev->udp_tunnel_nic_info->sync_table) udp_tunnel_nic_device_sync_by_table(dev, utn); else udp_tunnel_nic_device_sync_by_port(dev, utn); utn->need_sync = 0; /* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ utn->need_replay = udp_tunnel_nic_should_replay(dev, utn); } static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; queue_delayed_work(udp_tunnel_nic_workqueue, &utn->work, 0); } static bool udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table, struct udp_tunnel_info *ti) { return table->tunnel_types & ti->type; } static bool udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i; /* Special case IPv4-only NICs */ if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY && ti->sa_family != AF_INET) return false; for (i = 0; i < utn->n_tables; i++) if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti)) return true; return false; } static int udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_table_entry *entry; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { __set_bit(i, &utn->missed); return true; } } return false; } static void udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; unsigned int from, to; WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX); /* If not going from used to unused or vice versa - all done. * For dodgy entries make sure we try to sync again (queue the entry). */ entry->use_cnt += use_cnt_adj; if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj)) return; /* Cancel the op before it was sent to the device, if possible, * otherwise we'd need to take special care to issue commands * in the same order the ports arrived. */ if (use_cnt_adj < 0) { from = UDP_TUNNEL_NIC_ENTRY_ADD; to = UDP_TUNNEL_NIC_ENTRY_DEL; } else { from = UDP_TUNNEL_NIC_ENTRY_DEL; to = UDP_TUNNEL_NIC_ENTRY_ADD; } if (entry->flags & from) { entry->flags &= ~from; if (!dodgy) return; } udp_tunnel_nic_entry_queue(utn, entry, to); } static bool udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; if (udp_tunnel_nic_entry_is_free(entry) || entry->port != ti->port || entry->type != ti->type) return false; if (udp_tunnel_nic_entry_is_frozen(entry)) return true; udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj); return true; } /* Try to find existing matching entry and adjust its use count, instead of * adding a new one. Returns true if entry was found. In case of delete the * entry may have gotten removed in the process, in which case it will be * queued for removal. */ static bool udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti, int use_cnt_adj) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti, use_cnt_adj)) return true; } return false; } static bool udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, +1); } static bool udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, -1); } static bool udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry)) continue; entry->port = ti->port; entry->type = ti->type; entry->use_cnt = 1; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); return true; } /* The different table may still fit this port in, but there * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ __set_bit(i, &utn->missed); } return false; } static void __udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) return; if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN && ti->port == htons(IANA_VXLAN_UDP_PORT)) { if (ti->type != UDP_TUNNEL_TYPE_VXLAN) netdev_warn(dev, "device assumes port 4789 will be used by vxlan tunnels\n"); return; } if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; /* It may happen that a tunnel of one type is removed and different * tunnel type tries to reuse its port before the device was informed. * Rely on utn->missed to re-add this port later. */ if (udp_tunnel_nic_has_collision(dev, utn, ti)) return; if (!udp_tunnel_nic_add_existing(dev, utn, ti)) udp_tunnel_nic_add_new(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; udp_tunnel_nic_del_existing(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int i, j; utn = dev->udp_tunnel_nic; if (!utn) return; mutex_lock(&utn->lock); utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); /* We don't release utn lock across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); } __udp_tunnel_nic_device_sync(dev, utn); mutex_unlock(&utn->lock); } static size_t __udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int j; size_t size; utn = dev->udp_tunnel_nic; if (!utn) return 0; size = 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; size += nla_total_size(0) + /* _TABLE_ENTRY */ nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ } return size; } static int __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; struct nlattr *nest; unsigned int j; utn = dev->udp_tunnel_nic; if (!utn) return 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, ilog2(utn->entries[table][j].type))) goto err_cancel; nla_nest_end(skb, nest); } return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void __udp_tunnel_nic_assert_locked(struct net_device *dev) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (utn) lockdep_assert_held(&utn->lock); } static void __udp_tunnel_nic_lock(struct net_device *dev) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (utn) mutex_lock(&utn->lock); } static void __udp_tunnel_nic_unlock(struct net_device *dev) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (utn) mutex_unlock(&utn->lock); } static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, .add_port = __udp_tunnel_nic_add_port, .del_port = __udp_tunnel_nic_del_port, .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, .assert_locked = __udp_tunnel_nic_assert_locked, .lock = __udp_tunnel_nic_lock, .unlock = __udp_tunnel_nic_unlock, }; static void udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { int adj_cnt = -utn->entries[i][j].use_cnt; if (adj_cnt) udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt); } __udp_tunnel_nic_device_sync(dev, utn); for (i = 0; i < utn->n_tables; i++) memset(utn->entries[i], 0, array_size(info->tables[i].n_entries, sizeof(**utn->entries))); WARN_ON(utn->need_sync); utn->need_replay = 0; } static void udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node; unsigned int i, j; /* Freeze all the ports we are already tracking so that the replay * does not double up the refcount. */ for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]); utn->missed = 0; utn->need_replay = 0; if (!info->shared) { udp_tunnel_get_rx_info(dev); } else { list_for_each_entry(node, &info->shared->devices, list) udp_tunnel_get_rx_info(node->dev); } for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); } static void udp_tunnel_nic_device_sync_work(struct work_struct *work) { struct udp_tunnel_nic *utn = container_of(work, struct udp_tunnel_nic, work.work); /* We cannot block on RTNL here, otherwise we would deadlock with * udp_tunnel_nic_unregister() calling cancel_delayed_work_sync() * while holding RTNL. Requeue with 1 jiffy delay if RTNL is contended. */ if (!rtnl_trylock()) { queue_delayed_work(udp_tunnel_nic_workqueue, &utn->work, 1); return; } mutex_lock(&utn->lock); __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); mutex_unlock(&utn->lock); rtnl_unlock(); } static struct udp_tunnel_nic * udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, unsigned int n_tables) { struct udp_tunnel_nic *utn; unsigned int i; utn = kzalloc_flex(*utn, entries, n_tables); if (!utn) return NULL; utn->n_tables = n_tables; INIT_DELAYED_WORK(&utn->work, udp_tunnel_nic_device_sync_work); mutex_init(&utn->lock); for (i = 0; i < n_tables; i++) { utn->entries[i] = kzalloc_objs(*utn->entries[i], info->tables[i].n_entries); if (!utn->entries[i]) goto err_free_prev_entries; } return utn; err_free_prev_entries: while (i--) kfree(utn->entries[i]); kfree(utn); return NULL; } static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) { unsigned int i; for (i = 0; i < utn->n_tables; i++) kfree(utn->entries[i]); kfree(utn); } static int udp_tunnel_nic_register(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node = NULL; struct udp_tunnel_nic *utn; unsigned int n_tables, i; BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < UDP_TUNNEL_NIC_MAX_TABLES); /* Expect use count of at most 2 (IPv4, IPv6) per device */ BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX < UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2); /* Check that the driver info is sane */ if (WARN_ON(!info->set_port != !info->unset_port) || WARN_ON(!info->set_port == !info->sync_table) || WARN_ON(!info->tables[0].n_entries)) return -EINVAL; if (WARN_ON(info->shared && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return -EINVAL; n_tables = 1; for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) continue; n_tables++; if (WARN_ON(!info->tables[i - 1].n_entries)) return -EINVAL; } /* Create UDP tunnel state structures */ if (info->shared) { node = kzalloc_obj(*node); if (!node) return -ENOMEM; node->dev = dev; } if (info->shared && info->shared->udp_tunnel_nic_info) { utn = info->shared->udp_tunnel_nic_info; } else { utn = udp_tunnel_nic_alloc(info, n_tables); if (!utn) { kfree(node); return -ENOMEM; } } if (info->shared) { if (!info->shared->udp_tunnel_nic_info) { INIT_LIST_HEAD(&info->shared->devices); info->shared->udp_tunnel_nic_info = utn; } list_add_tail(&node->list, &info->shared->devices); } utn->dev = dev; dev_hold(dev); dev->udp_tunnel_nic = utn; if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) { udp_tunnel_nic_lock(dev); udp_tunnel_get_rx_info(dev); udp_tunnel_nic_unlock(dev); } return 0; } static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; udp_tunnel_nic_lock(dev); /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ if (info->shared) { struct udp_tunnel_nic_shared_node *node, *first; list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; if (list_entry_is_head(node, &info->shared->devices, list)) { udp_tunnel_nic_unlock(dev); return; } list_del(&node->list); kfree(node); first = list_first_entry_or_null(&info->shared->devices, typeof(*first), list); if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; udp_tunnel_nic_unlock(dev); goto release_dev; } info->shared->udp_tunnel_nic_info = NULL; } /* Flush before we check work, so we don't waste time adding entries * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); udp_tunnel_nic_unlock(dev); /* Make sure no work is running or queued before freeing @utn. * The work handler uses rtnl_trylock(), so it will not deadlock * against the RTNL we are holding here. */ cancel_delayed_work_sync(&utn->work); udp_tunnel_nic_free(utn); release_dev: dev->udp_tunnel_nic = NULL; dev_put(dev); } static int udp_tunnel_nic_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); const struct udp_tunnel_nic_info *info; struct udp_tunnel_nic *utn; info = dev->udp_tunnel_nic_info; if (!info) return NOTIFY_DONE; if (event == NETDEV_REGISTER) { int err; err = udp_tunnel_nic_register(dev); if (err) netdev_warn(dev, "failed to register for UDP tunnel offloads: %d", err); return notifier_from_errno(err); } /* All other events will need the udp_tunnel_nic state */ utn = dev->udp_tunnel_nic; if (!utn) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { udp_tunnel_nic_unregister(dev, utn); return NOTIFY_OK; } /* All other events only matter if NIC has to be programmed open */ if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return NOTIFY_DONE; if (event == NETDEV_UP) { udp_tunnel_nic_lock(dev); WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { udp_tunnel_nic_lock(dev); udp_tunnel_nic_flush(dev, utn); udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } return NOTIFY_DONE; } static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = { .notifier_call = udp_tunnel_nic_netdevice_event, }; static int __init udp_tunnel_nic_init_module(void) { int err; udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; rtnl_lock(); udp_tunnel_nic_ops = &__udp_tunnel_nic_ops; rtnl_unlock(); err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block); if (err) goto err_unset_ops; return 0; err_unset_ops: rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); return err; } late_initcall(udp_tunnel_nic_init_module); static void __exit udp_tunnel_nic_cleanup_module(void) { unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block); rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); } module_exit(udp_tunnel_nic_cleanup_module); MODULE_LICENSE("GPL"); |
| 6 6 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Device core Trace Support * Copyright (C) 2021, Intel Corporation * * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM dev #if !defined(__DEV_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define __DEV_TRACE_H #include <linux/device.h> #include <linux/tracepoint.h> #include <linux/types.h> DECLARE_EVENT_CLASS(devres, TP_PROTO(struct device *dev, const char *op, void *node, const char *name, size_t size), TP_ARGS(dev, op, node, name, size), TP_STRUCT__entry( __string(devname, dev_name(dev)) __field(struct device *, dev) __field(const char *, op) __field(void *, node) __string(name, name) __field(size_t, size) ), TP_fast_assign( __assign_str(devname); __entry->op = op; __entry->node = node; __assign_str(name); __entry->size = size; ), TP_printk("%s %3s %p %s (%zu bytes)", __get_str(devname), __entry->op, __entry->node, __get_str(name), __entry->size) ); DEFINE_EVENT(devres, devres_log, TP_PROTO(struct device *dev, const char *op, void *node, const char *name, size_t size), TP_ARGS(dev, op, node, name, size) ); #endif /* __DEV_TRACE_H */ /* this part has to be here */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 1018 2 86 1345 19 10 10 1565 45 2 1559 3 577 534 9 43 600 290 405 398 373 364 10 1712 1447 16 377 376 3 1324 238 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/l3mdev/l3mdev.c - L3 master device implementation * Copyright (c) 2015 Cumulus Networks * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> */ #include <linux/netdevice.h> #include <net/fib_rules.h> #include <net/l3mdev.h> static DEFINE_SPINLOCK(l3mdev_lock); struct l3mdev_handler { lookup_by_table_id_t dev_lookup; }; static struct l3mdev_handler l3mdev_handlers[L3MDEV_TYPE_MAX + 1]; static int l3mdev_check_type(enum l3mdev_type l3type) { if (l3type <= L3MDEV_TYPE_UNSPEC || l3type > L3MDEV_TYPE_MAX) return -EINVAL; return 0; } int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn) { struct l3mdev_handler *hdlr; int res; res = l3mdev_check_type(l3type); if (res) return res; hdlr = &l3mdev_handlers[l3type]; spin_lock(&l3mdev_lock); if (hdlr->dev_lookup) { res = -EBUSY; goto unlock; } hdlr->dev_lookup = fn; res = 0; unlock: spin_unlock(&l3mdev_lock); return res; } EXPORT_SYMBOL_GPL(l3mdev_table_lookup_register); void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn) { struct l3mdev_handler *hdlr; if (l3mdev_check_type(l3type)) return; hdlr = &l3mdev_handlers[l3type]; spin_lock(&l3mdev_lock); if (hdlr->dev_lookup == fn) hdlr->dev_lookup = NULL; spin_unlock(&l3mdev_lock); } EXPORT_SYMBOL_GPL(l3mdev_table_lookup_unregister); int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id) { lookup_by_table_id_t lookup; struct l3mdev_handler *hdlr; int ifindex = -EINVAL; int res; res = l3mdev_check_type(l3type); if (res) return res; hdlr = &l3mdev_handlers[l3type]; spin_lock(&l3mdev_lock); lookup = hdlr->dev_lookup; if (!lookup) goto unlock; ifindex = lookup(net, table_id); unlock: spin_unlock(&l3mdev_lock); return ifindex; } EXPORT_SYMBOL_GPL(l3mdev_ifindex_lookup_by_table_id); /** * l3mdev_master_ifindex_rcu - get index of L3 master device * @dev: targeted interface */ int l3mdev_master_ifindex_rcu(const struct net_device *dev) { int ifindex = 0; if (!dev) return 0; if (netif_is_l3_master(dev)) { ifindex = dev->ifindex; } else if (netif_is_l3_slave(dev)) { struct net_device *master; struct net_device *_dev = (struct net_device *)dev; /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. * list_first_or_null_rcu does not handle a const arg. We aren't * making changes, just want the master device from that list so * typecast to remove the const */ master = netdev_master_upper_dev_get_rcu(_dev); if (master) ifindex = master->ifindex; } return ifindex; } EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu); /** * l3mdev_master_upper_ifindex_by_index_rcu - get index of upper l3 master * device * @net: network namespace for device index lookup * @ifindex: targeted interface */ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) { struct net_device *dev; dev = dev_get_by_index_rcu(net, ifindex); while (dev && !netif_is_l3_master(dev)) dev = netdev_master_upper_dev_get_rcu(dev); return dev ? dev->ifindex : 0; } EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu); /** * l3mdev_fib_table_rcu - get FIB table id associated with an L3 * master interface * @dev: targeted interface */ u32 l3mdev_fib_table_rcu(const struct net_device *dev) { u32 tb_id = 0; if (!dev) return 0; if (netif_is_l3_master(dev)) { if (dev->l3mdev_ops->l3mdev_fib_table) tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev); } else if (netif_is_l3_slave(dev)) { /* Users of netdev_master_upper_dev_get_rcu need non-const, * but current inet_*type functions take a const */ struct net_device *_dev = (struct net_device *) dev; const struct net_device *master; master = netdev_master_upper_dev_get_rcu(_dev); if (master && master->l3mdev_ops->l3mdev_fib_table) tb_id = master->l3mdev_ops->l3mdev_fib_table(master); } return tb_id; } EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) { struct net_device *dev; u32 tb_id = 0; if (!ifindex) return 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) tb_id = l3mdev_fib_table_rcu(dev); rcu_read_unlock(); return tb_id; } EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index); /** * l3mdev_link_scope_lookup - IPv6 route lookup based on flow for link * local and multicast addresses * @net: network namespace for device index lookup * @fl6: IPv6 flow struct for lookup * This function does not hold refcnt on the returned dst. * Caller must hold rcu_read_lock(). */ struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { struct dst_entry *dst = NULL; struct net_device *dev; WARN_ON_ONCE(!rcu_read_lock_held()); if (fl6->flowi6_oif) { dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); if (dev && netif_is_l3_slave(dev)) dev = netdev_master_upper_dev_get_rcu(dev); if (dev && netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_link_scope_lookup) dst = dev->l3mdev_ops->l3mdev_link_scope_lookup(dev, fl6); } return dst; } EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup); /** * l3mdev_fib_rule_match - Determine if flowi references an * L3 master device * @net: network namespace for device index lookup * @fl: flow struct * @arg: store the table the rule matched with here */ int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg) { struct net_device *dev; int rc = 0; /* update flow ensures flowi_l3mdev is set when relevant */ if (!fl->flowi_l3mdev) return 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, fl->flowi_l3mdev); if (dev && netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_fib_table) { arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev); rc = 1; } rcu_read_unlock(); return rc; } void l3mdev_update_flow(struct net *net, struct flowi *fl) { struct net_device *dev; rcu_read_lock(); if (fl->flowi_oif) { dev = dev_get_by_index_rcu(net, fl->flowi_oif); if (dev) { if (!fl->flowi_l3mdev) { fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev); fl->flowi_flags |= FLOWI_FLAG_L3MDEV_OIF; } /* oif set to L3mdev directs lookup to its table; * reset to avoid oif match in fib_lookup */ if (netif_is_l3_master(dev)) fl->flowi_oif = 0; goto out; } } if (fl->flowi_iif > LOOPBACK_IFINDEX && !fl->flowi_l3mdev) { dev = dev_get_by_index_rcu(net, fl->flowi_iif); if (dev) fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev); } out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(l3mdev_update_flow); |
| 1 5 2 2 2 18 18 15 2 5 5 2 1 6 1 5 6 5 6 6 5 6 1 7 5 5 1 5 13 13 13 7 7 7 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:ip,port,ip type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <net/tcp.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ /* 5 skbinfo support added */ #define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:ip,port,ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:ip,port,ip"); /* Type specific function prefix */ #define HTYPE hash_ipportip /* IPv4 variant */ /* Member elements */ struct hash_ipportip4_elem { __be32 ip; __be32 ip2; __be16 port; u8 proto; u8 padding; }; static bool hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1, const struct hash_ipportip4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->ip2 == ip2->ip2 && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipportip4_data_list(struct sk_buff *skb, const struct hash_ipportip4_elem *data) { if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip2) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_ipportip4_data_next(struct hash_ipportip4_elem *next, const struct hash_ipportip4_elem *d) { next->ip = d->ip; next->port = d->port; } /* Common functions */ #define MTYPE hash_ipportip4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_ipportip4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_ipportip4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip, ip_to = 0, p = 0, port, port_to, i = 0; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP2], &e.ip2); if (ret) return ret; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } ip_to = ip = ntohl(e.ip); if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip > ip_to) swap(ip, ip_to); } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } port_to = port = ntohs(e.port); if (with_ports && tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); } if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to;) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++, i++) { e.ip = htonl(ip); e.port = htons(p); if (i > IPSET_MAX_RANGE) { hash_ipportip4_data_next(&h->next, &e); return -ERANGE; } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } if (ip == ip_to) break; ip++; } return ret; } /* IPv6 variant */ struct hash_ipportip6_elem { union nf_inet_addr ip; union nf_inet_addr ip2; __be16 port; u8 proto; u8 padding; }; /* Common functions */ static bool hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1, const struct hash_ipportip6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipportip6_data_list(struct sk_buff *skb, const struct hash_ipportip6_elem *data) { if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_ipportip6_data_next(struct hash_ipportip6_elem *next, const struct hash_ipportip6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_ipportip6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_ipportip6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2.in6); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_ipportip6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (unlikely(tb[IPSET_ATTR_CIDR])) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (cidr != HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip2); if (ret) return ret; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_ipportip_type __read_mostly = { .name = "hash:ip,port,ip", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipportip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_IP2] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_ipportip_init(void) { return ip_set_type_register(&hash_ipportip_type); } static void __exit hash_ipportip_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_ipportip_type); } module_init(hash_ipportip_init); module_exit(hash_ipportip_fini); |
| 9 12 4 9 9 13 13 5 9 5 5 5 51 50 5 5 51 5 5 5 5 5 15 9 14 5 13 13 12 4 9 43 1 1 79 51 80 80 79 80 51 51 43 10 51 51 51 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 | // SPDX-License-Identifier: GPL-2.0-only /* * IEEE 802.1D Generic Attribute Registration Protocol (GARP) * * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/module.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/garp.h> #include <linux/unaligned.h> static unsigned int garp_join_time __read_mostly = 200; module_param(garp_join_time, uint, 0644); MODULE_PARM_DESC(garp_join_time, "Join time in ms (default 200ms)"); MODULE_DESCRIPTION("IEEE 802.1D Generic Attribute Registration Protocol (GARP)"); MODULE_LICENSE("GPL"); static const struct garp_state_trans { u8 state; u8 action; } garp_applicant_state_table[GARP_APPLICANT_MAX + 1][GARP_EVENT_MAX + 1] = { [GARP_APPLICANT_VA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_AA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_QA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_LA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_VO, .action = GARP_ACTION_S_LEAVE_EMPTY }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_VP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_VO }, }, [GARP_APPLICANT_AP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_AO }, }, [GARP_APPLICANT_QP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_QO }, }, [GARP_APPLICANT_VO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_AO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_QO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, }; static int garp_attr_cmp(const struct garp_attr *attr, const void *data, u8 len, u8 type) { if (attr->type != type) return attr->type - type; if (attr->dlen != len) return attr->dlen - len; return memcmp(attr->data, data, len); } static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = app->gid.rb_node; struct garp_attr *attr; int d; while (parent) { attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) parent = parent->rb_left; else if (d < 0) parent = parent->rb_right; else return attr; } return NULL; } static struct garp_attr *garp_attr_create(struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = NULL, **p = &app->gid.rb_node; struct garp_attr *attr; int d; while (*p) { parent = *p; attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) p = &parent->rb_left; else if (d < 0) p = &parent->rb_right; else { /* The attribute already exists; re-use it. */ return attr; } } attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); if (!attr) return attr; attr->state = GARP_APPLICANT_VO; attr->type = type; attr->dlen = len; memcpy(attr->data, data, len); rb_link_node(&attr->node, parent, p); rb_insert_color(&attr->node, &app->gid); return attr; } static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr) { rb_erase(&attr->node, &app->gid); kfree(attr); } static void garp_attr_destroy_all(struct garp_applicant *app) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_destroy(app, attr); } } static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; struct garp_pdu_hdr *gp; #define LLC_RESERVE sizeof(struct llc_pdu_un) skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev), GFP_ATOMIC); if (!skb) return -ENOMEM; skb->dev = app->dev; skb->protocol = htons(ETH_P_802_2); skb_reserve(skb, LL_RESERVED_SPACE(app->dev) + LLC_RESERVE); gp = __skb_put(skb, sizeof(*gp)); put_unaligned(htons(GARP_PROTOCOL_ID), &gp->protocol); app->pdu = skb; return 0; } static int garp_pdu_append_end_mark(struct garp_applicant *app) { if (skb_tailroom(app->pdu) < sizeof(u8)) return -1; __skb_put_u8(app->pdu, GARP_END_MARK); return 0; } static void garp_pdu_queue(struct garp_applicant *app) { if (!app->pdu) return; garp_pdu_append_end_mark(app); garp_pdu_append_end_mark(app); llc_pdu_header_init(app->pdu, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(app->pdu); llc_mac_hdr_init(app->pdu, app->dev->dev_addr, app->app->proto.group_address); skb_queue_tail(&app->queue, app->pdu); app->pdu = NULL; } static void garp_queue_xmit(struct garp_applicant *app) { struct sk_buff *skb; while ((skb = skb_dequeue(&app->queue))) dev_queue_xmit(skb); } static int garp_pdu_append_msg(struct garp_applicant *app, u8 attrtype) { struct garp_msg_hdr *gm; if (skb_tailroom(app->pdu) < sizeof(*gm)) return -1; gm = __skb_put(app->pdu, sizeof(*gm)); gm->attrtype = attrtype; garp_cb(app->pdu)->cur_type = attrtype; return 0; } static int garp_pdu_append_attr(struct garp_applicant *app, const struct garp_attr *attr, enum garp_attr_event event) { struct garp_attr_hdr *ga; unsigned int len; int err; again: if (!app->pdu) { err = garp_pdu_init(app); if (err < 0) return err; } if (garp_cb(app->pdu)->cur_type != attr->type) { if (garp_cb(app->pdu)->cur_type && garp_pdu_append_end_mark(app) < 0) goto queue; if (garp_pdu_append_msg(app, attr->type) < 0) goto queue; } len = sizeof(*ga) + attr->dlen; if (skb_tailroom(app->pdu) < len) goto queue; ga = __skb_put(app->pdu, len); ga->len = len; ga->event = event; memcpy(ga->data, attr->data, attr->dlen); return 0; queue: garp_pdu_queue(app); goto again; } static void garp_attr_event(struct garp_applicant *app, struct garp_attr *attr, enum garp_event event) { enum garp_applicant_state state; state = garp_applicant_state_table[attr->state][event].state; if (state == GARP_APPLICANT_INVALID) return; switch (garp_applicant_state_table[attr->state][event].action) { case GARP_ACTION_NONE: break; case GARP_ACTION_S_JOIN_IN: /* When appending the attribute fails, don't update state in * order to retry on next TRANSMIT_PDU event. */ if (garp_pdu_append_attr(app, attr, GARP_JOIN_IN) < 0) return; break; case GARP_ACTION_S_LEAVE_EMPTY: garp_pdu_append_attr(app, attr, GARP_LEAVE_EMPTY); /* As a pure applicant, sending a leave message implies that * the attribute was unregistered and can be destroyed. */ garp_attr_destroy(app, attr); return; default: WARN_ON(1); } attr->state = state; } int garp_request_join(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_create(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return -ENOMEM; } garp_attr_event(app, attr, GARP_EVENT_REQ_JOIN); spin_unlock_bh(&app->lock); return 0; } EXPORT_SYMBOL_GPL(garp_request_join); void garp_request_leave(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_lookup(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return; } garp_attr_event(app, attr, GARP_EVENT_REQ_LEAVE); spin_unlock_bh(&app->lock); } EXPORT_SYMBOL_GPL(garp_request_leave); static void garp_gid_event(struct garp_applicant *app, enum garp_event event) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_event(app, attr, event); } } static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; delay = get_random_u32_below(msecs_to_jiffies(garp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } static void garp_join_timer(struct timer_list *t) { struct garp_applicant *app = timer_container_of(app, t, join_timer); spin_lock(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_pdu_queue(app); spin_unlock(&app->lock); garp_queue_xmit(app); garp_join_timer_arm(app); } static int garp_pdu_parse_end_mark(struct sk_buff *skb) { if (!pskb_may_pull(skb, sizeof(u8))) return -1; if (*skb->data == GARP_END_MARK) { skb_pull(skb, sizeof(u8)); return -1; } return 0; } static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb, u8 attrtype) { const struct garp_attr_hdr *ga; struct garp_attr *attr; enum garp_event event; unsigned int dlen; if (!pskb_may_pull(skb, sizeof(*ga))) return -1; ga = (struct garp_attr_hdr *)skb->data; if (ga->len < sizeof(*ga)) return -1; if (!pskb_may_pull(skb, ga->len)) return -1; ga = (struct garp_attr_hdr *)skb->data; skb_pull(skb, ga->len); dlen = ga->len - sizeof(*ga); if (attrtype > app->app->maxattr) return 0; switch (ga->event) { case GARP_LEAVE_ALL: if (dlen != 0) return -1; garp_gid_event(app, GARP_EVENT_R_LEAVE_EMPTY); return 0; case GARP_JOIN_EMPTY: event = GARP_EVENT_R_JOIN_EMPTY; break; case GARP_JOIN_IN: event = GARP_EVENT_R_JOIN_IN; break; case GARP_LEAVE_EMPTY: event = GARP_EVENT_R_LEAVE_EMPTY; break; case GARP_EMPTY: event = GARP_EVENT_R_EMPTY; break; default: return 0; } if (dlen == 0) return -1; attr = garp_attr_lookup(app, ga->data, dlen, attrtype); if (attr == NULL) return 0; garp_attr_event(app, attr, event); return 0; } static int garp_pdu_parse_msg(struct garp_applicant *app, struct sk_buff *skb) { const struct garp_msg_hdr *gm; u8 attrtype; if (!pskb_may_pull(skb, sizeof(*gm))) return -1; gm = (struct garp_msg_hdr *)skb->data; if (gm->attrtype == 0) return -1; skb_pull(skb, sizeof(*gm)); attrtype = gm->attrtype; while (skb->len > 0) { if (garp_pdu_parse_attr(app, skb, attrtype) < 0) return -1; if (garp_pdu_parse_end_mark(skb) < 0) break; } return 0; } static void garp_pdu_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct garp_application *appl = proto->data; struct garp_port *port; struct garp_applicant *app; const struct garp_pdu_hdr *gp; port = rcu_dereference(dev->garp_port); if (!port) goto err; app = rcu_dereference(port->applicants[appl->type]); if (!app) goto err; if (!pskb_may_pull(skb, sizeof(*gp))) goto err; gp = (struct garp_pdu_hdr *)skb->data; if (get_unaligned(&gp->protocol) != htons(GARP_PROTOCOL_ID)) goto err; skb_pull(skb, sizeof(*gp)); spin_lock(&app->lock); while (skb->len > 0) { if (garp_pdu_parse_msg(app, skb) < 0) break; if (garp_pdu_parse_end_mark(skb) < 0) break; } spin_unlock(&app->lock); err: kfree_skb(skb); } static int garp_init_port(struct net_device *dev) { struct garp_port *port; port = kzalloc_obj(*port); if (!port) return -ENOMEM; rcu_assign_pointer(dev->garp_port, port); return 0; } static void garp_release_port(struct net_device *dev) { struct garp_port *port = rtnl_dereference(dev->garp_port); unsigned int i; for (i = 0; i <= GARP_APPLICATION_MAX; i++) { if (rtnl_dereference(port->applicants[i])) return; } RCU_INIT_POINTER(dev->garp_port, NULL); kfree_rcu(port, rcu); } int garp_init_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_applicant *app; int err; ASSERT_RTNL(); if (!rtnl_dereference(dev->garp_port)) { err = garp_init_port(dev); if (err < 0) goto err1; } err = -ENOMEM; app = kzalloc_obj(*app); if (!app) goto err2; err = dev_mc_add(dev, appl->proto.group_address); if (err < 0) goto err3; app->dev = dev; app->app = appl; app->gid = RB_ROOT; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->garp_port->applicants[appl->type], app); timer_setup(&app->join_timer, garp_join_timer, 0); garp_join_timer_arm(app); return 0; err3: kfree(app); err2: garp_release_port(dev); err1: return err; } EXPORT_SYMBOL_GPL(garp_init_applicant); void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); ASSERT_RTNL(); RCU_INIT_POINTER(port->applicants[appl->type], NULL); /* Delete timer and generate a final TRANSMIT_PDU event to flush out * all pending messages before the applicant is gone. */ timer_shutdown_sync(&app->join_timer); spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); garp_queue_xmit(app); dev_mc_del(dev, appl->proto.group_address); kfree_rcu(app, rcu); garp_release_port(dev); } EXPORT_SYMBOL_GPL(garp_uninit_applicant); int garp_register_application(struct garp_application *appl) { appl->proto.rcv = garp_pdu_rcv; appl->proto.data = appl; return stp_proto_register(&appl->proto); } EXPORT_SYMBOL_GPL(garp_register_application); void garp_unregister_application(struct garp_application *appl) { stp_proto_unregister(&appl->proto); } EXPORT_SYMBOL_GPL(garp_unregister_application); |
| 11 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 | // SPDX-License-Identifier: GPL-2.0 #include <linux/build_bug.h> #include <linux/errno.h> #include <linux/errname.h> #include <linux/kernel.h> #include <linux/math.h> /* * Ensure these tables do not accidentally become gigantic if some * huge errno makes it in. On most architectures, the first table will * only have about 140 entries, but mips and parisc have more sparsely * allocated errnos (with EHWPOISON = 257 on parisc, and EDQUOT = 1133 * on mips), so this wastes a bit of space on those - though we * special case the EDQUOT case. */ #define E(err) [err + BUILD_BUG_ON_ZERO(err <= 0 || err > 300)] = "-" #err static const char *names_0[] = { E(E2BIG), E(EACCES), E(EADDRINUSE), E(EADDRNOTAVAIL), E(EADV), E(EAFNOSUPPORT), E(EAGAIN), /* EWOULDBLOCK */ E(EALREADY), E(EBADE), E(EBADF), E(EBADFD), E(EBADMSG), E(EBADR), E(EBADRQC), E(EBADSLT), E(EBFONT), E(EBUSY), E(ECANCELED), /* ECANCELLED */ E(ECHILD), E(ECHRNG), E(ECOMM), E(ECONNABORTED), E(ECONNREFUSED), /* EREFUSED */ E(ECONNRESET), E(EDEADLK), /* EDEADLOCK */ #if EDEADLK != EDEADLOCK /* mips, sparc, powerpc */ E(EDEADLOCK), #endif E(EDESTADDRREQ), E(EDOM), E(EDOTDOT), #ifndef CONFIG_MIPS E(EDQUOT), #endif E(EEXIST), E(EFAULT), E(EFBIG), E(EHOSTDOWN), E(EHOSTUNREACH), E(EHWPOISON), E(EIDRM), E(EILSEQ), #ifdef EINIT E(EINIT), #endif E(EINPROGRESS), E(EINTR), E(EINVAL), E(EIO), E(EISCONN), E(EISDIR), E(EISNAM), E(EKEYEXPIRED), E(EKEYREJECTED), E(EKEYREVOKED), E(EL2HLT), E(EL2NSYNC), E(EL3HLT), E(EL3RST), E(ELIBACC), E(ELIBBAD), E(ELIBEXEC), E(ELIBMAX), E(ELIBSCN), E(ELNRNG), E(ELOOP), E(EMEDIUMTYPE), E(EMFILE), E(EMLINK), E(EMSGSIZE), E(EMULTIHOP), E(ENAMETOOLONG), E(ENAVAIL), E(ENETDOWN), E(ENETRESET), E(ENETUNREACH), E(ENFILE), E(ENOANO), E(ENOBUFS), E(ENOCSI), E(ENODATA), E(ENODEV), E(ENOENT), E(ENOEXEC), E(ENOKEY), E(ENOLCK), E(ENOLINK), E(ENOMEDIUM), E(ENOMEM), E(ENOMSG), E(ENONET), E(ENOPKG), E(ENOPROTOOPT), E(ENOSPC), E(ENOSR), E(ENOSTR), E(ENOSYS), E(ENOTBLK), E(ENOTCONN), E(ENOTDIR), E(ENOTEMPTY), E(ENOTNAM), E(ENOTRECOVERABLE), E(ENOTSOCK), E(ENOTTY), E(ENOTUNIQ), E(ENXIO), E(EOPNOTSUPP), E(EOVERFLOW), E(EOWNERDEAD), E(EPERM), E(EPFNOSUPPORT), E(EPIPE), #ifdef EPROCLIM E(EPROCLIM), #endif E(EPROTO), E(EPROTONOSUPPORT), E(EPROTOTYPE), E(ERANGE), E(EREMCHG), #ifdef EREMDEV E(EREMDEV), #endif E(EREMOTE), E(EREMOTEIO), E(ERESTART), E(ERFKILL), E(EROFS), #ifdef ERREMOTE E(ERREMOTE), #endif E(ESHUTDOWN), E(ESOCKTNOSUPPORT), E(ESPIPE), E(ESRCH), E(ESRMNT), E(ESTALE), E(ESTRPIPE), E(ETIME), E(ETIMEDOUT), E(ETOOMANYREFS), E(ETXTBSY), E(EUCLEAN), E(EUNATCH), E(EUSERS), E(EXDEV), E(EXFULL), }; #undef E #ifdef EREFUSED /* parisc */ static_assert(EREFUSED == ECONNREFUSED); #endif #ifdef ECANCELLED /* parisc */ static_assert(ECANCELLED == ECANCELED); #endif static_assert(EAGAIN == EWOULDBLOCK); /* everywhere */ #define E(err) [err - 512 + BUILD_BUG_ON_ZERO(err < 512 || err > 550)] = "-" #err static const char *names_512[] = { E(ERESTARTSYS), E(ERESTARTNOINTR), E(ERESTARTNOHAND), E(ENOIOCTLCMD), E(ERESTART_RESTARTBLOCK), E(EPROBE_DEFER), E(EOPENSTALE), E(ENOPARAM), E(EBADHANDLE), E(ENOTSYNC), E(EBADCOOKIE), E(ENOTSUPP), E(ETOOSMALL), E(ESERVERFAULT), E(EBADTYPE), E(EJUKEBOX), E(EIOCBQUEUED), E(ERECALLCONFLICT), }; #undef E static const char *__errname(unsigned err) { if (err < ARRAY_SIZE(names_0)) return names_0[err]; if (err >= 512 && err - 512 < ARRAY_SIZE(names_512)) return names_512[err - 512]; /* But why? */ if (IS_ENABLED(CONFIG_MIPS) && err == EDQUOT) /* 1133 */ return "-EDQUOT"; return NULL; } /* * errname(EIO) -> "EIO" * errname(-EIO) -> "-EIO" */ const char *errname(int err) { const char *name = __errname(abs(err)); if (!name) return NULL; return err > 0 ? name + 1 : name; } EXPORT_SYMBOL(errname); |
| 36333 30 2034 42119 42180 42119 2057 2055 4 2 4 4 4 1 1 1 4 1 4 4 4 1 3 4 3 4 4 4 1 4 4 4 4 3 1 4 4 79 76 76 77 76 76 3 1 36320 36332 36320 1 4 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/cpumask.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(). */ void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct llist_node *self; /* Prevent access to uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; lockdep_assert_preemption_disabled(); /* * The lockless insertion below relies on NMI-safe cmpxchg; * bail out in NMI on archs that don't provide it. */ if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && 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. In addition * this same per-cpu lnode can be modified through init_llist_node() * from css_rstat_flush() running on a different CPU. * * 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 * try_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. * * Please note that we can not use this_cpu_cmpxchg() here as on some * archs it is not safe against modifications from multiple CPUs. */ self = &rstatc->lnode; if (!try_cmpxchg(&rstatc->lnode.next, &self, NULL)) return; lhead = ss_lhead_cpu(css->ss, cpu); llist_add(&rstatc->lnode, lhead); } /* * BPF-facing wrapper for __css_rstat_updated(). Validate the caller-provided * CPU before passing it to the internal rstat updater. */ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { if (unlikely(cpu < 0 || cpu >= nr_cpu_ids || !cpu_possible(cpu))) return; __css_rstat_updated(css, cpu); } 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); |
| 2 2 2 2 2 1 1 4 1 2 2 1 4 1 2 1 1 1 5 1 3 1 1 1 1 2 2 2 17 17 17 1739 305 3 17 746 746 58 2 2 3 3 3 3 3 81 3 636 636 631 3 51 1076 1074 238 10 1046 234 3 1084 1084 2 250 6 4 5 5 5 1 1 1 1564 1548 43 5 712 708 31 805 805 1 870 863 32 906 897 32 3 3 7 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/export.h> #include <linux/init.h> #include <linux/udp.h> #include <linux/tcp.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/checksum.h> #include <linux/netfilter.h> #include <net/netfilter/nf_nat.h> #include <linux/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/xfrm.h> #include <net/ipv6.h> #include <net/pptp.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/nfnetlink_conntrack.h> static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype); static void __udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, struct udphdr *hdr, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, bool do_csum) { __be16 *portptr, newport; if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.udp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.udp.port; portptr = &hdr->dest; } if (do_csum) { nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); if (!hdr->check) hdr->check = CSUM_MANGLED_0; } *portptr = newport; } static bool udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); return true; } static bool sctp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_SCTP struct sctphdr *hdr; int hdrsize = 8; /* This could be an inner header returned in imcp packet; in such * cases we cannot update the checksum field since it is outside * of the 8 bytes of transport layer headers we are guaranteed. */ if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ hdr->source = tuple->src.u.sctp.port; } else { /* Get rid of dst port */ hdr->dest = tuple->dst.u.sctp.port; } if (hdrsize < sizeof(*hdr)) return true; if (skb->ip_summed != CHECKSUM_PARTIAL) { hdr->checksum = sctp_compute_cksum(skb, hdroff); skb->ip_summed = CHECKSUM_NONE; } #endif return true; } static bool tcp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct tcphdr *hdr; __be16 *portptr, newport, oldport; int hdrsize = 8; /* TCP connection tracking guarantees this much */ /* this could be a inner header returned in icmp packet; in such cases we cannot update the checksum field since it is outside of the 8 bytes of transport layer headers we are guaranteed */ if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct tcphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.tcp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.tcp.port; portptr = &hdr->dest; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false); return true; } static bool icmp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmphdr *)(skb->data + hdroff); switch (hdr->type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMP_INFO_REQUEST: case ICMP_INFO_REPLY: case ICMP_ADDRESS: case ICMP_ADDRESSREPLY: break; default: return true; } inet_proto_csum_replace2(&hdr->checksum, skb, hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; return true; } static bool icmpv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmp6hdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); nf_csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, false); hdr->icmp6_identifier = tuple->src.u.icmp.id; } return true; } /* manipulate a GRE packet according to maniptype */ static bool gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) const struct gre_base_hdr *greh; struct pptp_gre_header *pgreh; /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false; greh = (void *)skb->data + hdroff; pgreh = (struct pptp_gre_header *)greh; /* we only have destination manip of a packet, since 'source key' * is not present in the packet itself */ if (maniptype != NF_NAT_MANIP_DST) return true; switch (greh->flags & GRE_VERSION) { case GRE_VERSION_0: /* We do not currently NAT any GREv0 packets. * Try to behave like "nf_nat_proto_unknown" */ break; case GRE_VERSION_1: pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; default: pr_debug("can't nat unknown GRE version\n"); return false; } #endif return true; } static bool l4proto_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { switch (tuple->dst.protonum) { case IPPROTO_TCP: return tcp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDP: return udp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_SCTP: return sctp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMP: return icmp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMPV6: return icmpv6_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_GRE: return gre_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); } /* If we don't know protocol -- no error, pass it unmodified. */ return true; } static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { struct iphdr *iph; unsigned int hdroff; if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false; iph = (void *)skb->data + iphdroff; hdroff = iphdroff + iph->ihl * 4; if (!l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; iph = (void *)skb->data + iphdroff; if (maniptype == NF_NAT_MANIP_SRC) { csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); iph->saddr = target->src.u3.ip; } else { csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); iph->daddr = target->dst.u3.ip; } return true; } static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *ipv6h; __be16 frag_off; int hdroff; u8 nexthdr; if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false; ipv6h = (void *)skb->data + iphdroff; nexthdr = ipv6h->nexthdr; hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), &nexthdr, &frag_off); if (hdroff < 0) goto manip_addr; if ((frag_off & htons(~0x7)) == 0 && !l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; /* must reload, offset might have changed */ ipv6h = (void *)skb->data + iphdroff; manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; else ipv6h->daddr = target->dst.u3.in6; #endif return true; } unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir) { struct nf_conntrack_tuple target; /* We are aiming to look like inverse of other direction. */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (target.src.l3num) { case NFPROTO_IPV6: if (nf_nat_ipv6_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; case NFPROTO_IPV4: if (nf_nat_ipv4_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; default: WARN_ON_ONCE(1); break; } return NF_DROP; } static void nf_nat_ipv4_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); __be32 oldip, newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = iph->saddr; newip = t->src.u3.ip; } else { oldip = iph->daddr; newip = t->dst.u3.ip; } inet_proto_csum_replace4(check, skb, oldip, newip, true); } static void nf_nat_ipv6_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); const struct in6_addr *oldip, *newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = &ipv6h->saddr; newip = &t->src.u3.in6; } else { oldip = &ipv6h->daddr; newip = &t->dst.u3.in6; } inet_proto_csum_replace16(check, skb, oldip->s6_addr32, newip->s6_addr32, true); #endif } static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { switch (t->src.l3num) { case NFPROTO_IPV4: nf_nat_ipv4_csum_update(skb, iphdroff, check, t, maniptype); return; case NFPROTO_IPV6: nf_nat_ipv6_csum_update(skb, iphdroff, check, t, maniptype); return; } } static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct iphdr *iph = ip_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + ip_hdrlen(skb); skb->csum_offset = (void *)check - data; *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #if IS_ENABLED(CONFIG_IPV6) static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + (data - (void *)skb->data); skb->csum_offset = (void *)check - data; *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #endif void nf_nat_csum_recalc(struct sk_buff *skb, u8 nfproto, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { switch (nfproto) { case NFPROTO_IPV4: nf_nat_ipv4_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: nf_nat_ipv6_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #endif } WARN_ON_ONCE(1); } int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum) { struct { struct icmphdr icmp; struct iphdr ip; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); unsigned int hdrlen = ip_hdrlen(skb); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp.type == ICMP_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { /* Reloading "inside" here since manip_pkt may reallocate */ inside = (void *)skb->data + hdrlen; inside->icmp.checksum = 0; inside->icmp.checksum = csum_fold(skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); static unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; ct = nf_ct_get(skb, &ctinfo); if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, state->hook)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); return ret; } #ifdef CONFIG_XFRM static int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) { struct sock *sk = skb->sk; struct dst_entry *dst; unsigned int hh_len; struct flowi fl; int err; err = xfrm_decode_session(net, skb, &fl, family); if (err < 0) return err; dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; if (!dst_hold_safe(dst)) return -EHOSTUNREACH; if (sk && !net_eq(net, sock_net(sk))) sk = NULL; dst = xfrm_lookup(net, dst, &fl, sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_drop(skb); skb_dst_set(skb, dst); /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -ENOMEM; return 0; } #endif static bool nf_nat_inet_port_was_mangled(const struct sk_buff *skb, __be16 sport) { enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; const struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); if (!ct) return false; switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: case IPPROTO_UDP: break; default: return false; } dir = CTINFO2DIR(ctinfo); if (dir != IP_CT_DIR_ORIGINAL) return false; return ct->tuplehash[!dir].tuple.dst.u.all != sport; } static unsigned int nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { __be32 saddr = ip_hdr(skb)->saddr; struct sock *sk = skb->sk; unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_ACCEPT || !sk || inet_sk_transparent(sk)) return ret; /* skb has a socket assigned via tcp edemux. We need to check * if nf_nat_ipv4_fn() has mangled the packet in a way that * edemux would not have found this socket. * * This includes both changes to the source address and changes * to the source port, which are both handled by the * nf_nat_ipv4_fn() call above -- long after tcp/udp early demux * might have found a socket for the old (pre-snat) address. */ if (saddr != ip_hdr(skb)->saddr || nf_nat_inet_port_was_mangled(skb, sk->sk_dport)) skb_orphan(skb); /* TCP edemux obtained wrong socket */ return ret; } static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_pre_routing, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_out, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_local_fn, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_local_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, }; int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn); #if IS_ENABLED(CONFIG_IPV6) int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen) { struct { struct icmp6hdr icmp6; struct ipv6hdr ip6; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); inside = (void *)skb->data + hdrlen; inside->icmp6.icmp6_cksum = 0; inside->icmp6.icmp6_cksum = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len - hdrlen, IPPROTO_ICMPV6, skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); static unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be16 frag_off; int hdrlen; u8 nexthdr; ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would * have dropped it. Hence it's the user's responsibilty to * packet filter it out, or implement conntrack/NAT for that * protocol. 8) --RR */ if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { nexthdr = ipv6_hdr(skb)->nexthdr; hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, state->hook, hdrlen)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv6_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct in6_addr saddr = ipv6_hdr(skb)->saddr; struct sock *sk = skb->sk; unsigned int ret; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_ACCEPT || !sk || inet_sk_transparent(sk)) return ret; /* see nf_nat_ipv4_local_in */ if (ipv6_addr_cmp(&saddr, &ipv6_hdr(skb)->saddr) || nf_nat_inet_port_was_mangled(skb, sk->sk_dport)) skb_orphan(skb); return ret; } static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret, verdict; struct in6_addr daddr = ipv6_hdr(skb)->daddr; ret = nf_nat_ipv6_fn(priv, skb, state); verdict = ret & NF_VERDICT_MASK; if (verdict != NF_DROP && verdict != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); return ret; } static unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv6_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv6_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_out, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_local_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_local_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn); void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn); #endif /* CONFIG_IPV6 */ #if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT) int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops) { int ret; if (WARN_ON_ONCE(ops->pf != NFPROTO_INET)) return -EINVAL; ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); if (ret) return ret; ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); if (ret) nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); return ret; } EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn); void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn); #endif /* NFT INET NAT */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 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 | /* * videobuf2-core.c - video buffer 2 core framework * * Copyright (C) 2010 Samsung Electronics * * Author: Pawel Osciak <pawel@osciak.com> * Marek Szyprowski <m.szyprowski@samsung.com> * * The vb2_thread implementation was based on code from videobuf-dvb.c: * (c) 2004 Gerd Knorr <kraxel@bytesex.org> [SUSE Labs] * * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <media/videobuf2-core.h> #include <media/v4l2-mc.h> #include <trace/events/vb2.h> #define PLANE_INDEX_BITS 3 #define PLANE_INDEX_SHIFT (PAGE_SHIFT + PLANE_INDEX_BITS) #define PLANE_INDEX_MASK (BIT_MASK(PLANE_INDEX_BITS) - 1) #define MAX_BUFFER_INDEX BIT_MASK(30 - PLANE_INDEX_SHIFT) #define BUFFER_INDEX_MASK (MAX_BUFFER_INDEX - 1) #if BIT(PLANE_INDEX_BITS) != VIDEO_MAX_PLANES #error PLANE_INDEX_BITS order must be equal to VIDEO_MAX_PLANES #endif static int debug; module_param(debug, int, 0644); #define dprintk(q, level, fmt, arg...) \ do { \ if (debug >= level) \ pr_info("[%s] %s: " fmt, (q)->name, __func__, \ ## arg); \ } while (0) #ifdef CONFIG_VIDEO_ADV_DEBUG /* * If advanced debugging is on, then count how often each op is called * successfully, which can either be per-buffer or per-queue. * * This makes it easy to check that the 'init' and 'cleanup' * (and variations thereof) stay balanced. */ #define log_memop(vb, op) \ dprintk((vb)->vb2_queue, 2, "call_memop(%d, %s)%s\n", \ (vb)->index, #op, \ (vb)->vb2_queue->mem_ops->op ? "" : " (nop)") #define call_memop(vb, op, args...) \ ({ \ struct vb2_queue *_q = (vb)->vb2_queue; \ int err; \ \ log_memop(vb, op); \ err = _q->mem_ops->op ? _q->mem_ops->op(args) : 0; \ if (!err) \ (vb)->cnt_mem_ ## op++; \ err; \ }) #define call_ptr_memop(op, vb, args...) \ ({ \ struct vb2_queue *_q = (vb)->vb2_queue; \ void *ptr; \ \ log_memop(vb, op); \ ptr = _q->mem_ops->op ? _q->mem_ops->op(vb, args) : NULL; \ if (!IS_ERR_OR_NULL(ptr)) \ (vb)->cnt_mem_ ## op++; \ ptr; \ }) #define call_void_memop(vb, op, args...) \ ({ \ struct vb2_queue *_q = (vb)->vb2_queue; \ \ log_memop(vb, op); \ if (_q->mem_ops->op) \ _q->mem_ops->op(args); \ (vb)->cnt_mem_ ## op++; \ }) #define log_qop(q, op) \ dprintk(q, 2, "call_qop(%s)%s\n", #op, \ (q)->ops->op ? "" : " (nop)") #define call_qop(q, op, args...) \ ({ \ int err; \ \ log_qop(q, op); \ err = (q)->ops->op ? (q)->ops->op(args) : 0; \ if (!err) \ (q)->cnt_ ## op++; \ err; \ }) #define call_void_qop(q, op, args...) \ ({ \ log_qop(q, op); \ if ((q)->ops->op) \ (q)->ops->op(args); \ (q)->cnt_ ## op++; \ }) #define log_vb_qop(vb, op, args...) \ dprintk((vb)->vb2_queue, 2, "call_vb_qop(%d, %s)%s\n", \ (vb)->index, #op, \ (vb)->vb2_queue->ops->op ? "" : " (nop)") #define call_vb_qop(vb, op, args...) \ ({ \ int err; \ \ log_vb_qop(vb, op); \ err = (vb)->vb2_queue->ops->op ? \ (vb)->vb2_queue->ops->op(args) : 0; \ if (!err) \ (vb)->cnt_ ## op++; \ err; \ }) #define call_void_vb_qop(vb, op, args...) \ ({ \ log_vb_qop(vb, op); \ if ((vb)->vb2_queue->ops->op) \ (vb)->vb2_queue->ops->op(args); \ (vb)->cnt_ ## op++; \ }) #else #define call_memop(vb, op, args...) \ ((vb)->vb2_queue->mem_ops->op ? \ (vb)->vb2_queue->mem_ops->op(args) : 0) #define call_ptr_memop(op, vb, args...) \ ((vb)->vb2_queue->mem_ops->op ? \ (vb)->vb2_queue->mem_ops->op(vb, args) : NULL) #define call_void_memop(vb, op, args...) \ do { \ if ((vb)->vb2_queue->mem_ops->op) \ (vb)->vb2_queue->mem_ops->op(args); \ } while (0) #define call_qop(q, op, args...) \ ((q)->ops->op ? (q)->ops->op(args) : 0) #define call_void_qop(q, op, args...) \ do { \ if ((q)->ops->op) \ (q)->ops->op(args); \ } while (0) #define call_vb_qop(vb, op, args...) \ ((vb)->vb2_queue->ops->op ? (vb)->vb2_queue->ops->op(args) : 0) #define call_void_vb_qop(vb, op, args...) \ do { \ if ((vb)->vb2_queue->ops->op) \ (vb)->vb2_queue->ops->op(args); \ } while (0) #endif #define call_bufop(q, op, args...) \ ({ \ int ret = 0; \ if (q && q->buf_ops && q->buf_ops->op) \ ret = q->buf_ops->op(args); \ ret; \ }) #define call_void_bufop(q, op, args...) \ ({ \ if (q && q->buf_ops && q->buf_ops->op) \ q->buf_ops->op(args); \ }) static void __vb2_queue_cancel(struct vb2_queue *q); static const char *vb2_state_name(enum vb2_buffer_state s) { static const char * const state_names[] = { [VB2_BUF_STATE_DEQUEUED] = "dequeued", [VB2_BUF_STATE_IN_REQUEST] = "in request", [VB2_BUF_STATE_PREPARING] = "preparing", [VB2_BUF_STATE_QUEUED] = "queued", [VB2_BUF_STATE_ACTIVE] = "active", [VB2_BUF_STATE_DONE] = "done", [VB2_BUF_STATE_ERROR] = "error", }; if ((unsigned int)(s) < ARRAY_SIZE(state_names)) return state_names[s]; return "unknown"; } /* * __vb2_buf_mem_alloc() - allocate video memory for the given buffer */ static int __vb2_buf_mem_alloc(struct vb2_buffer *vb) { struct vb2_queue *q = vb->vb2_queue; void *mem_priv; int plane; int ret = -ENOMEM; /* * Allocate memory for all planes in this buffer * NOTE: mmapped areas should be page aligned */ for (plane = 0; plane < vb->num_planes; ++plane) { /* Memops alloc requires size to be page aligned. */ unsigned long size = PAGE_ALIGN(vb->planes[plane].length); /* Did it wrap around? */ if (size < vb->planes[plane].length) goto free; mem_priv = call_ptr_memop(alloc, vb, q->alloc_devs[plane] ? : q->dev, size); if (IS_ERR_OR_NULL(mem_priv)) { if (mem_priv) ret = PTR_ERR(mem_priv); goto free; } /* Associate allocator private data with this plane */ vb->planes[plane].mem_priv = mem_priv; } return 0; free: /* Free already allocated memory if one of the allocations failed */ for (; plane > 0; --plane) { call_void_memop(vb, put, vb->planes[plane - 1].mem_priv); vb->planes[plane - 1].mem_priv = NULL; } return ret; } /* * __vb2_buf_mem_free() - free memory of the given buffer */ static void __vb2_buf_mem_free(struct vb2_buffer *vb) { unsigned int plane; for (plane = 0; plane < vb->num_planes; ++plane) { call_void_memop(vb, put, vb->planes[plane].mem_priv); vb->planes[plane].mem_priv = NULL; dprintk(vb->vb2_queue, 3, "freed plane %d of buffer %d\n", plane, vb->index); } } /* * __vb2_buf_userptr_put() - release userspace memory associated with * a USERPTR buffer */ static void __vb2_buf_userptr_put(struct vb2_buffer *vb) { unsigned int plane; for (plane = 0; plane < vb->num_planes; ++plane) { if (vb->planes[plane].mem_priv) call_void_memop(vb, put_userptr, vb->planes[plane].mem_priv); vb->planes[plane].mem_priv = NULL; } } /* * __vb2_plane_dmabuf_put() - release memory associated with * a DMABUF shared plane */ static void __vb2_plane_dmabuf_put(struct vb2_buffer *vb, struct vb2_plane *p) { if (!p->mem_priv) return; if (!p->dbuf_duplicated) { if (p->dbuf_mapped) call_void_memop(vb, unmap_dmabuf, p->mem_priv); call_void_memop(vb, detach_dmabuf, p->mem_priv); } dma_buf_put(p->dbuf); p->mem_priv = NULL; p->dbuf = NULL; p->dbuf_mapped = 0; p->bytesused = 0; p->length = 0; p->m.fd = 0; p->data_offset = 0; p->dbuf_duplicated = false; } /* * __vb2_buf_dmabuf_put() - release memory associated with * a DMABUF shared buffer */ static void __vb2_buf_dmabuf_put(struct vb2_buffer *vb) { int plane; /* * When multiple planes share the same DMA buffer attachment, the plane * with the lowest index owns the mem_priv. * Put planes in the reversed order so that we don't leave invalid * mem_priv behind. */ for (plane = vb->num_planes - 1; plane >= 0; --plane) __vb2_plane_dmabuf_put(vb, &vb->planes[plane]); } /* * __vb2_buf_mem_prepare() - call ->prepare() on buffer's private memory * to sync caches */ static void __vb2_buf_mem_prepare(struct vb2_buffer *vb) { unsigned int plane; if (vb->synced) return; vb->synced = 1; for (plane = 0; plane < vb->num_planes; ++plane) call_void_memop(vb, prepare, vb->planes[plane].mem_priv); } /* * __vb2_buf_mem_finish() - call ->finish on buffer's private memory * to sync caches */ static void __vb2_buf_mem_finish(struct vb2_buffer *vb) { unsigned int plane; if (!vb->synced) return; vb->synced = 0; for (plane = 0; plane < vb->num_planes; ++plane) call_void_memop(vb, finish, vb->planes[plane].mem_priv); } /* * __setup_offsets() - setup unique offsets ("cookies") for every plane in * the buffer. */ static void __setup_offsets(struct vb2_buffer *vb) { struct vb2_queue *q = vb->vb2_queue; unsigned int plane; unsigned long offset = 0; /* * The offset "cookie" value has the following constraints: * - a buffer can have up to 8 planes. * - v4l2 mem2mem uses bit 30 to distinguish between * OUTPUT (aka "source", bit 30 is 0) and * CAPTURE (aka "destination", bit 30 is 1) buffers. * - must be page aligned * That led to this bit mapping when PAGE_SHIFT = 12: * |30 |29 15|14 12|11 0| * |DST_QUEUE_OFF_BASE|buffer index|plane index| 0 | * where there are 15 bits to store the buffer index. * Depending on PAGE_SHIFT value we can have fewer bits * to store the buffer index. */ offset = vb->index << PLANE_INDEX_SHIFT; for (plane = 0; plane < vb->num_planes; ++plane) { vb->planes[plane].m.offset = offset + (plane << PAGE_SHIFT); dprintk(q, 3, "buffer %d, plane %d offset 0x%08lx\n", vb->index, plane, offset); } } static void init_buffer_cache_hints(struct vb2_queue *q, struct vb2_buffer *vb) { /* * DMA exporter should take care of cache syncs, so we can avoid * explicit ->prepare()/->finish() syncs. For other ->memory types * we always need ->prepare() or/and ->finish() cache sync. */ if (q->memory == VB2_MEMORY_DMABUF) { vb->skip_cache_sync_on_finish = 1; vb->skip_cache_sync_on_prepare = 1; return; } /* * ->finish() cache sync can be avoided when queue direction is * TO_DEVICE. */ if (q->dma_dir == DMA_TO_DEVICE) vb->skip_cache_sync_on_finish = 1; } /** * vb2_queue_add_buffer() - add a buffer to a queue * @q: pointer to &struct vb2_queue with videobuf2 queue. * @vb: pointer to &struct vb2_buffer to be added to the queue. * @index: index where add vb2_buffer in the queue */ static void vb2_queue_add_buffer(struct vb2_queue *q, struct vb2_buffer *vb, unsigned int index) { WARN_ON(index >= q->max_num_buffers || test_bit(index, q->bufs_bitmap) || vb->vb2_queue); q->bufs[index] = vb; vb->index = index; vb->vb2_queue = q; set_bit(index, q->bufs_bitmap); } /** * vb2_queue_remove_buffer() - remove a buffer from a queue * @vb: pointer to &struct vb2_buffer to be removed from the queue. */ static void vb2_queue_remove_buffer(struct vb2_buffer *vb) { clear_bit(vb->index, vb->vb2_queue->bufs_bitmap); vb->vb2_queue->bufs[vb->index] = NULL; vb->vb2_queue = NULL; } /* * __vb2_queue_alloc() - allocate vb2 buffer structures and (for MMAP type) * video buffer memory for all buffers/planes on the queue and initializes the * queue * @first_index: index of the first created buffer, all newly allocated buffers * have indices in the range [first_index..first_index+count-1] * * Returns the number of buffers successfully allocated. */ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory, unsigned int num_buffers, unsigned int num_planes, const unsigned int plane_sizes[VB2_MAX_PLANES], unsigned int *first_index) { unsigned int buffer, plane; struct vb2_buffer *vb; unsigned long index = q->max_num_buffers; int ret; /* * Ensure that the number of already queue + the number of buffers already * in the queue is below q->max_num_buffers */ num_buffers = min_t(unsigned int, num_buffers, q->max_num_buffers - vb2_get_num_buffers(q)); while (num_buffers) { index = bitmap_find_next_zero_area(q->bufs_bitmap, q->max_num_buffers, 0, num_buffers, 0); if (index < q->max_num_buffers) break; /* Try to find free space for less buffers */ num_buffers--; } /* If there is no space left to allocate buffers return 0 to indicate the error */ if (!num_buffers) { *first_index = 0; return 0; } *first_index = index; for (buffer = 0; buffer < num_buffers; ++buffer) { /* Allocate vb2 buffer structures */ vb = kzalloc(q->buf_struct_size, GFP_KERNEL); if (!vb) { dprintk(q, 1, "memory alloc for buffer struct failed\n"); break; } vb->state = VB2_BUF_STATE_DEQUEUED; vb->num_planes = num_planes; vb->type = q->type; vb->memory = memory; init_buffer_cache_hints(q, vb); for (plane = 0; plane < num_planes; ++plane) { vb->planes[plane].length = plane_sizes[plane]; vb->planes[plane].min_length = plane_sizes[plane]; } vb2_queue_add_buffer(q, vb, index++); call_void_bufop(q, init_buffer, vb); /* Allocate video buffer memory for the MMAP type */ if (memory == VB2_MEMORY_MMAP) { ret = __vb2_buf_mem_alloc(vb); if (ret) { dprintk(q, 1, "failed allocating memory for buffer %d\n", buffer); vb2_queue_remove_buffer(vb); kfree(vb); break; } __setup_offsets(vb); /* * Call the driver-provided buffer initialization * callback, if given. An error in initialization * results in queue setup failure. */ ret = call_vb_qop(vb, buf_init, vb); if (ret) { dprintk(q, 1, "buffer %d %p initialization failed\n", buffer, vb); __vb2_buf_mem_free(vb); vb2_queue_remove_buffer(vb); kfree(vb); break; } } } dprintk(q, 3, "allocated %d buffers, %d plane(s) each\n", buffer, num_planes); return buffer; } /* * __vb2_free_mem() - release video buffer memory for a given range of * buffers in a given queue */ static void __vb2_free_mem(struct vb2_queue *q, unsigned int start, unsigned int count) { unsigned int i; struct vb2_buffer *vb; for (i = start; i < start + count; i++) { vb = vb2_get_buffer(q, i); if (!vb) continue; /* Free MMAP buffers or release USERPTR buffers */ if (q->memory == VB2_MEMORY_MMAP) __vb2_buf_mem_free(vb); else if (q->memory == VB2_MEMORY_DMABUF) __vb2_buf_dmabuf_put(vb); else __vb2_buf_userptr_put(vb); } } /* * __vb2_queue_free() - free @count buffers from @start index of the queue - video memory and * related information, if no buffers are left return the queue to an * uninitialized state. Might be called even if the queue has already been freed. */ static void __vb2_queue_free(struct vb2_queue *q, unsigned int start, unsigned int count) { unsigned int i; lockdep_assert_held(&q->mmap_lock); /* Call driver-provided cleanup function for each buffer, if provided */ for (i = start; i < start + count; i++) { struct vb2_buffer *vb = vb2_get_buffer(q, i); if (vb && vb->planes[0].mem_priv) call_void_vb_qop(vb, buf_cleanup, vb); } /* Release video buffer memory */ __vb2_free_mem(q, start, count); #ifdef CONFIG_VIDEO_ADV_DEBUG /* * Check that all the calls were balanced during the life-time of this * queue. If not then dump the counters to the kernel log. */ if (vb2_get_num_buffers(q)) { bool unbalanced = q->cnt_start_streaming != q->cnt_stop_streaming || q->cnt_prepare_streaming != q->cnt_unprepare_streaming; if (unbalanced) { pr_info("unbalanced counters for queue %p:\n", q); if (q->cnt_start_streaming != q->cnt_stop_streaming) pr_info(" setup: %u start_streaming: %u stop_streaming: %u\n", q->cnt_queue_setup, q->cnt_start_streaming, q->cnt_stop_streaming); if (q->cnt_prepare_streaming != q->cnt_unprepare_streaming) pr_info(" prepare_streaming: %u unprepare_streaming: %u\n", q->cnt_prepare_streaming, q->cnt_unprepare_streaming); } q->cnt_queue_setup = 0; q->cnt_prepare_streaming = 0; q->cnt_start_streaming = 0; q->cnt_stop_streaming = 0; q->cnt_unprepare_streaming = 0; } for (i = start; i < start + count; i++) { struct vb2_buffer *vb = vb2_get_buffer(q, i); bool unbalanced; if (!vb) continue; unbalanced = vb->cnt_mem_alloc != vb->cnt_mem_put || vb->cnt_mem_prepare != vb->cnt_mem_finish || vb->cnt_mem_get_userptr != vb->cnt_mem_put_userptr || vb->cnt_mem_attach_dmabuf != vb->cnt_mem_detach_dmabuf || vb->cnt_mem_map_dmabuf != vb->cnt_mem_unmap_dmabuf || vb->cnt_buf_queue != vb->cnt_buf_done || vb->cnt_buf_prepare != vb->cnt_buf_finish || vb->cnt_buf_init != vb->cnt_buf_cleanup; if (unbalanced) { pr_info("unbalanced counters for queue %p, buffer %d:\n", q, i); if (vb->cnt_buf_init != vb->cnt_buf_cleanup) pr_info(" buf_init: %u buf_cleanup: %u\n", vb->cnt_buf_init, vb->cnt_buf_cleanup); if (vb->cnt_buf_prepare != vb->cnt_buf_finish) pr_info(" buf_prepare: %u buf_finish: %u\n", vb->cnt_buf_prepare, vb->cnt_buf_finish); if (vb->cnt_buf_queue != vb->cnt_buf_done) pr_info(" buf_out_validate: %u buf_queue: %u buf_done: %u buf_request_complete: %u\n", vb->cnt_buf_out_validate, vb->cnt_buf_queue, vb->cnt_buf_done, vb->cnt_buf_request_complete); if (vb->cnt_mem_alloc != vb->cnt_mem_put) pr_info(" alloc: %u put: %u\n", vb->cnt_mem_alloc, vb->cnt_mem_put); if (vb->cnt_mem_prepare != vb->cnt_mem_finish) pr_info(" prepare: %u finish: %u\n", vb->cnt_mem_prepare, vb->cnt_mem_finish); if (vb->cnt_mem_get_userptr != vb->cnt_mem_put_userptr) pr_info(" get_userptr: %u put_userptr: %u\n", vb->cnt_mem_get_userptr, vb->cnt_mem_put_userptr); if (vb->cnt_mem_attach_dmabuf != vb->cnt_mem_detach_dmabuf) pr_info(" attach_dmabuf: %u detach_dmabuf: %u\n", vb->cnt_mem_attach_dmabuf, vb->cnt_mem_detach_dmabuf); if (vb->cnt_mem_map_dmabuf != vb->cnt_mem_unmap_dmabuf) pr_info(" map_dmabuf: %u unmap_dmabuf: %u\n", vb->cnt_mem_map_dmabuf, vb->cnt_mem_unmap_dmabuf); pr_info(" get_dmabuf: %u num_users: %u\n", vb->cnt_mem_get_dmabuf, vb->cnt_mem_num_users); } } #endif /* Free vb2 buffers */ for (i = start; i < start + count; i++) { struct vb2_buffer *vb = vb2_get_buffer(q, i); if (!vb) continue; vb2_queue_remove_buffer(vb); kfree(vb); } if (!vb2_get_num_buffers(q)) { q->memory = VB2_MEMORY_UNKNOWN; INIT_LIST_HEAD(&q->queued_list); } } bool vb2_buffer_in_use(struct vb2_queue *q, struct vb2_buffer *vb) { unsigned int plane; for (plane = 0; plane < vb->num_planes; ++plane) { void *mem_priv = vb->planes[plane].mem_priv; /* * If num_users() has not been provided, call_memop * will return 0, apparently nobody cares about this * case anyway. If num_users() returns more than 1, * we are not the only user of the plane's memory. */ if (mem_priv && call_memop(vb, num_users, mem_priv) > 1) return true; } return false; } EXPORT_SYMBOL(vb2_buffer_in_use); /* * __buffers_in_use() - return true if any buffers on the queue are in use and * the queue cannot be freed (by the means of REQBUFS(0)) call */ static bool __buffers_in_use(struct vb2_queue *q) { unsigned int buffer; for (buffer = 0; buffer < q->max_num_buffers; ++buffer) { struct vb2_buffer *vb = vb2_get_buffer(q, buffer); if (!vb) continue; if (vb2_buffer_in_use(q, vb)) return true; } return false; } void vb2_core_querybuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb) { call_void_bufop(q, fill_user_buffer, vb, pb); } EXPORT_SYMBOL_GPL(vb2_core_querybuf); /* * __verify_userptr_ops() - verify that all memory operations required for * USERPTR queue type have been provided */ static int __verify_userptr_ops(struct vb2_queue *q) { if (!(q->io_modes & VB2_USERPTR) || !q->mem_ops->get_userptr || !q->mem_ops->put_userptr) return -EINVAL; return 0; } /* * __verify_mmap_ops() - verify that all memory operations required for * MMAP queue type have been provided */ static int __verify_mmap_ops(struct vb2_queue *q) { if (!(q->io_modes & VB2_MMAP) || !q->mem_ops->alloc || !q->mem_ops->put || !q->mem_ops->mmap) return -EINVAL; return 0; } /* * __verify_dmabuf_ops() - verify that all memory operations required for * DMABUF queue type have been provided */ static int __verify_dmabuf_ops(struct vb2_queue *q) { if (!(q->io_modes & VB2_DMABUF) || !q->mem_ops->attach_dmabuf || !q->mem_ops->detach_dmabuf || !q->mem_ops->map_dmabuf || !q->mem_ops->unmap_dmabuf) return -EINVAL; return 0; } int vb2_verify_memory_type(struct vb2_queue *q, enum vb2_memory memory, unsigned int type) { if (memory != VB2_MEMORY_MMAP && memory != VB2_MEMORY_USERPTR && memory != VB2_MEMORY_DMABUF) { dprintk(q, 1, "unsupported memory type\n"); return -EINVAL; } if (type != q->type) { dprintk(q, 1, "requested type is incorrect\n"); return -EINVAL; } /* * Make sure all the required memory ops for given memory type * are available. */ if (memory == VB2_MEMORY_MMAP && __verify_mmap_ops(q)) { dprintk(q, 1, "MMAP for current setup unsupported\n"); return -EINVAL; } if (memory == VB2_MEMORY_USERPTR && __verify_userptr_ops(q)) { dprintk(q, 1, "USERPTR for current setup unsupported\n"); return -EINVAL; } if (memory == VB2_MEMORY_DMABUF && __verify_dmabuf_ops(q)) { dprintk(q, 1, "DMABUF for current setup unsupported\n"); return -EINVAL; } /* * Place the busy tests at the end: -EBUSY can be ignored when * create_bufs is called with count == 0, but count == 0 should still * do the memory and type validation. */ if (vb2_fileio_is_active(q)) { dprintk(q, 1, "file io in progress\n"); return -EBUSY; } return 0; } EXPORT_SYMBOL(vb2_verify_memory_type); static void set_queue_coherency(struct vb2_queue *q, bool non_coherent_mem) { q->non_coherent_mem = 0; if (!vb2_queue_allows_cache_hints(q)) return; q->non_coherent_mem = non_coherent_mem; } static bool verify_coherency_flags(struct vb2_queue *q, bool non_coherent_mem) { if (non_coherent_mem != q->non_coherent_mem) { dprintk(q, 1, "memory coherency model mismatch\n"); return false; } return true; } static int vb2_core_allocated_buffers_storage(struct vb2_queue *q) { if (!q->bufs) q->bufs = kzalloc_objs(*q->bufs, q->max_num_buffers); if (!q->bufs) return -ENOMEM; if (!q->bufs_bitmap) q->bufs_bitmap = bitmap_zalloc(q->max_num_buffers, GFP_KERNEL); if (!q->bufs_bitmap) { kfree(q->bufs); q->bufs = NULL; return -ENOMEM; } return 0; } static void vb2_core_free_buffers_storage(struct vb2_queue *q) { kfree(q->bufs); q->bufs = NULL; bitmap_free(q->bufs_bitmap); q->bufs_bitmap = NULL; } int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, unsigned int flags, unsigned int *count) { unsigned int num_buffers, allocated_buffers, num_planes = 0; unsigned int q_num_bufs = vb2_get_num_buffers(q); unsigned plane_sizes[VB2_MAX_PLANES] = { }; bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; unsigned int i, first_index; int ret = 0; if (q->streaming) { dprintk(q, 1, "streaming active\n"); return -EBUSY; } if (q->waiting_in_dqbuf && *count) { dprintk(q, 1, "another dup()ped fd is waiting for a buffer\n"); return -EBUSY; } if (*count == 0 || q_num_bufs != 0 || (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory) || !verify_coherency_flags(q, non_coherent_mem)) { /* * We already have buffers allocated, so first check if they * are not in use and can be freed. */ mutex_lock(&q->mmap_lock); if (debug && q->memory == VB2_MEMORY_MMAP && __buffers_in_use(q)) dprintk(q, 1, "memory in use, orphaning buffers\n"); /* * Call queue_cancel to clean up any buffers in the * QUEUED state which is possible if buffers were prepared or * queued without ever calling STREAMON. */ __vb2_queue_cancel(q); __vb2_queue_free(q, 0, q->max_num_buffers); mutex_unlock(&q->mmap_lock); q->is_busy = 0; /* * In case of REQBUFS(0) return immediately without calling * driver's queue_setup() callback and allocating resources. */ if (*count == 0) return 0; } /* * Make sure the requested values and current defaults are sane. */ num_buffers = max_t(unsigned int, *count, q->min_reqbufs_allocation); num_buffers = min_t(unsigned int, num_buffers, q->max_num_buffers); memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); /* * Set this now to ensure that drivers see the correct q->memory value * in the queue_setup op. */ mutex_lock(&q->mmap_lock); ret = vb2_core_allocated_buffers_storage(q); q->memory = memory; mutex_unlock(&q->mmap_lock); if (ret) return ret; set_queue_coherency(q, non_coherent_mem); /* * Ask the driver how many buffers and planes per buffer it requires. * Driver also sets the size and allocator context for each plane. */ ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) goto error; /* Check that driver has set sane values */ if (WARN_ON(!num_planes)) { ret = -EINVAL; goto error; } for (i = 0; i < num_planes; i++) if (WARN_ON(!plane_sizes[i])) { ret = -EINVAL; goto error; } /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes, &first_index); if (allocated_buffers == 0) { /* There shouldn't be any buffers allocated, so first_index == 0 */ WARN_ON(first_index); dprintk(q, 1, "memory allocation failed\n"); ret = -ENOMEM; goto error; } /* * There is no point in continuing if we can't allocate the minimum * number of buffers needed by this vb2_queue. */ if (allocated_buffers < q->min_reqbufs_allocation) ret = -ENOMEM; /* * Check if driver can handle the allocated number of buffers. */ if (!ret && allocated_buffers < num_buffers) { num_buffers = allocated_buffers; /* * num_planes is set by the previous queue_setup(), but since it * signals to queue_setup() whether it is called from create_bufs() * vs reqbufs() we zero it here to signal that queue_setup() is * called for the reqbufs() case. */ num_planes = 0; ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (!ret && allocated_buffers < num_buffers) ret = -ENOMEM; /* * Either the driver has accepted a smaller number of buffers, * or .queue_setup() returned an error */ } mutex_lock(&q->mmap_lock); if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' * from already queued buffers and it will reset q->memory to * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, first_index, allocated_buffers); mutex_unlock(&q->mmap_lock); return ret; } mutex_unlock(&q->mmap_lock); /* * Return the number of successfully allocated buffers * to the userspace. */ *count = allocated_buffers; q->waiting_for_buffers = !q->is_output; q->is_busy = 1; return 0; error: mutex_lock(&q->mmap_lock); q->memory = VB2_MEMORY_UNKNOWN; mutex_unlock(&q->mmap_lock); vb2_core_free_buffers_storage(q); return ret; } EXPORT_SYMBOL_GPL(vb2_core_reqbufs); int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, unsigned int flags, unsigned int *count, unsigned int requested_planes, const unsigned int requested_sizes[], unsigned int *first_index) { unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; unsigned int q_num_bufs = vb2_get_num_buffers(q); bool no_previous_buffers = !q_num_bufs; int ret = 0; if (q_num_bufs == q->max_num_buffers) { dprintk(q, 1, "maximum number of buffers already allocated\n"); return -ENOBUFS; } if (no_previous_buffers) { if (q->waiting_in_dqbuf && *count) { dprintk(q, 1, "another dup()ped fd is waiting for a buffer\n"); return -EBUSY; } memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); /* * Set this now to ensure that drivers see the correct q->memory * value in the queue_setup op. */ mutex_lock(&q->mmap_lock); ret = vb2_core_allocated_buffers_storage(q); q->memory = memory; mutex_unlock(&q->mmap_lock); if (ret) return ret; q->waiting_for_buffers = !q->is_output; set_queue_coherency(q, non_coherent_mem); } else { if (q->memory != memory) { dprintk(q, 1, "memory model mismatch\n"); return -EINVAL; } if (!verify_coherency_flags(q, non_coherent_mem)) return -EINVAL; } num_buffers = min(*count, q->max_num_buffers - q_num_bufs); if (requested_planes && requested_sizes) { num_planes = requested_planes; memcpy(plane_sizes, requested_sizes, sizeof(plane_sizes)); } /* * Ask the driver, whether the requested number of buffers, planes per * buffer and their sizes are acceptable */ ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) goto error; /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes, first_index); if (allocated_buffers == 0) { dprintk(q, 1, "memory allocation failed\n"); ret = -ENOMEM; goto error; } /* * Check if driver can handle the so far allocated number of buffers. */ if (allocated_buffers < num_buffers) { num_buffers = allocated_buffers; /* * num_buffers contains the total number of buffers, that the * queue driver has set up */ ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (!ret && allocated_buffers < num_buffers) ret = -ENOMEM; /* * Either the driver has accepted a smaller number of buffers, * or .queue_setup() returned an error */ } mutex_lock(&q->mmap_lock); if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' * from already queued buffers and it will reset q->memory to * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, *first_index, allocated_buffers); mutex_unlock(&q->mmap_lock); return -ENOMEM; } mutex_unlock(&q->mmap_lock); /* * Return the number of successfully allocated buffers * to the userspace. */ *count = allocated_buffers; q->is_busy = 1; return 0; error: if (no_previous_buffers) { mutex_lock(&q->mmap_lock); q->memory = VB2_MEMORY_UNKNOWN; mutex_unlock(&q->mmap_lock); } return ret; } EXPORT_SYMBOL_GPL(vb2_core_create_bufs); void *vb2_plane_vaddr(struct vb2_buffer *vb, unsigned int plane_no) { if (plane_no >= vb->num_planes || !vb->planes[plane_no].mem_priv) return NULL; return call_ptr_memop(vaddr, vb, vb->planes[plane_no].mem_priv); } EXPORT_SYMBOL_GPL(vb2_plane_vaddr); void *vb2_plane_cookie(struct vb2_buffer *vb, unsigned int plane_no) { if (plane_no >= vb->num_planes || !vb->planes[plane_no].mem_priv) return NULL; return call_ptr_memop(cookie, vb, vb->planes[plane_no].mem_priv); } EXPORT_SYMBOL_GPL(vb2_plane_cookie); void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state) { struct vb2_queue *q = vb->vb2_queue; unsigned long flags; if (WARN_ON(vb->state != VB2_BUF_STATE_ACTIVE)) return; if (WARN_ON(state != VB2_BUF_STATE_DONE && state != VB2_BUF_STATE_ERROR && state != VB2_BUF_STATE_QUEUED)) state = VB2_BUF_STATE_ERROR; #ifdef CONFIG_VIDEO_ADV_DEBUG /* * Although this is not a callback, it still does have to balance * with the buf_queue op. So update this counter manually. */ vb->cnt_buf_done++; #endif dprintk(q, 4, "done processing on buffer %d, state: %s\n", vb->index, vb2_state_name(state)); if (state != VB2_BUF_STATE_QUEUED) __vb2_buf_mem_finish(vb); spin_lock_irqsave(&q->done_lock, flags); if (state == VB2_BUF_STATE_QUEUED) { vb->state = VB2_BUF_STATE_QUEUED; } else { /* Add the buffer to the done buffers list */ list_add_tail(&vb->done_entry, &q->done_list); vb->state = state; } atomic_dec(&q->owned_by_drv_count); if (state != VB2_BUF_STATE_QUEUED && vb->req_obj.req) { media_request_object_unbind(&vb->req_obj); media_request_object_put(&vb->req_obj); } spin_unlock_irqrestore(&q->done_lock, flags); trace_vb2_buf_done(q, vb); switch (state) { case VB2_BUF_STATE_QUEUED: return; default: /* Inform any processes that may be waiting for buffers */ wake_up(&q->done_wq); break; } } EXPORT_SYMBOL_GPL(vb2_buffer_done); void vb2_discard_done(struct vb2_queue *q) { struct vb2_buffer *vb; unsigned long flags; spin_lock_irqsave(&q->done_lock, flags); list_for_each_entry(vb, &q->done_list, done_entry) vb->state = VB2_BUF_STATE_ERROR; spin_unlock_irqrestore(&q->done_lock, flags); } EXPORT_SYMBOL_GPL(vb2_discard_done); /* * __prepare_mmap() - prepare an MMAP buffer */ static int __prepare_mmap(struct vb2_buffer *vb) { int ret = 0; ret = call_bufop(vb->vb2_queue, fill_vb2_buffer, vb, vb->planes); return ret ? ret : call_vb_qop(vb, buf_prepare, vb); } /* * __prepare_userptr() - prepare a USERPTR buffer */ static int __prepare_userptr(struct vb2_buffer *vb) { struct vb2_plane planes[VB2_MAX_PLANES]; struct vb2_queue *q = vb->vb2_queue; void *mem_priv; unsigned int plane; int ret = 0; bool reacquired = vb->planes[0].mem_priv == NULL; memset(planes, 0, sizeof(planes[0]) * vb->num_planes); /* Copy relevant information provided by the userspace */ ret = call_bufop(vb->vb2_queue, fill_vb2_buffer, vb, planes); if (ret) return ret; for (plane = 0; plane < vb->num_planes; ++plane) { /* Skip the plane if already verified */ if (vb->planes[plane].m.userptr && vb->planes[plane].m.userptr == planes[plane].m.userptr && vb->planes[plane].length == planes[plane].length) continue; dprintk(q, 3, "userspace address for plane %d changed, reacquiring memory\n", plane); /* Check if the provided plane buffer is large enough */ if (planes[plane].length < vb->planes[plane].min_length) { dprintk(q, 1, "provided buffer size %u is less than setup size %u for plane %d\n", planes[plane].length, vb->planes[plane].min_length, plane); ret = -EINVAL; goto err; } /* Release previously acquired memory if present */ if (vb->planes[plane].mem_priv) { if (!reacquired) { reacquired = true; vb->copied_timestamp = 0; call_void_vb_qop(vb, buf_cleanup, vb); } call_void_memop(vb, put_userptr, vb->planes[plane].mem_priv); } vb->planes[plane].mem_priv = NULL; vb->planes[plane].bytesused = 0; vb->planes[plane].length = 0; vb->planes[plane].m.userptr = 0; vb->planes[plane].data_offset = 0; /* Acquire each plane's memory */ mem_priv = call_ptr_memop(get_userptr, vb, q->alloc_devs[plane] ? : q->dev, planes[plane].m.userptr, planes[plane].length); if (IS_ERR(mem_priv)) { dprintk(q, 1, "failed acquiring userspace memory for plane %d\n", plane); ret = PTR_ERR(mem_priv); goto err; } vb->planes[plane].mem_priv = mem_priv; } /* * Now that everything is in order, copy relevant information * provided by userspace. */ for (plane = 0; plane < vb->num_planes; ++plane) { vb->planes[plane].bytesused = planes[plane].bytesused; vb->planes[plane].length = planes[plane].length; vb->planes[plane].m.userptr = planes[plane].m.userptr; vb->planes[plane].data_offset = planes[plane].data_offset; } if (reacquired) { /* * One or more planes changed, so we must call buf_init to do * the driver-specific initialization on the newly acquired * buffer, if provided. */ ret = call_vb_qop(vb, buf_init, vb); if (ret) { dprintk(q, 1, "buffer initialization failed\n"); goto err; } } ret = call_vb_qop(vb, buf_prepare, vb); if (ret) { dprintk(q, 1, "buffer preparation failed\n"); call_void_vb_qop(vb, buf_cleanup, vb); goto err; } return 0; err: /* In case of errors, release planes that were already acquired */ for (plane = 0; plane < vb->num_planes; ++plane) { if (vb->planes[plane].mem_priv) call_void_memop(vb, put_userptr, vb->planes[plane].mem_priv); vb->planes[plane].mem_priv = NULL; vb->planes[plane].m.userptr = 0; vb->planes[plane].length = 0; } return ret; } /* * __prepare_dmabuf() - prepare a DMABUF buffer */ static int __prepare_dmabuf(struct vb2_buffer *vb) { struct vb2_plane planes[VB2_MAX_PLANES]; struct vb2_queue *q = vb->vb2_queue; void *mem_priv; unsigned int plane, i; int ret = 0; bool reacquired = vb->planes[0].mem_priv == NULL; memset(planes, 0, sizeof(planes[0]) * vb->num_planes); /* Copy relevant information provided by the userspace */ ret = call_bufop(vb->vb2_queue, fill_vb2_buffer, vb, planes); if (ret) return ret; for (plane = 0; plane < vb->num_planes; ++plane) { struct dma_buf *dbuf = dma_buf_get(planes[plane].m.fd); planes[plane].dbuf = dbuf; if (IS_ERR_OR_NULL(dbuf)) { dprintk(q, 1, "invalid dmabuf fd for plane %d\n", plane); ret = -EINVAL; goto err_put_planes; } /* use DMABUF size if length is not provided */ if (planes[plane].length == 0) planes[plane].length = dbuf->size; if (planes[plane].length < vb->planes[plane].min_length) { dprintk(q, 1, "invalid dmabuf length %u for plane %d, minimum length %u\n", planes[plane].length, plane, vb->planes[plane].min_length); ret = -EINVAL; goto err_put_planes; } /* Skip the plane if already verified */ if (dbuf == vb->planes[plane].dbuf && vb->planes[plane].length == planes[plane].length) continue; dprintk(q, 3, "buffer for plane %d changed\n", plane); reacquired = true; } if (reacquired) { if (vb->planes[0].mem_priv) { vb->copied_timestamp = 0; call_void_vb_qop(vb, buf_cleanup, vb); __vb2_buf_dmabuf_put(vb); } for (plane = 0; plane < vb->num_planes; ++plane) { /* * This is an optimization to reduce dma_buf attachment/mapping. * When the same dma_buf is used for multiple planes, there is no need * to create duplicated attachments. */ for (i = 0; i < plane; ++i) { if (planes[plane].dbuf == vb->planes[i].dbuf && q->alloc_devs[plane] == q->alloc_devs[i]) { vb->planes[plane].dbuf_duplicated = true; vb->planes[plane].dbuf = vb->planes[i].dbuf; vb->planes[plane].mem_priv = vb->planes[i].mem_priv; break; } } if (vb->planes[plane].dbuf_duplicated) continue; /* Acquire each plane's memory */ mem_priv = call_ptr_memop(attach_dmabuf, vb, q->alloc_devs[plane] ? : q->dev, planes[plane].dbuf, planes[plane].length); if (IS_ERR(mem_priv)) { dprintk(q, 1, "failed to attach dmabuf\n"); ret = PTR_ERR(mem_priv); goto err_put_vb2_buf; } vb->planes[plane].dbuf = planes[plane].dbuf; vb->planes[plane].mem_priv = mem_priv; /* * This pins the buffer(s) with dma_buf_map_attachment()). It's done * here instead just before the DMA, while queueing the buffer(s) so * userspace knows sooner rather than later if the dma-buf map fails. */ ret = call_memop(vb, map_dmabuf, vb->planes[plane].mem_priv); if (ret) { dprintk(q, 1, "failed to map dmabuf for plane %d\n", plane); goto err_put_vb2_buf; } vb->planes[plane].dbuf_mapped = 1; } } else { for (plane = 0; plane < vb->num_planes; ++plane) dma_buf_put(planes[plane].dbuf); } /* * Now that everything is in order, copy relevant information * provided by userspace. */ for (plane = 0; plane < vb->num_planes; ++plane) { vb->planes[plane].bytesused = planes[plane].bytesused; vb->planes[plane].length = planes[plane].length; vb->planes[plane].m.fd = planes[plane].m.fd; vb->planes[plane].data_offset = planes[plane].data_offset; } if (reacquired) { /* * Call driver-specific initialization on the newly acquired buffer, * if provided. */ ret = call_vb_qop(vb, buf_init, vb); if (ret) { dprintk(q, 1, "buffer initialization failed\n"); goto err_put_vb2_buf; } } ret = call_vb_qop(vb, buf_prepare, vb); if (ret) { dprintk(q, 1, "buffer preparation failed\n"); call_void_vb_qop(vb, buf_cleanup, vb); goto err_put_vb2_buf; } return 0; err_put_planes: for (plane = 0; plane < vb->num_planes; ++plane) { if (!IS_ERR_OR_NULL(planes[plane].dbuf)) dma_buf_put(planes[plane].dbuf); } err_put_vb2_buf: /* In case of errors, release planes that were already acquired */ __vb2_buf_dmabuf_put(vb); return ret; } /* * __enqueue_in_driver() - enqueue a vb2_buffer in driver for processing */ static void __enqueue_in_driver(struct vb2_buffer *vb) { struct vb2_queue *q = vb->vb2_queue; vb->state = VB2_BUF_STATE_ACTIVE; atomic_inc(&q->owned_by_drv_count); trace_vb2_buf_queue(q, vb); call_void_vb_qop(vb, buf_queue, vb); } static int __buf_prepare(struct vb2_buffer *vb) { struct vb2_queue *q = vb->vb2_queue; enum vb2_buffer_state orig_state = vb->state; int ret; if (q->error) { dprintk(q, 1, "fatal error occurred on queue\n"); return -EIO; } if (vb->prepared) return 0; WARN_ON(vb->synced); if (q->is_output) { ret = call_vb_qop(vb, buf_out_validate, vb); if (ret) { dprintk(q, 1, "buffer validation failed\n"); return ret; } } vb->state = VB2_BUF_STATE_PREPARING; switch (q->memory) { case VB2_MEMORY_MMAP: ret = __prepare_mmap(vb); break; case VB2_MEMORY_USERPTR: ret = __prepare_userptr(vb); break; case VB2_MEMORY_DMABUF: ret = __prepare_dmabuf(vb); break; default: WARN(1, "Invalid queue type\n"); ret = -EINVAL; break; } if (ret) { dprintk(q, 1, "buffer preparation failed: %d\n", ret); vb->state = orig_state; return ret; } __vb2_buf_mem_prepare(vb); vb->prepared = 1; vb->state = orig_state; return 0; } static int vb2_req_prepare(struct media_request_object *obj) { struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj); int ret; if (WARN_ON(vb->state != VB2_BUF_STATE_IN_REQUEST)) return -EINVAL; mutex_lock(vb->vb2_queue->lock); ret = __buf_prepare(vb); mutex_unlock(vb->vb2_queue->lock); return ret; } static void __vb2_dqbuf(struct vb2_buffer *vb); static void vb2_req_unprepare(struct media_request_object *obj) { struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj); mutex_lock(vb->vb2_queue->lock); __vb2_dqbuf(vb); vb->state = VB2_BUF_STATE_IN_REQUEST; mutex_unlock(vb->vb2_queue->lock); WARN_ON(!vb->req_obj.req); } static void vb2_req_queue(struct media_request_object *obj) { struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj); int err; mutex_lock(vb->vb2_queue->lock); /* * There is no method to propagate an error from vb2_core_qbuf(), * so if this returns a non-0 value, then WARN. * * The only exception is -EIO which is returned if q->error is * set. We just ignore that, and expect this will be caught the * next time vb2_req_prepare() is called. */ err = vb2_core_qbuf(vb->vb2_queue, vb, NULL, NULL); WARN_ON_ONCE(err && err != -EIO); mutex_unlock(vb->vb2_queue->lock); } static void vb2_req_unbind(struct media_request_object *obj) { struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj); if (vb->state == VB2_BUF_STATE_IN_REQUEST) call_void_bufop(vb->vb2_queue, init_buffer, vb); } static void vb2_req_release(struct media_request_object *obj) { struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj); if (vb->state == VB2_BUF_STATE_IN_REQUEST) { vb->state = VB2_BUF_STATE_DEQUEUED; if (vb->request) media_request_put(vb->request); vb->request = NULL; } } static const struct media_request_object_ops vb2_core_req_ops = { .prepare = vb2_req_prepare, .unprepare = vb2_req_unprepare, .queue = vb2_req_queue, .unbind = vb2_req_unbind, .release = vb2_req_release, }; bool vb2_request_object_is_buffer(struct media_request_object *obj) { return obj->ops == &vb2_core_req_ops; } EXPORT_SYMBOL_GPL(vb2_request_object_is_buffer); unsigned int vb2_request_buffer_cnt(struct media_request *req) { struct media_request_object *obj; unsigned long flags; unsigned int buffer_cnt = 0; spin_lock_irqsave(&req->lock, flags); list_for_each_entry(obj, &req->objects, list) if (vb2_request_object_is_buffer(obj)) buffer_cnt++; spin_unlock_irqrestore(&req->lock, flags); return buffer_cnt; } EXPORT_SYMBOL_GPL(vb2_request_buffer_cnt); int vb2_core_prepare_buf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb) { int ret; if (vb->state != VB2_BUF_STATE_DEQUEUED) { dprintk(q, 1, "invalid buffer state %s\n", vb2_state_name(vb->state)); return -EINVAL; } if (vb->prepared) { dprintk(q, 1, "buffer already prepared\n"); return -EINVAL; } ret = __buf_prepare(vb); if (ret) return ret; /* Fill buffer information for the userspace */ call_void_bufop(q, fill_user_buffer, vb, pb); dprintk(q, 2, "prepare of buffer %d succeeded\n", vb->index); return 0; } EXPORT_SYMBOL_GPL(vb2_core_prepare_buf); int vb2_core_remove_bufs(struct vb2_queue *q, unsigned int start, unsigned int count) { unsigned int i, ret = 0; unsigned int q_num_bufs = vb2_get_num_buffers(q); if (count == 0) return 0; if (count > q_num_bufs) return -EINVAL; if (start > q->max_num_buffers - count) return -EINVAL; mutex_lock(&q->mmap_lock); /* Check that all buffers in the range exist */ for (i = start; i < start + count; i++) { struct vb2_buffer *vb = vb2_get_buffer(q, i); if (!vb) { ret = -EINVAL; goto unlock; } if (vb->state != VB2_BUF_STATE_DEQUEUED) { ret = -EBUSY; goto unlock; } } __vb2_queue_free(q, start, count); dprintk(q, 2, "%u buffers removed\n", count); unlock: mutex_unlock(&q->mmap_lock); return ret; } EXPORT_SYMBOL_GPL(vb2_core_remove_bufs); /* * vb2_start_streaming() - Attempt to start streaming. * @q: videobuf2 queue * * Attempt to start streaming. When this function is called there must be * at least q->min_queued_buffers queued up (i.e. the minimum * number of buffers required for the DMA engine to function). If the * @start_streaming op fails it is supposed to return all the driver-owned * buffers back to vb2 in state QUEUED. Check if that happened and if * not warn and reclaim them forcefully. */ static int vb2_start_streaming(struct vb2_queue *q) { struct vb2_buffer *vb; int ret; /* * If any buffers were queued before streamon, * we can now pass them to driver for processing. */ list_for_each_entry(vb, &q->queued_list, queued_entry) __enqueue_in_driver(vb); /* Tell the driver to start streaming */ q->start_streaming_called = 1; ret = call_qop(q, start_streaming, q, atomic_read(&q->owned_by_drv_count)); if (!ret) return 0; q->start_streaming_called = 0; dprintk(q, 1, "driver refused to start streaming\n"); /* * If you see this warning, then the driver isn't cleaning up properly * after a failed start_streaming(). See the start_streaming() * documentation in videobuf2-core.h for more information how buffers * should be returned to vb2 in start_streaming(). */ if (WARN_ON(atomic_read(&q->owned_by_drv_count))) { unsigned i; /* * Forcefully reclaim buffers if the driver did not * correctly return them to vb2. */ for (i = 0; i < q->max_num_buffers; ++i) { vb = vb2_get_buffer(q, i); if (!vb) continue; if (vb->state == VB2_BUF_STATE_ACTIVE) vb2_buffer_done(vb, VB2_BUF_STATE_QUEUED); } /* Must be zero now */ WARN_ON(atomic_read(&q->owned_by_drv_count)); } /* * If done_list is not empty, then start_streaming() didn't call * vb2_buffer_done(vb, VB2_BUF_STATE_QUEUED) but STATE_ERROR or * STATE_DONE. */ WARN_ON(!list_empty(&q->done_list)); return ret; } int vb2_core_qbuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb, struct media_request *req) { enum vb2_buffer_state orig_state; int ret; if (q->error) { dprintk(q, 1, "fatal error occurred on queue\n"); return -EIO; } if (!req && vb->state != VB2_BUF_STATE_IN_REQUEST && q->requires_requests) { dprintk(q, 1, "qbuf requires a request\n"); return -EBADR; } if ((req && q->uses_qbuf) || (!req && vb->state != VB2_BUF_STATE_IN_REQUEST && q->uses_requests)) { dprintk(q, 1, "queue in wrong mode (qbuf vs requests)\n"); return -EBUSY; } if (req) { int ret; q->uses_requests = 1; if (vb->state != VB2_BUF_STATE_DEQUEUED) { dprintk(q, 1, "buffer %d not in dequeued state\n", vb->index); return -EINVAL; } if (q->is_output && !vb->prepared) { ret = call_vb_qop(vb, buf_out_validate, vb); if (ret) { dprintk(q, 1, "buffer validation failed\n"); return ret; } } media_request_object_init(&vb->req_obj); /* Make sure the request is in a safe state for updating. */ ret = media_request_lock_for_update(req); if (ret) return ret; ret = media_request_object_bind(req, &vb2_core_req_ops, q, true, &vb->req_obj); media_request_unlock_for_update(req); if (ret) return ret; vb->state = VB2_BUF_STATE_IN_REQUEST; /* * Increment the refcount and store the request. * The request refcount is decremented again when the * buffer is dequeued. This is to prevent vb2_buffer_done() * from freeing the request from interrupt context, which can * happen if the application closed the request fd after * queueing the request. */ media_request_get(req); vb->request = req; /* Fill buffer information for the userspace */ if (pb) { call_void_bufop(q, copy_timestamp, vb, pb); call_void_bufop(q, fill_user_buffer, vb, pb); } dprintk(q, 2, "qbuf of buffer %d succeeded\n", vb->index); return 0; } if (vb->state != VB2_BUF_STATE_IN_REQUEST) q->uses_qbuf = 1; switch (vb->state) { case VB2_BUF_STATE_DEQUEUED: case VB2_BUF_STATE_IN_REQUEST: if (!vb->prepared) { ret = __buf_prepare(vb); if (ret) return ret; } break; case VB2_BUF_STATE_PREPARING: dprintk(q, 1, "buffer still being prepared\n"); return -EINVAL; default: dprintk(q, 1, "invalid buffer state %s\n", vb2_state_name(vb->state)); return -EINVAL; } /* * Add to the queued buffers list, a buffer will stay on it until * dequeued in dqbuf. */ orig_state = vb->state; list_add_tail(&vb->queued_entry, &q->queued_list); q->queued_count++; q->waiting_for_buffers = false; vb->state = VB2_BUF_STATE_QUEUED; if (pb) call_void_bufop(q, copy_timestamp, vb, pb); trace_vb2_qbuf(q, vb); /* * If already streaming, give the buffer to driver for processing. * If not, the buffer will be given to driver on next streamon. */ if (q->start_streaming_called) __enqueue_in_driver(vb); /* Fill buffer information for the userspace */ if (pb) call_void_bufop(q, fill_user_buffer, vb, pb); /* * If streamon has been called, and we haven't yet called * start_streaming() since not enough buffers were queued, and * we now have reached the minimum number of queued buffers, * then we can finally call start_streaming(). */ if (q->streaming && !q->start_streaming_called && q->queued_count >= q->min_queued_buffers) { ret = vb2_start_streaming(q); if (ret) { /* * Since vb2_core_qbuf will return with an error, * we should return it to state DEQUEUED since * the error indicates that the buffer wasn't queued. */ list_del(&vb->queued_entry); q->queued_count--; vb->state = orig_state; return ret; } } dprintk(q, 2, "qbuf of buffer %d succeeded\n", vb->index); return 0; } EXPORT_SYMBOL_GPL(vb2_core_qbuf); /* * __vb2_wait_for_done_vb() - wait for a buffer to become available * for dequeuing * * Will sleep if required for nonblocking == false. */ static int __vb2_wait_for_done_vb(struct vb2_queue *q, int nonblocking) { /* * All operations on vb_done_list are performed under done_lock * spinlock protection. However, buffers may be removed from * it and returned to userspace only while holding both driver's * lock and the done_lock spinlock. Thus we can be sure that as * long as we hold the driver's lock, the list will remain not * empty if list_empty() check succeeds. */ for (;;) { int ret; if (q->waiting_in_dqbuf) { dprintk(q, 1, "another dup()ped fd is waiting for a buffer\n"); return -EBUSY; } if (!q->streaming) { dprintk(q, 1, "streaming off, will not wait for buffers\n"); return -EINVAL; } if (q->error) { dprintk(q, 1, "Queue in error state, will not wait for buffers\n"); return -EIO; } if (q->last_buffer_dequeued) { dprintk(q, 3, "last buffer dequeued already, will not wait for buffers\n"); return -EPIPE; } if (!list_empty(&q->done_list)) { /* * Found a buffer that we were waiting for. */ break; } if (nonblocking) { dprintk(q, 3, "nonblocking and no buffers to dequeue, will not wait\n"); return -EAGAIN; } q->waiting_in_dqbuf = 1; /* * We are streaming and blocking, wait for another buffer to * become ready or for streamoff. Driver's lock is released to * allow streamoff or qbuf to be called while waiting. */ mutex_unlock(q->lock); /* * All locks have been released, it is safe to sleep now. */ dprintk(q, 3, "will sleep waiting for buffers\n"); ret = wait_event_interruptible(q->done_wq, !list_empty(&q->done_list) || !q->streaming || q->error); mutex_lock(q->lock); q->waiting_in_dqbuf = 0; /* * We need to reevaluate both conditions again after reacquiring * the locks or return an error if one occurred. */ if (ret) { dprintk(q, 1, "sleep was interrupted\n"); return ret; } } return 0; } /* * __vb2_get_done_vb() - get a buffer ready for dequeuing * * Will sleep if required for nonblocking == false. */ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb, void *pb, int nonblocking) { unsigned long flags; int ret = 0; /* * Wait for at least one buffer to become available on the done_list. */ ret = __vb2_wait_for_done_vb(q, nonblocking); if (ret) return ret; /* * Driver's lock has been held since we last verified that done_list * is not empty, so no need for another list_empty(done_list) check. */ spin_lock_irqsave(&q->done_lock, flags); *vb = list_first_entry(&q->done_list, struct vb2_buffer, done_entry); /* * Only remove the buffer from done_list if all planes can be * handled. Some cases such as V4L2 file I/O and DVB have pb * == NULL; skip the check then as there's nothing to verify. */ if (pb) ret = call_bufop(q, verify_planes_array, *vb, pb); if (!ret) list_del(&(*vb)->done_entry); spin_unlock_irqrestore(&q->done_lock, flags); return ret; } int vb2_wait_for_all_buffers(struct vb2_queue *q) { if (!q->streaming) { dprintk(q, 1, "streaming off, will not wait for buffers\n"); return -EINVAL; } if (q->start_streaming_called) wait_event(q->done_wq, !atomic_read(&q->owned_by_drv_count)); return 0; } EXPORT_SYMBOL_GPL(vb2_wait_for_all_buffers); /* * __vb2_dqbuf() - bring back the buffer to the DEQUEUED state */ static void __vb2_dqbuf(struct vb2_buffer *vb) { struct vb2_queue *q = vb->vb2_queue; /* nothing to do if the buffer is already dequeued */ if (vb->state == VB2_BUF_STATE_DEQUEUED) return; vb->state = VB2_BUF_STATE_DEQUEUED; call_void_bufop(q, init_buffer, vb); } int vb2_core_dqbuf(struct vb2_queue *q, unsigned int *pindex, void *pb, bool nonblocking) { struct vb2_buffer *vb = NULL; int ret; ret = __vb2_get_done_vb(q, &vb, pb, nonblocking); if (ret < 0) return ret; switch (vb->state) { case VB2_BUF_STATE_DONE: dprintk(q, 3, "returning done buffer\n"); break; case VB2_BUF_STATE_ERROR: dprintk(q, 3, "returning done buffer with errors\n"); break; default: dprintk(q, 1, "invalid buffer state %s\n", vb2_state_name(vb->state)); return -EINVAL; } call_void_vb_qop(vb, buf_finish, vb); vb->prepared = 0; if (pindex) *pindex = vb->index; /* Fill buffer information for the userspace */ if (pb) call_void_bufop(q, fill_user_buffer, vb, pb); /* Remove from vb2 queue */ list_del(&vb->queued_entry); q->queued_count--; trace_vb2_dqbuf(q, vb); /* go back to dequeued state */ __vb2_dqbuf(vb); if (WARN_ON(vb->req_obj.req)) { media_request_object_unbind(&vb->req_obj); media_request_object_put(&vb->req_obj); } if (vb->request) media_request_put(vb->request); vb->request = NULL; dprintk(q, 2, "dqbuf of buffer %d, state: %s\n", vb->index, vb2_state_name(vb->state)); return 0; } EXPORT_SYMBOL_GPL(vb2_core_dqbuf); /* * __vb2_queue_cancel() - cancel and stop (pause) streaming * * Removes all queued buffers from driver's queue and all buffers queued by * userspace from vb2's queue. Returns to state after reqbufs. */ static void __vb2_queue_cancel(struct vb2_queue *q) { unsigned int i; /* * Tell driver to stop all transactions and release all queued * buffers. */ if (q->start_streaming_called) call_void_qop(q, stop_streaming, q); if (q->streaming) call_void_qop(q, unprepare_streaming, q); /* * If you see this warning, then the driver isn't cleaning up properly * in stop_streaming(). See the stop_streaming() documentation in * videobuf2-core.h for more information how buffers should be returned * to vb2 in stop_streaming(). */ if (WARN_ON(atomic_read(&q->owned_by_drv_count))) { for (i = 0; i < q->max_num_buffers; i++) { struct vb2_buffer *vb = vb2_get_buffer(q, i); if (!vb) continue; if (vb->state == VB2_BUF_STATE_ACTIVE) { pr_warn("driver bug: stop_streaming operation is leaving buffer %u in active state\n", vb->index); vb2_buffer_done(vb, VB2_BUF_STATE_ERROR); } } /* Must be zero now */ WARN_ON(atomic_read(&q->owned_by_drv_count)); } q->streaming = 0; q->start_streaming_called = 0; q->queued_count = 0; q->error = 0; q->uses_requests = 0; q->uses_qbuf = 0; /* * Remove all buffers from vb2's list... */ INIT_LIST_HEAD(&q->queued_list); /* * ...and done list; userspace will not receive any buffers it * has not already dequeued before initiating cancel. */ INIT_LIST_HEAD(&q->done_list); atomic_set(&q->owned_by_drv_count, 0); wake_up_all(&q->done_wq); /* * Reinitialize all buffers for next use. * Make sure to call buf_finish for any queued buffers. Normally * that's done in dqbuf, but that's not going to happen when we * cancel the whole queue. Note: this code belongs here, not in * __vb2_dqbuf() since in vb2_core_dqbuf() there is a critical * call to __fill_user_buffer() after buf_finish(). That order can't * be changed, so we can't move the buf_finish() to __vb2_dqbuf(). */ for (i = 0; i < q->max_num_buffers; i++) { struct vb2_buffer *vb; struct media_request *req; vb = vb2_get_buffer(q, i); if (!vb) continue; req = vb->req_obj.req; /* * If a request is associated with this buffer, then * call buf_request_cancel() to give the driver to complete() * related request objects. Otherwise those objects would * never complete. */ if (req) { enum media_request_state state; unsigned long flags; spin_lock_irqsave(&req->lock, flags); state = req->state; spin_unlock_irqrestore(&req->lock, flags); if (state == MEDIA_REQUEST_STATE_QUEUED) call_void_vb_qop(vb, buf_request_complete, vb); } __vb2_buf_mem_finish(vb); if (vb->prepared) { call_void_vb_qop(vb, buf_finish, vb); vb->prepared = 0; } __vb2_dqbuf(vb); if (vb->req_obj.req) { media_request_object_unbind(&vb->req_obj); media_request_object_put(&vb->req_obj); } if (vb->request) media_request_put(vb->request); vb->request = NULL; vb->copied_timestamp = 0; } } int vb2_core_streamon(struct vb2_queue *q, unsigned int type) { unsigned int q_num_bufs = vb2_get_num_buffers(q); int ret; if (type != q->type) { dprintk(q, 1, "invalid stream type\n"); return -EINVAL; } if (q->streaming) { dprintk(q, 3, "already streaming\n"); return 0; } if (!q_num_bufs) { dprintk(q, 1, "no buffers have been allocated\n"); return -EINVAL; } if (q_num_bufs < q->min_queued_buffers) { dprintk(q, 1, "need at least %u allocated buffers\n", q->min_queued_buffers); return -EINVAL; } ret = call_qop(q, prepare_streaming, q); if (ret) return ret; /* * Tell driver to start streaming provided sufficient buffers * are available. */ if (q->queued_count >= q->min_queued_buffers) { ret = vb2_start_streaming(q); if (ret) goto unprepare; } q->streaming = 1; dprintk(q, 3, "successful\n"); return 0; unprepare: call_void_qop(q, unprepare_streaming, q); return ret; } EXPORT_SYMBOL_GPL(vb2_core_streamon); void vb2_queue_error(struct vb2_queue *q) { q->error = 1; wake_up_all(&q->done_wq); } EXPORT_SYMBOL_GPL(vb2_queue_error); int vb2_core_streamoff(struct vb2_queue *q, unsigned int type) { if (type != q->type) { dprintk(q, 1, "invalid stream type\n"); return -EINVAL; } /* * Cancel will pause streaming and remove all buffers from the driver * and vb2, effectively returning control over them to userspace. * * Note that we do this even if q->streaming == 0: if you prepare or * queue buffers, and then call streamoff without ever having called * streamon, you would still expect those buffers to be returned to * their normal dequeued state. */ __vb2_queue_cancel(q); q->waiting_for_buffers = !q->is_output; q->last_buffer_dequeued = false; dprintk(q, 3, "successful\n"); return 0; } EXPORT_SYMBOL_GPL(vb2_core_streamoff); /* * __find_plane_by_offset() - find plane associated with the given offset */ static int __find_plane_by_offset(struct vb2_queue *q, unsigned long offset, struct vb2_buffer **vb, unsigned int *plane) { unsigned int buffer; /* * Sanity checks to ensure the lock is held, MEMORY_MMAP is * used and fileio isn't active. */ lockdep_assert_held(&q->mmap_lock); if (q->memory != VB2_MEMORY_MMAP) { dprintk(q, 1, "queue is not currently set up for mmap\n"); return -EINVAL; } if (vb2_fileio_is_active(q)) { dprintk(q, 1, "file io in progress\n"); return -EBUSY; } /* Get buffer and plane from the offset */ buffer = (offset >> PLANE_INDEX_SHIFT) & BUFFER_INDEX_MASK; *plane = (offset >> PAGE_SHIFT) & PLANE_INDEX_MASK; *vb = vb2_get_buffer(q, buffer); if (!*vb) return -EINVAL; if (*plane >= (*vb)->num_planes) return -EINVAL; return 0; } int vb2_core_expbuf(struct vb2_queue *q, int *fd, unsigned int type, struct vb2_buffer *vb, unsigned int plane, unsigned int flags) { struct vb2_plane *vb_plane; int ret; struct dma_buf *dbuf; if (q->memory != VB2_MEMORY_MMAP) { dprintk(q, 1, "queue is not currently set up for mmap\n"); return -EINVAL; } if (!q->mem_ops->get_dmabuf) { dprintk(q, 1, "queue does not support DMA buffer exporting\n"); return -EINVAL; } if (flags & ~(O_CLOEXEC | O_ACCMODE)) { dprintk(q, 1, "queue does support only O_CLOEXEC and access mode flags\n"); return -EINVAL; } if (type != q->type) { dprintk(q, 1, "invalid buffer type\n"); return -EINVAL; } if (plane >= vb->num_planes) { dprintk(q, 1, "buffer plane out of range\n"); return -EINVAL; } if (vb2_fileio_is_active(q)) { dprintk(q, 1, "expbuf: file io in progress\n"); return -EBUSY; } vb_plane = &vb->planes[plane]; dbuf = call_ptr_memop(get_dmabuf, vb, vb_plane->mem_priv, flags & O_ACCMODE); if (IS_ERR_OR_NULL(dbuf)) { dprintk(q, 1, "failed to export buffer %d, plane %d\n", vb->index, plane); return -EINVAL; } ret = dma_buf_fd(dbuf, flags & ~O_ACCMODE); if (ret < 0) { dprintk(q, 3, "buffer %d, plane %d failed to export (%d)\n", vb->index, plane, ret); dma_buf_put(dbuf); return ret; } dprintk(q, 3, "buffer %d, plane %d exported as %d descriptor\n", vb->index, plane, ret); *fd = ret; return 0; } EXPORT_SYMBOL_GPL(vb2_core_expbuf); int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) { unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; struct vb2_buffer *vb; unsigned int plane = 0; int ret; unsigned long length; /* * Check memory area access mode. */ if (!(vma->vm_flags & VM_SHARED)) { dprintk(q, 1, "invalid vma flags, VM_SHARED needed\n"); return -EINVAL; } if (q->is_output) { if (!(vma->vm_flags & VM_WRITE)) { dprintk(q, 1, "invalid vma flags, VM_WRITE needed\n"); return -EINVAL; } } else { if (!(vma->vm_flags & VM_READ)) { dprintk(q, 1, "invalid vma flags, VM_READ needed\n"); return -EINVAL; } } mutex_lock(&q->mmap_lock); /* * Find the plane corresponding to the offset passed by userspace. This * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, offset, &vb, &plane); if (ret) goto unlock; /* * MMAP requires page_aligned buffers. * The buffer length was page_aligned at __vb2_buf_mem_alloc(), * so, we need to do the same here. */ length = PAGE_ALIGN(vb->planes[plane].length); if (length < (vma->vm_end - vma->vm_start)) { dprintk(q, 1, "MMAP invalid, as it would overflow buffer length\n"); ret = -EINVAL; goto unlock; } /* * vm_pgoff is treated in V4L2 API as a 'cookie' to select a buffer, * not as a in-buffer offset. We always want to mmap a whole buffer * from its beginning. */ vma->vm_pgoff = 0; ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma); unlock: mutex_unlock(&q->mmap_lock); if (ret) return ret; dprintk(q, 3, "buffer %u, plane %d successfully mapped\n", vb->index, plane); return 0; } EXPORT_SYMBOL_GPL(vb2_mmap); #ifndef CONFIG_MMU unsigned long vb2_get_unmapped_area(struct vb2_queue *q, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long offset = pgoff << PAGE_SHIFT; struct vb2_buffer *vb; unsigned int plane; void *vaddr; int ret; mutex_lock(&q->mmap_lock); /* * Find the plane corresponding to the offset passed by userspace. This * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, offset, &vb, &plane); if (ret) goto unlock; vaddr = vb2_plane_vaddr(vb, plane); mutex_unlock(&q->mmap_lock); return vaddr ? (unsigned long)vaddr : -EINVAL; unlock: mutex_unlock(&q->mmap_lock); return ret; } EXPORT_SYMBOL_GPL(vb2_get_unmapped_area); #endif int vb2_core_queue_init(struct vb2_queue *q) { /* * Sanity check */ /* * For drivers who don't support max_num_buffers ensure * a backward compatibility. */ if (!q->max_num_buffers) q->max_num_buffers = VB2_MAX_FRAME; /* The maximum is limited by offset cookie encoding pattern */ q->max_num_buffers = min_t(unsigned int, q->max_num_buffers, MAX_BUFFER_INDEX); if (WARN_ON(!q) || WARN_ON(!q->ops) || WARN_ON(!q->mem_ops) || WARN_ON(!q->type) || WARN_ON(!q->io_modes) || WARN_ON(!q->ops->queue_setup) || WARN_ON(!q->ops->buf_queue)) return -EINVAL; if (WARN_ON(q->max_num_buffers < VB2_MAX_FRAME) || WARN_ON(q->min_queued_buffers > q->max_num_buffers)) return -EINVAL; if (WARN_ON(q->requires_requests && !q->supports_requests)) return -EINVAL; /* * This combination is not allowed since a non-zero value of * q->min_queued_buffers can cause vb2_core_qbuf() to fail if * it has to call start_streaming(), and the Request API expects * that queueing a request (and thus queueing a buffer contained * in that request) will always succeed. There is no method of * propagating an error back to userspace. */ if (WARN_ON(q->supports_requests && q->min_queued_buffers)) return -EINVAL; /* * If the driver needs 'min_queued_buffers' in the queue before * calling start_streaming() then the minimum requirement is * 'min_queued_buffers + 1' to keep at least one buffer available * for userspace. */ if (q->min_reqbufs_allocation < q->min_queued_buffers + 1) q->min_reqbufs_allocation = q->min_queued_buffers + 1; if (WARN_ON(q->min_reqbufs_allocation > q->max_num_buffers)) return -EINVAL; /* Warn if q->lock is NULL */ if (WARN_ON(!q->lock)) return -EINVAL; INIT_LIST_HEAD(&q->queued_list); INIT_LIST_HEAD(&q->done_list); spin_lock_init(&q->done_lock); mutex_init(&q->mmap_lock); init_waitqueue_head(&q->done_wq); q->memory = VB2_MEMORY_UNKNOWN; if (q->buf_struct_size == 0) q->buf_struct_size = sizeof(struct vb2_buffer); if (q->bidirectional) q->dma_dir = DMA_BIDIRECTIONAL; else q->dma_dir = q->is_output ? DMA_TO_DEVICE : DMA_FROM_DEVICE; if (q->name[0] == '\0') snprintf(q->name, sizeof(q->name), "%s-%p", q->is_output ? "out" : "cap", q); return 0; } EXPORT_SYMBOL_GPL(vb2_core_queue_init); static int __vb2_init_fileio(struct vb2_queue *q, int read); static int __vb2_cleanup_fileio(struct vb2_queue *q); void vb2_core_queue_release(struct vb2_queue *q) { __vb2_cleanup_fileio(q); __vb2_queue_cancel(q); mutex_lock(&q->mmap_lock); __vb2_queue_free(q, 0, q->max_num_buffers); vb2_core_free_buffers_storage(q); q->is_busy = 0; mutex_unlock(&q->mmap_lock); } EXPORT_SYMBOL_GPL(vb2_core_queue_release); __poll_t vb2_core_poll(struct vb2_queue *q, struct file *file, poll_table *wait) { __poll_t req_events = poll_requested_events(wait); struct vb2_buffer *vb = NULL; unsigned long flags; /* * poll_wait() MUST be called on the first invocation on all the * potential queues of interest, even if we are not interested in their * events during this first call. Failure to do so will result in * queue's events to be ignored because the poll_table won't be capable * of adding new wait queues thereafter. */ poll_wait(file, &q->done_wq, wait); if (!q->is_output && !(req_events & (EPOLLIN | EPOLLRDNORM))) return 0; if (q->is_output && !(req_events & (EPOLLOUT | EPOLLWRNORM))) return 0; /* * Start file I/O emulator only if streaming API has not been used yet. */ if (vb2_get_num_buffers(q) == 0 && !vb2_fileio_is_active(q)) { if (!q->is_output && (q->io_modes & VB2_READ) && (req_events & (EPOLLIN | EPOLLRDNORM))) { if (__vb2_init_fileio(q, 1)) return EPOLLERR; } if (q->is_output && (q->io_modes & VB2_WRITE) && (req_events & (EPOLLOUT | EPOLLWRNORM))) { if (__vb2_init_fileio(q, 0)) return EPOLLERR; /* * Write to OUTPUT queue can be done immediately. */ return EPOLLOUT | EPOLLWRNORM; } } /* * There is nothing to wait for if the queue isn't streaming, or if the * error flag is set. */ if (!vb2_is_streaming(q) || q->error) return EPOLLERR; /* * If this quirk is set and QBUF hasn't been called yet then * return EPOLLERR as well. This only affects capture queues, output * queues will always initialize waiting_for_buffers to false. * This quirk is set by V4L2 for backwards compatibility reasons. */ if (q->quirk_poll_must_check_waiting_for_buffers && q->waiting_for_buffers && (req_events & (EPOLLIN | EPOLLRDNORM))) return EPOLLERR; /* * For output streams you can call write() as long as there are fewer * buffers queued than there are buffers available. */ if (q->is_output && q->fileio && q->queued_count < vb2_get_num_buffers(q)) return EPOLLOUT | EPOLLWRNORM; if (list_empty(&q->done_list)) { /* * If the last buffer was dequeued from a capture queue, * return immediately. DQBUF will return -EPIPE. */ if (q->last_buffer_dequeued) return EPOLLIN | EPOLLRDNORM; } /* * Take first buffer available for dequeuing. */ spin_lock_irqsave(&q->done_lock, flags); if (!list_empty(&q->done_list)) vb = list_first_entry(&q->done_list, struct vb2_buffer, done_entry); spin_unlock_irqrestore(&q->done_lock, flags); if (vb && (vb->state == VB2_BUF_STATE_DONE || vb->state == VB2_BUF_STATE_ERROR)) { return (q->is_output) ? EPOLLOUT | EPOLLWRNORM : EPOLLIN | EPOLLRDNORM; } return 0; } EXPORT_SYMBOL_GPL(vb2_core_poll); /* * struct vb2_fileio_buf - buffer context used by file io emulator * * vb2 provides a compatibility layer and emulator of file io (read and * write) calls on top of streaming API. This structure is used for * tracking context related to the buffers. */ struct vb2_fileio_buf { void *vaddr; unsigned int size; unsigned int pos; unsigned int queued:1; }; /* * struct vb2_fileio_data - queue context used by file io emulator * * @cur_index: the index of the buffer currently being read from or * written to. If equal to number of buffers in the vb2_queue * then a new buffer must be dequeued. * @initial_index: in the read() case all buffers are queued up immediately * in __vb2_init_fileio() and __vb2_perform_fileio() just cycles * buffers. However, in the write() case no buffers are initially * queued, instead whenever a buffer is full it is queued up by * __vb2_perform_fileio(). Only once all available buffers have * been queued up will __vb2_perform_fileio() start to dequeue * buffers. This means that initially __vb2_perform_fileio() * needs to know what buffer index to use when it is queuing up * the buffers for the first time. That initial index is stored * in this field. Once it is equal to number of buffers in the * vb2_queue all available buffers have been queued and * __vb2_perform_fileio() should start the normal dequeue/queue cycle. * * vb2 provides a compatibility layer and emulator of file io (read and * write) calls on top of streaming API. For proper operation it required * this structure to save the driver state between each call of the read * or write function. */ struct vb2_fileio_data { unsigned int count; unsigned int type; unsigned int memory; struct vb2_fileio_buf bufs[VB2_MAX_FRAME]; unsigned int cur_index; unsigned int initial_index; unsigned int q_count; unsigned int dq_count; unsigned read_once:1; unsigned write_immediately:1; }; /* * __vb2_init_fileio() - initialize file io emulator * @q: videobuf2 queue * @read: mode selector (1 means read, 0 means write) */ static int __vb2_init_fileio(struct vb2_queue *q, int read) { struct vb2_fileio_data *fileio; struct vb2_buffer *vb; int i, ret; /* * Sanity check */ if (WARN_ON((read && !(q->io_modes & VB2_READ)) || (!read && !(q->io_modes & VB2_WRITE)))) return -EINVAL; /* * Check if device supports mapping buffers to kernel virtual space. */ if (!q->mem_ops->vaddr) return -EBUSY; /* * Check if streaming api has not been already activated. */ if (q->streaming || vb2_get_num_buffers(q) > 0) return -EBUSY; dprintk(q, 3, "setting up file io: mode %s, count %d, read_once %d, write_immediately %d\n", (read) ? "read" : "write", q->min_reqbufs_allocation, q->fileio_read_once, q->fileio_write_immediately); fileio = kzalloc_obj(*fileio); if (fileio == NULL) return -ENOMEM; fileio->read_once = q->fileio_read_once; fileio->write_immediately = q->fileio_write_immediately; /* * Request buffers and use MMAP type to force driver * to allocate buffers by itself. */ fileio->count = q->min_reqbufs_allocation; fileio->memory = VB2_MEMORY_MMAP; fileio->type = q->type; q->fileio = fileio; ret = vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); if (ret) goto err_kfree; /* vb2_fileio_data supports max VB2_MAX_FRAME buffers */ if (fileio->count > VB2_MAX_FRAME) { dprintk(q, 1, "fileio: more than VB2_MAX_FRAME buffers requested\n"); ret = -ENOSPC; goto err_reqbufs; } /* * Userspace can never add or delete buffers later, so there * will never be holes. It is safe to assume that vb2_get_buffer(q, 0) * will always return a valid vb pointer */ vb = vb2_get_buffer(q, 0); /* * Check if plane_count is correct * (multiplane buffers are not supported). */ if (vb->num_planes != 1) { ret = -EBUSY; goto err_reqbufs; } /* * Get kernel address of each buffer. */ for (i = 0; i < vb2_get_num_buffers(q); i++) { /* vb can never be NULL when using fileio. */ vb = vb2_get_buffer(q, i); fileio->bufs[i].vaddr = vb2_plane_vaddr(vb, 0); if (fileio->bufs[i].vaddr == NULL) { ret = -EINVAL; goto err_reqbufs; } fileio->bufs[i].size = vb2_plane_size(vb, 0); } /* * Read mode requires pre queuing of all buffers. */ if (read) { /* * Queue all buffers. */ for (i = 0; i < vb2_get_num_buffers(q); i++) { struct vb2_buffer *vb2 = vb2_get_buffer(q, i); if (!vb2) continue; ret = vb2_core_qbuf(q, vb2, NULL, NULL); if (ret) goto err_reqbufs; fileio->bufs[i].queued = 1; } /* * All buffers have been queued, so mark that by setting * initial_index to the number of buffers in the vb2_queue */ fileio->initial_index = vb2_get_num_buffers(q); fileio->cur_index = fileio->initial_index; } /* * Start streaming. */ ret = vb2_core_streamon(q, q->type); if (ret) goto err_reqbufs; return ret; err_reqbufs: fileio->count = 0; vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); err_kfree: q->fileio = NULL; kfree(fileio); return ret; } /* * __vb2_cleanup_fileio() - free resourced used by file io emulator * @q: videobuf2 queue */ static int __vb2_cleanup_fileio(struct vb2_queue *q) { struct vb2_fileio_data *fileio = q->fileio; if (fileio) { vb2_core_streamoff(q, q->type); q->fileio = NULL; fileio->count = 0; vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); kfree(fileio); dprintk(q, 3, "file io emulator closed\n"); } return 0; } /* * __vb2_perform_fileio() - perform a single file io (read or write) operation * @q: videobuf2 queue * @data: pointed to target userspace buffer * @count: number of bytes to read or write * @ppos: file handle position tracking pointer * @nonblock: mode selector (1 means blocking calls, 0 means nonblocking) * @read: access mode selector (1 means read, 0 means write) */ static ssize_t __vb2_perform_fileio(struct vb2_queue *q, char __user *data, size_t count, loff_t *ppos, int nonblock, int read) { struct vb2_fileio_data *fileio; struct vb2_fileio_buf *buf; bool is_multiplanar = q->is_multiplanar; /* * When using write() to write data to an output video node the vb2 core * should copy timestamps if V4L2_BUF_FLAG_TIMESTAMP_COPY is set. Nobody * else is able to provide this information with the write() operation. */ bool copy_timestamp = !read && q->copy_timestamp; unsigned index; int ret; dprintk(q, 3, "mode %s, offset %ld, count %zd, %sblocking\n", read ? "read" : "write", (long)*ppos, count, nonblock ? "non" : ""); if (!data) return -EINVAL; if (q->waiting_in_dqbuf) { dprintk(q, 3, "another dup()ped fd is %s\n", read ? "reading" : "writing"); return -EBUSY; } /* * Initialize emulator on first call. */ if (!vb2_fileio_is_active(q)) { ret = __vb2_init_fileio(q, read); dprintk(q, 3, "vb2_init_fileio result: %d\n", ret); if (ret) return ret; } fileio = q->fileio; /* * Check if we need to dequeue the buffer. */ index = fileio->cur_index; if (index >= vb2_get_num_buffers(q)) { struct vb2_buffer *b; /* * Call vb2_dqbuf to get buffer back. */ ret = vb2_core_dqbuf(q, &index, NULL, nonblock); dprintk(q, 5, "vb2_dqbuf result: %d\n", ret); if (ret) return ret; fileio->dq_count += 1; fileio->cur_index = index; buf = &fileio->bufs[index]; /* b can never be NULL when using fileio. */ b = vb2_get_buffer(q, index); /* * Get number of bytes filled by the driver */ buf->pos = 0; buf->queued = 0; buf->size = read ? vb2_get_plane_payload(b, 0) : vb2_plane_size(b, 0); /* Compensate for data_offset on read in the multiplanar case. */ if (is_multiplanar && read && b->planes[0].data_offset < buf->size) { buf->pos = b->planes[0].data_offset; buf->size -= buf->pos; } } else { buf = &fileio->bufs[index]; } /* * Limit count on last few bytes of the buffer. */ if (buf->pos + count > buf->size) { count = buf->size - buf->pos; dprintk(q, 5, "reducing read count: %zd\n", count); } /* * Transfer data to userspace. */ dprintk(q, 3, "copying %zd bytes - buffer %d, offset %u\n", count, index, buf->pos); if (read) ret = copy_to_user(data, buf->vaddr + buf->pos, count); else ret = copy_from_user(buf->vaddr + buf->pos, data, count); if (ret) { dprintk(q, 3, "error copying data\n"); return -EFAULT; } /* * Update counters. */ buf->pos += count; *ppos += count; /* * Queue next buffer if required. */ if (buf->pos == buf->size || (!read && fileio->write_immediately)) { /* b can never be NULL when using fileio. */ struct vb2_buffer *b = vb2_get_buffer(q, index); /* * Check if this is the last buffer to read. */ if (read && fileio->read_once && fileio->dq_count == 1) { dprintk(q, 3, "read limit reached\n"); return __vb2_cleanup_fileio(q); } /* * Call vb2_qbuf and give buffer to the driver. */ b->planes[0].bytesused = buf->pos; if (copy_timestamp) b->timestamp = ktime_get_ns(); ret = vb2_core_qbuf(q, b, NULL, NULL); dprintk(q, 5, "vb2_qbuf result: %d\n", ret); if (ret) return ret; /* * Buffer has been queued, update the status */ buf->pos = 0; buf->queued = 1; buf->size = vb2_plane_size(b, 0); fileio->q_count += 1; /* * If we are queuing up buffers for the first time, then * increase initial_index by one. */ if (fileio->initial_index < vb2_get_num_buffers(q)) fileio->initial_index++; /* * The next buffer to use is either a buffer that's going to be * queued for the first time (initial_index < number of buffers in the vb2_queue) * or it is equal to the number of buffers in the vb2_queue, * meaning that the next time we need to dequeue a buffer since * we've now queued up all the 'first time' buffers. */ fileio->cur_index = fileio->initial_index; } /* * Return proper number of bytes processed. */ if (ret == 0) ret = count; return ret; } ssize_t vb2_read(struct vb2_queue *q, char __user *data, size_t count, loff_t *ppos, int nonblocking) { return __vb2_perform_fileio(q, data, count, ppos, nonblocking, 1); } EXPORT_SYMBOL_GPL(vb2_read); ssize_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count, loff_t *ppos, int nonblocking) { return __vb2_perform_fileio(q, (char __user *) data, count, ppos, nonblocking, 0); } EXPORT_SYMBOL_GPL(vb2_write); struct vb2_threadio_data { struct task_struct *thread; vb2_thread_fnc fnc; void *priv; bool stop; }; static int vb2_thread(void *data) { struct vb2_queue *q = data; struct vb2_threadio_data *threadio = q->threadio; bool copy_timestamp = false; unsigned prequeue = 0; unsigned index = 0; int ret = 0; if (q->is_output) { prequeue = vb2_get_num_buffers(q); copy_timestamp = q->copy_timestamp; } set_freezable(); for (;;) { struct vb2_buffer *vb; /* * Call vb2_dqbuf to get buffer back. */ if (prequeue) { vb = vb2_get_buffer(q, index++); if (!vb) continue; prequeue--; } else { mutex_lock(q->lock); if (!threadio->stop) ret = vb2_core_dqbuf(q, &index, NULL, 0); mutex_unlock(q->lock); dprintk(q, 5, "file io: vb2_dqbuf result: %d\n", ret); if (!ret) vb = vb2_get_buffer(q, index); } if (ret || threadio->stop) break; try_to_freeze(); if (vb->state != VB2_BUF_STATE_ERROR) if (threadio->fnc(vb, threadio->priv)) break; if (copy_timestamp) vb->timestamp = ktime_get_ns(); if (!threadio->stop) { mutex_lock(q->lock); ret = vb2_core_qbuf(q, vb, NULL, NULL); mutex_unlock(q->lock); } if (ret || threadio->stop) break; } /* Hmm, linux becomes *very* unhappy without this ... */ while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); schedule(); } return 0; } /* * This function should not be used for anything else but the videobuf2-dvb * support. If you think you have another good use-case for this, then please * contact the linux-media mailinglist first. */ int vb2_thread_start(struct vb2_queue *q, vb2_thread_fnc fnc, void *priv, const char *thread_name) { struct vb2_threadio_data *threadio; int ret = 0; if (q->threadio) return -EBUSY; if (vb2_is_busy(q)) return -EBUSY; if (WARN_ON(q->fileio)) return -EBUSY; threadio = kzalloc_obj(*threadio); if (threadio == NULL) return -ENOMEM; threadio->fnc = fnc; threadio->priv = priv; ret = __vb2_init_fileio(q, !q->is_output); dprintk(q, 3, "file io: vb2_init_fileio result: %d\n", ret); if (ret) goto nomem; q->threadio = threadio; threadio->thread = kthread_run(vb2_thread, q, "vb2-%s", thread_name); if (IS_ERR(threadio->thread)) { ret = PTR_ERR(threadio->thread); threadio->thread = NULL; goto nothread; } return 0; nothread: __vb2_cleanup_fileio(q); nomem: kfree(threadio); return ret; } EXPORT_SYMBOL_GPL(vb2_thread_start); int vb2_thread_stop(struct vb2_queue *q) { struct vb2_threadio_data *threadio = q->threadio; int err; if (threadio == NULL) return 0; threadio->stop = true; /* Wake up all pending sleeps in the thread */ vb2_queue_error(q); err = kthread_stop(threadio->thread); __vb2_cleanup_fileio(q); threadio->thread = NULL; kfree(threadio); q->threadio = NULL; return err; } EXPORT_SYMBOL_GPL(vb2_thread_stop); MODULE_DESCRIPTION("Media buffer core framework"); MODULE_AUTHOR("Pawel Osciak <pawel@osciak.com>, Marek Szyprowski"); MODULE_LICENSE("GPL"); MODULE_IMPORT_NS("DMA_BUF"); |
| 293 2319 2282 2296 1774 1772 77 258 2282 2145 36 85 18 112 113 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */ #ifndef _ASM_GENERIC__TLB_H #define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/hugetlb_inline.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */ #ifndef nmi_uaccess_okay # define nmi_uaccess_okay() true #endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / * tlb_finish_mmu() * * start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_free_vmas() * * tlb_free_vmas() marks the start of unlinking of one or more vmas * and freeing page-tables. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / tlb_remove_page_size() * - __tlb_remove_folio_pages() / __tlb_remove_page_size() * - __tlb_remove_folio_pages_size() * * __tlb_remove_folio_pages_size() is the basic primitive that queues pages * for freeing. It will return a boolean indicating if the queue is (now) * full and a call to tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * __tlb_remove_folio_pages() is similar to __tlb_remove_page_size(), * however, instead of removing a single page, assume PAGE_SIZE and remove * the given number of consecutive pages that are all part of the * same (large) folio. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() or * use the generic __tlb_remove_table(), which does the actual freeing of these * pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_FLUSH_CACHE * * Indicates the architecture has flush_cache_range() but it needs *NOT* be called * before unmapping a VMA. * * NOTE: strictly speaking we shouldn't have this knob and instead rely on * flush_cache_range() being a NOP, except Sparc64 seems to be * different here. * * MMU_GATHER_MERGE_VMAS * * Indicates the architecture wants to merge ranges over VMAs; typical when * multiple range invalidates are more expensive than a full invalidate. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). This * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch { #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; #endif unsigned int nr; void *tables[]; }; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) #ifndef CONFIG_HAVE_ARCH_TLB_REMOVE_TABLE static inline void __tlb_remove_table(void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor_free(ptdesc); } #endif extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor(ptdesc); tlb_remove_page(tlb, ptdesc_page(ptdesc)); } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */ #ifndef tlb_needs_table_invalidate #define tlb_needs_table_invalidate() (true) #endif void tlb_remove_table_sync_one(void); void tlb_remove_table_sync_rcu(void); #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif static inline void tlb_remove_table_sync_one(void) { } static inline void tlb_remove_table_sync_rcu(void) { } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */ #define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct encoded_page *encoded_pages[]; }; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap); #ifdef CONFIG_SMP /* * This both sets 'delayed_rmap', and returns true. It would be an inline * function, except we define it before the 'struct mmu_gather'. */ #define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true) extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma); #endif #endif /* * We have a no-op version of the rmap removal that doesn't * delay anything. That is used on S390, which flushes remote * TLBs synchronously, and on UP, which doesn't have any * remote TLBs to flush and is not preemptible due to this * all happening under the page table lock. */ #ifndef tlb_delay_rmap #define tlb_delay_rmap(tlb) (false) static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * Do we have pending delayed rmap removals? */ unsigned int delayed_rmap : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int vma_pfn : 1; /* * Did we unshare (unmap) any shared page tables? For now only * used for hugetlb PMD table sharing. */ unsigned int unshared_tables : 1; /* * Did we unshare any page tables such that they are now exclusive * and could get reused+modified by the new owner? When setting this * flag, "unshared_tables" will be set as well. For now only used * for hugetlb PMD table sharing. */ unsigned int fully_unshared_tables : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size); } static inline void __tlb_reset_range(struct mmu_gather *tlb) { if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */ } #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush) #error MMU_GATHER_NO_RANGE relies on default tlb_flush() #endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->end) flush_tlb_mm(tlb->mm); } #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); } } #endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); /* * Track if there's at least one VM_PFNMAP/VM_MIXEDMAP vma * in the tracked range, see tlb_free_vmas(). */ tlb->vma_pfn |= !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)); } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* * Anything calling __tlb_adjust_range() also sets at least one of * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); __tlb_reset_range(tlb); } static inline void tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { if (__tlb_remove_page_size(tlb, page, page_size)) tlb_flush_mmu(tlb); } static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return tlb_remove_page_size(tlb, page, PAGE_SIZE); } static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt) { tlb_remove_table(tlb, pt); } static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { #ifdef CONFIG_MMU_GATHER_PAGE_SIZE if (tlb->page_size && tlb->page_size != page_size) { if (!tlb->fullmm && !tlb->need_flush_all) tlb_flush_mmu(tlb); } tlb->page_size = page_size; #endif } static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { if (tlb->cleared_ptes) return PAGE_SHIFT; if (tlb->cleared_pmds) return PMD_SHIFT; if (tlb->cleared_puds) return PUD_SHIFT; if (tlb->cleared_p4ds) return P4D_SHIFT; return PAGE_SHIFT; } static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) { return 1UL << tlb_get_unmap_shift(tlb); } /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); #ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE flush_cache_range(vma, vma->vm_start, vma->vm_end); #endif } static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm || IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) return; /* * Do a TLB flush and reset the range at VMA boundaries; this avoids * the ranges growing with the unused space between consecutive VMAs, * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on * this. */ tlb_flush_mmu_tlbonly(tlb); } static inline void tlb_free_vmas(struct mmu_gather *tlb) { if (tlb->fullmm) return; /* * VM_PFNMAP is more fragile because the core mm will not track the * page mapcount -- there might not be page-frames for these PFNs * after all. * * Specifically() there is a race between munmap() and * unmap_mapping_range(), where munmap() will unlink the VMA, such * that unmap_mapping_range() will no longer observe the VMA and * no-op, without observing the TLBI, returning prematurely. * * So if we're about to unlink such a VMA, and we have pending * TLBI for such a vma, flush things now. */ if (tlb->vma_pfn) tlb_flush_mmu_tlbonly(tlb); } /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, * and set corresponding cleared_*. */ static inline void tlb_flush_pte_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_ptes = 1; } static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_pmds = 1; } static inline void tlb_flush_pud_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_puds = 1; } static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_p4ds = 1; } #ifndef __tlb_remove_tlb_entry static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { } #endif /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * * Record the fact that pte's were really unmapped by updating the range, * so we can later optimise away the tlb invalidate. This helps when * userspace is unmapping already-unmapped pages, which happens quite a lot. */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ tlb_flush_pte_range(tlb, address, PAGE_SIZE); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_tlb_entries - remember unmapping of multiple consecutive ptes for * later tlb invalidation. * * Similar to tlb_remove_tlb_entry(), but remember unmapping of multiple * consecutive ptes instead of only a single one. */ static inline void tlb_remove_tlb_entries(struct mmu_gather *tlb, pte_t *ptep, unsigned int nr, unsigned long address) { tlb_flush_pte_range(tlb, address, PAGE_SIZE * nr); for (;;) { __tlb_remove_tlb_entry(tlb, ptep, address); if (--nr == 0) break; ptep++; address += PAGE_SIZE; } } #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ if (_sz >= P4D_SIZE) \ tlb_flush_p4d_range(tlb, address, _sz); \ else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ else if (_sz >= PMD_SIZE) \ tlb_flush_pmd_range(tlb, address, _sz); \ else \ tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation * This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pmd_tlb_entry #define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0) #endif #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) /** * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb * invalidation. This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pud_tlb_entry #define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0) #endif #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) /* * For things like page tables caches (ie caching addresses "inside" the * page tables, like x86 does), for legacy reasons, flushing an * individual page had better flush the page table caches behind it. This * is definitely how x86 works, for example. And if you have an * architected non-legacy page table cache (which I'm not aware of * anybody actually doing), you're going to have some architecturally * explicit flushing for that, likely *separate* from a regular TLB entry * flush, and thus you'd need more than just some range expansion.. * * So if we ever find an architecture * that would want something that odd, I think it is up to that * architecture to do its own odd thing, not cause pain for others * http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com * * For now w.r.t page table cache, mark the range_size as PAGE_SIZE */ #ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif #ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ tlb_flush_pud_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef pte_needs_flush static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) { return true; } #endif #ifndef huge_pmd_needs_flush static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) { return true; } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, unsigned long addr) { /* * The caller must make sure that concurrent unsharing + exclusive * reuse is impossible until tlb_flush_unshared_tables() was called. */ VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); ptdesc_pmd_pts_dec(pt); /* Clearing a PUD pointing at a PMD table with PMD leaves. */ tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); /* * If the page table is now exclusively owned, we fully unshared * a page table. */ if (!ptdesc_pmd_is_shared(pt)) tlb->fully_unshared_tables = true; tlb->unshared_tables = true; } static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) { /* * As soon as the caller drops locks to allow for reuse of * previously-shared tables, these tables could get modified and * even reused outside of hugetlb context, so we have to make sure that * any page table walkers (incl. TLB, GUP-fast) are aware of that * change. * * Even if we are not fully unsharing a PMD table, we must * flush the TLB for the unsharer now. */ if (tlb->unshared_tables) tlb_flush_mmu_tlbonly(tlb); /* * Similarly, we must make sure that concurrent GUP-fast will not * walk previously-shared page tables that are getting modified+reused * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. * * We only perform this when we are the last sharer of a page table, * as the IPI will reach all CPUs: any GUP-fast. * * Note that on configs where tlb_remove_table_sync_one() is a NOP, * the expectation is that the tlb_flush_mmu_tlbonly() would have issued * required IPIs already for us. */ if (tlb->fully_unshared_tables) { tlb_remove_table_sync_one(); tlb->fully_unshared_tables = false; } } #endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ |
| 3274 416 443 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Statically sized hash table implementation * (C) 2012 Sasha Levin <levinsasha928@gmail.com> */ #ifndef _LINUX_HASHTABLE_H #define _LINUX_HASHTABLE_H #include <linux/list.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/rculist.h> #define DEFINE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DEFINE_READ_MOSTLY_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] __read_mostly = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DECLARE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] #define HASH_SIZE(name) (ARRAY_SIZE(name)) #define HASH_BITS(name) ilog2(HASH_SIZE(name)) /* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */ #define hash_min(val, bits) \ (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)) static inline void __hash_init(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) INIT_HLIST_HEAD(&ht[i]); } /** * hash_init - initialize a hash table * @hashtable: hashtable to be initialized * * Calculates the size of the hashtable from the given parameter, otherwise * same as hash_init_size. * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable)) /** * hash_add - add an object to a hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add(hashtable, node, key) \ hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_add_rcu - add an object to a rcu enabled hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add_rcu(hashtable, node, key) \ hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_hashed - check whether an object is in any hashtable * @node: the &struct hlist_node of the object to be checked */ static inline bool hash_hashed(struct hlist_node *node) { return !hlist_unhashed(node); } static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) if (!hlist_empty(&ht[i])) return false; return true; } /** * hash_empty - check whether a hashtable is empty * @hashtable: hashtable to check * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable)) /** * hash_del - remove an object from a hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del(struct hlist_node *node) { hlist_del_init(node); } /** * hash_del_rcu - remove an object from a rcu enabled hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del_rcu(struct hlist_node *node) { hlist_del_init_rcu(node); } /** * hash_for_each - iterate over a hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry(obj, &name[bkt], member) /** * hash_for_each_rcu - iterate over a rcu enabled hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_rcu(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_rcu(obj, &name[bkt], member) /** * hash_for_each_safe - iterate over a hashtable safe against removal of * hash entry * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @tmp: a &struct hlist_node used for temporary storage * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_safe(name, bkt, tmp, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_safe(obj, tmp, &name[bkt], member) /** * hash_for_each_possible - iterate over all possible objects hashing to the * same bucket * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible(name, obj, member, key) \ hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the * same bucket in an rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_rcu(name, obj, member, key, cond...) \ hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ member, ## cond) /** * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing * to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over * * This is the same as hash_for_each_possible_rcu() except that it does * not do any RCU debugging or tracing. */ #define hash_for_each_possible_rcu_notrace(name, obj, member, key) \ hlist_for_each_entry_rcu_notrace(obj, \ &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_safe - iterate over all possible objects hashing to the * same bucket safe against removals * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @tmp: a &struct hlist_node used for temporary storage * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_safe(name, obj, tmp, member, key) \ hlist_for_each_entry_safe(obj, tmp,\ &name[hash_min(key, HASH_BITS(name))], member) #endif |
| 34 23 23 1 66 65 65 65 7 65 16 5 14 29 59 46 55 62 62 45 40 41 6 67 67 52 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/isofs/namei.c * * (C) 1992 Eric Youngdale Modified for ISO 9660 filesystem. * * (C) 1991 Linus Torvalds - minix filesystem */ #include <linux/gfp.h> #include "isofs.h" static int isofs_cmp(struct dentry *dentry, const char *compare, int dlen) { if (likely(!dentry->d_op)) return dentry->d_name.len != dlen || memcmp(dentry->d_name.name, compare, dlen); return dentry->d_op->d_compare(NULL, dentry->d_name.len, dentry->d_name.name, &QSTR_LEN(compare, dlen)); } /* * isofs_find_entry() * * finds an entry in the specified directory with the wanted name. It * returns the inode number of the found entry, or 0 on error. */ static unsigned long isofs_find_entry(struct inode *dir, struct dentry *dentry, unsigned long *block_rv, unsigned long *offset_rv, char *tmpname, struct iso_directory_record *tmpde) { unsigned long bufsize = ISOFS_BUFFER_SIZE(dir); unsigned char bufbits = ISOFS_BUFFER_BITS(dir); unsigned long block, f_pos, offset, block_saved, offset_saved; struct buffer_head *bh = NULL; struct isofs_sb_info *sbi = ISOFS_SB(dir->i_sb); if (!ISOFS_I(dir)->i_first_extent) return 0; f_pos = 0; offset = 0; block = 0; while (f_pos < dir->i_size) { struct iso_directory_record *de; int de_len, match, i, dlen; char *dpnt; if (!bh) { bh = isofs_bread(dir, block); if (!bh) return 0; } de = (struct iso_directory_record *) (bh->b_data + offset); de_len = *(unsigned char *) de; if (!de_len) { brelse(bh); bh = NULL; f_pos = (f_pos + ISOFS_BLOCK_SIZE) & ~(ISOFS_BLOCK_SIZE - 1); block = f_pos >> bufbits; offset = 0; continue; } block_saved = bh->b_blocknr; offset_saved = offset; offset += de_len; f_pos += de_len; /* Make sure we have a full directory entry */ if (offset >= bufsize) { int slop = bufsize - offset + de_len; memcpy(tmpde, de, slop); offset &= bufsize - 1; block++; brelse(bh); bh = NULL; if (offset) { bh = isofs_bread(dir, block); if (!bh) return 0; memcpy((void *) tmpde + slop, bh->b_data, offset); } de = tmpde; } dlen = de->name_len[0]; dpnt = de->name; /* Basic sanity check, whether name doesn't exceed dir entry */ if (de_len < dlen + sizeof(struct iso_directory_record)) { printk(KERN_NOTICE "iso9660: Corrupted directory entry" " in block %lu of inode %llu\n", block, dir->i_ino); brelse(bh); return 0; } if (sbi->s_rock && ((i = get_rock_ridge_filename(de, tmpname, dir)))) { dlen = i; /* possibly -1 */ dpnt = tmpname; #ifdef CONFIG_JOLIET } else if (sbi->s_joliet_level) { dlen = get_joliet_filename(de, tmpname, dir); dpnt = tmpname; #endif } else if (sbi->s_mapping == 'a') { dlen = get_acorn_filename(de, tmpname, dir); dpnt = tmpname; } else if (sbi->s_mapping == 'n') { dlen = isofs_name_translate(de, tmpname, dir); dpnt = tmpname; } /* * Skip hidden or associated files unless hide or showassoc, * respectively, is set */ match = 0; if (dlen > 0 && (!sbi->s_hide || (!(de->flags[-sbi->s_high_sierra] & 1))) && (sbi->s_showassoc || (!(de->flags[-sbi->s_high_sierra] & 4)))) { if (dpnt && (dlen > 1 || dpnt[0] > 1)) match = (isofs_cmp(dentry, dpnt, dlen) == 0); } if (match) { isofs_normalize_block_and_offset(de, &block_saved, &offset_saved); *block_rv = block_saved; *offset_rv = offset_saved; brelse(bh); return 1; } } brelse(bh); return 0; } struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int found; unsigned long block; unsigned long offset; struct inode *inode; struct page *page; page = alloc_page(GFP_USER); if (!page) return ERR_PTR(-ENOMEM); found = isofs_find_entry(dir, dentry, &block, &offset, page_address(page), 1024 + page_address(page)); __free_page(page); inode = found ? isofs_iget(dir->i_sb, block, offset) : NULL; return d_splice_alias(inode, dentry); } |
| 7 6 306 164 288 315 99 33 311 93 7 186 189 40 186 251 7 16 292 17 405 11 340 13 14700 5 240 499 489 6 492 1167 140 68 44 1172 204 553 178 577 1 1 69 648 11 654 5 232 81 301 11 6 10 6 9 16 13 134 26 23 2 18 36 18 119 22 26 5 3 3 3 3 56 113 167 112 21 276 317 178 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_XFRM_H #define _NET_XFRM_H #include <linux/compiler.h> #include <linux/xfrm.h> #include <linux/spinlock.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/refcount.h> #include <linux/sockptr.h> #include <net/sock.h> #include <net/dst.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/flow.h> #include <net/gro_cells.h> #include <linux/interrupt.h> #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif #define XFRM_PROTO_ESP 50 #define XFRM_PROTO_AH 51 #define XFRM_PROTO_COMP 108 #define XFRM_PROTO_IPIP 4 #define XFRM_PROTO_IPV6 41 #define XFRM_PROTO_IPTFS IPPROTO_AGGFRAG #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS #define XFRM_ALIGN4(len) (((len) + 3) & ~3) #define XFRM_ALIGN8(len) (((len) + 7) & ~7) #define MODULE_ALIAS_XFRM_MODE(family, encap) \ MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap)) #define MODULE_ALIAS_XFRM_TYPE(family, proto) \ MODULE_ALIAS("xfrm-type-" __stringify(family) "-" __stringify(proto)) #define MODULE_ALIAS_XFRM_OFFLOAD_TYPE(family, proto) \ MODULE_ALIAS("xfrm-offload-" __stringify(family) "-" __stringify(proto)) #ifdef CONFIG_XFRM_STATISTICS #define XFRM_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.xfrm_statistics, field) #define XFRM_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.xfrm_statistics, field, val) #else #define XFRM_INC_STATS(net, field) ((void)(net)) #define XFRM_ADD_STATS(net, field, val) ((void)(net)) #endif /* Organization of SPD aka "XFRM rules" ------------------------------------ Basic objects: - policy rule, struct xfrm_policy (=SPD entry) - bundle of transformations, struct dst_entry == struct xfrm_dst (=SA bundle) - instance of a transformer, struct xfrm_state (=SA) - template to clone xfrm_state, struct xfrm_tmpl SPD is organized as hash table (for policies that meet minimum address prefix length setting, net->xfrm.policy_hthresh). Other policies are stored in lists, sorted into rbtree ordered by destination and source address networks. See net/xfrm/xfrm_policy.c for details. (To be compatible with existing pfkeyv2 implementations, many rules with priority of 0x7fffffff are allowed to exist and such rules are ordered in an unpredictable way, thanks to bsd folks.) If "action" is "block", then we prohibit the flow, otherwise: if "xfrms_nr" is zero, the flow passes untransformed. Otherwise, policy entry has list of up to XFRM_MAX_DEPTH transformations, described by templates xfrm_tmpl. Each template is resolved to a complete xfrm_state (see below) and we pack bundle of transformations to a dst_entry returned to requester. dst -. xfrm .-> xfrm_state #1 |---. child .-> dst -. xfrm .-> xfrm_state #2 |---. child .-> dst -. xfrm .-> xfrm_state #3 |---. child .-> NULL Resolution of xrfm_tmpl ----------------------- Template contains: 1. ->mode Mode: transport or tunnel 2. ->id.proto Protocol: AH/ESP/IPCOMP 3. ->id.daddr Remote tunnel endpoint, ignored for transport mode. Q: allow to resolve security gateway? 4. ->id.spi If not zero, static SPI. 5. ->saddr Local tunnel endpoint, ignored for transport mode. 6. ->algos List of allowed algos. Plain bitmask now. Q: ealgos, aalgos, calgos. What a mess... 7. ->share Sharing mode. Q: how to implement private sharing mode? To add struct sock* to flow id? Having this template we search through SAD searching for entries with appropriate mode/proto/algo, permitted by selector. If no appropriate entry found, it is requested from key manager. PROBLEMS: Q: How to find all the bundles referring to a physical path for PMTU discovery? Seems, dst should contain list of all parents... and enter to infinite locking hierarchy disaster. No! It is easier, we will not search for them, let them find us. We add genid to each dst plus pointer to genid of raw IP route, pmtu disc will update pmtu on raw IP route and increase its genid. dst_check() will see this for top level and trigger resyncing metrics. Plus, it will be made via sk->sk_dst_cache. Solved. */ struct xfrm_state_walk { struct list_head all; u8 state; u8 dying; u8 proto; u32 seq; struct xfrm_address_filter *filter; }; enum { XFRM_DEV_OFFLOAD_IN = 1, XFRM_DEV_OFFLOAD_OUT, XFRM_DEV_OFFLOAD_FWD, }; enum { XFRM_DEV_OFFLOAD_UNSPECIFIED, XFRM_DEV_OFFLOAD_CRYPTO, XFRM_DEV_OFFLOAD_PACKET, }; enum { XFRM_DEV_OFFLOAD_FLAG_ACQ = 1, }; struct xfrm_dev_offload { /* The device for this offload. * Device drivers should not use this directly, as that will prevent * them from working with bonding device. Instead, the device passed * to the add/delete callbacks should be used. */ struct net_device *dev; netdevice_tracker dev_tracker; /* This is a private pointer used by the bonding driver (and eventually * should be moved there). Device drivers should not use it. * Protected by xfrm_state.lock AND bond.ipsec_lock in most cases, * except in the .xdo_dev_state_del() flow, where only xfrm_state.lock * is held. */ struct net_device *real_dev; unsigned long offload_handle; /* Snapshot the attached device index for dump paths. */ int ifindex; u8 dir : 2; u8 type : 2; u8 flags : 2; }; struct xfrm_mode { u8 encap; u8 family; u8 flags; }; /* Flags for xfrm_mode. */ enum { XFRM_MODE_FLAG_TUNNEL = 1, }; enum xfrm_replay_mode { XFRM_REPLAY_MODE_LEGACY, XFRM_REPLAY_MODE_BMP, XFRM_REPLAY_MODE_ESN, }; /* Full description of state of transformer. */ struct xfrm_state { possible_net_t xs_net; union { struct hlist_node gclist; struct hlist_node bydst; }; union { struct hlist_node dev_gclist; struct hlist_node bysrc; }; struct hlist_node byspi; struct hlist_node byseq; struct hlist_node state_cache; struct hlist_node state_cache_input; refcount_t refcnt; spinlock_t lock; u32 pcpu_num; struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; u32 if_id; u32 tfcpad; u32 genid; /* Key manager bits */ struct xfrm_state_walk km; /* Parameters of this state. */ struct { u32 reqid; u8 mode; u8 replay_window; u8 aalgo, ealgo, calgo; u8 flags; u16 family; xfrm_address_t saddr; int header_len; int enc_hdr_len; int trailer_len; u32 extra_flags; struct xfrm_mark smark; } props; struct xfrm_lifetime_cfg lft; /* Data for transformer */ struct xfrm_algo_auth *aalg; struct xfrm_algo *ealg; struct xfrm_algo *calg; struct xfrm_algo_aead *aead; const char *geniv; /* mapping change rate limiting */ __be16 new_mapping_sport; u32 new_mapping; /* seconds */ u32 mapping_maxage; /* seconds for input SA */ /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; /* NAT keepalive */ u32 nat_keepalive_interval; /* seconds */ time64_t nat_keepalive_expiration; /* Data for care-of address */ xfrm_address_t *coaddr; /* IPComp needs an IPIP tunnel for handling uncompressed packets */ struct xfrm_state *tunnel; /* If a tunnel, number of users + 1 */ atomic_t tunnel_users; /* State for replay detection */ struct xfrm_replay_state replay; struct xfrm_replay_state_esn *replay_esn; /* Replay detection state at the time we sent the last notification */ struct xfrm_replay_state preplay; struct xfrm_replay_state_esn *preplay_esn; /* replay detection mode */ enum xfrm_replay_mode repl_mode; /* internal flag that only holds state for delayed aevent at the * moment */ u32 xflags; /* Replay detection notification settings */ u32 replay_maxage; u32 replay_maxdiff; /* Replay detection notification timer */ struct timer_list rtimer; /* Statistics */ struct xfrm_stats stats; struct xfrm_lifetime_cur curlft; struct hrtimer mtimer; struct xfrm_dev_offload xso; /* used to fix curlft->add_time when changing date */ long saved_tmo; /* Last used time */ time64_t lastused; struct page_frag xfrag; /* Reference to data common to all the instances of this * transformer. */ const struct xfrm_type *type; struct xfrm_mode inner_mode; struct xfrm_mode inner_mode_iaf; struct xfrm_mode outer_mode; const struct xfrm_type_offload *type_offload; /* Security context */ struct xfrm_sec_ctx *security; /* Private data of this transformer, format is opaque, * interpreted by xfrm_type methods. */ void *data; u8 dir; const struct xfrm_mode_cbs *mode_cbs; void *mode_data; }; static inline struct net *xs_net(struct xfrm_state *x) { return read_pnet(&x->xs_net); } /* xflags - make enum if more show up */ #define XFRM_TIME_DEFER 1 #define XFRM_SOFT_EXPIRE 2 enum { XFRM_STATE_VOID, XFRM_STATE_ACQ, XFRM_STATE_VALID, XFRM_STATE_ERROR, XFRM_STATE_EXPIRED, XFRM_STATE_DEAD }; /* callback structure passed from either netlink or pfkey */ struct km_event { union { u32 hard; u32 proto; u32 byid; u32 aevent; u32 type; } data; u32 seq; u32 portid; u32 event; struct net *net; }; struct xfrm_if_decode_session_result { struct net *net; u32 if_id; }; struct xfrm_if_cb { bool (*decode_session)(struct sk_buff *skb, unsigned short family, struct xfrm_if_decode_session_result *res); }; void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); void xfrm_if_unregister_cb(void); struct xfrm_dst_lookup_params { struct net *net; dscp_t dscp; int oif; xfrm_address_t *saddr; xfrm_address_t *daddr; u32 mark; __u8 ipproto; union flowi_uli uli; }; struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; struct dst_entry *(*dst_lookup)(const struct xfrm_dst_lookup_params *params); int (*get_saddr)(xfrm_address_t *saddr, const struct xfrm_dst_lookup_params *params); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); struct dst_entry *(*blackhole_route)(struct net *net, struct dst_entry *orig); }; int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { u8 family; u8 proto; const struct xfrm_type_offload *type_offload_esp; const struct xfrm_type *type_esp; const struct xfrm_type *type_ipip; const struct xfrm_type *type_ipip6; const struct xfrm_type *type_comp; const struct xfrm_type *type_ah; const struct xfrm_type *type_routing; const struct xfrm_type *type_dstopts; int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*transport_finish)(struct sk_buff *skb, int async); void (*local_error)(struct sk_buff *skb, u32 mtu); }; int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family); struct xfrm_input_afinfo { u8 family; bool is_ipip; int (*callback)(struct sk_buff *skb, u8 protocol, int err); }; int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_flush_gc(void); struct xfrm_type { struct module *owner; u8 proto; u8 flags; #define XFRM_TYPE_NON_FRAGMENT 1 #define XFRM_TYPE_REPLAY_PROT 2 #define XFRM_TYPE_LOCAL_COADDR 4 #define XFRM_TYPE_REMOTE_COADDR 8 int (*init_state)(struct xfrm_state *x, struct netlink_ext_ack *extack); void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { struct module *owner; u8 proto; void (*encap)(struct xfrm_state *, struct sk_buff *pskb); int (*input_tail)(struct xfrm_state *x, struct sk_buff *skb); int (*xmit)(struct xfrm_state *, struct sk_buff *pskb, netdev_features_t features); }; int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_set_type_offload(struct xfrm_state *x, bool try_load); static inline void xfrm_unset_type_offload(struct xfrm_state *x) { if (!x->type_offload) return; module_put(x->type_offload->owner); x->type_offload = NULL; } /** * struct xfrm_mode_cbs - XFRM mode callbacks * @owner: module owner or NULL * @init_state: Add/init mode specific state in `xfrm_state *x` * @clone_state: Copy mode specific values from `orig` to new state `x` * @destroy_state: Cleanup mode specific state from `xfrm_state *x` * @user_init: Process mode specific netlink attributes from user * @copy_to_user: Add netlink attributes to `attrs` based on state in `x` * @sa_len: Return space required to store mode specific netlink attributes * @get_inner_mtu: Return avail payload space after removing encap overhead * @input: Process received packet from SA using mode * @output: Output given packet using mode * @prepare_output: Add mode specific encapsulation to packet in skb. On return * `transport_header` should point at ESP header, `network_header` should * point at outer IP header and `mac_header` should opint at the * protocol/nexthdr field of the outer IP. * * One should examine and understand the specific uses of these callbacks in * xfrm for further detail on how and when these functions are called. RTSL. */ struct xfrm_mode_cbs { struct module *owner; int (*init_state)(struct xfrm_state *x); int (*clone_state)(struct xfrm_state *x, struct xfrm_state *orig); void (*destroy_state)(struct xfrm_state *x); int (*user_init)(struct net *net, struct xfrm_state *x, struct nlattr **attrs, struct netlink_ext_ack *extack); int (*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb); unsigned int (*sa_len)(const struct xfrm_state *x); u32 (*get_inner_mtu)(struct xfrm_state *x, int outer_mtu); int (*input)(struct xfrm_state *x, struct sk_buff *skb); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*prepare_output)(struct xfrm_state *x, struct sk_buff *skb); }; int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs); void xfrm_unregister_mode_cbs(u8 mode); static inline int xfrm_af2proto(unsigned int family) { switch(family) { case AF_INET: return IPPROTO_IPIP; case AF_INET6: return IPPROTO_IPV6; default: return 0; } } static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { if ((x->sel.family != AF_UNSPEC) || (ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) return &x->inner_mode; else return &x->inner_mode_iaf; } struct xfrm_tmpl { /* id in template is interpreted as: * daddr - destination of tunnel, may be zero for transport mode. * spi - zero to acquire spi. Not zero if spi is static, then * daddr must be fixed too. * proto - AH/ESP/IPCOMP */ struct xfrm_id id; /* Source address of tunnel. Ignored, if it is not a tunnel. */ xfrm_address_t saddr; unsigned short encap_family; u32 reqid; /* Mode: transport, tunnel etc. */ u8 mode; /* Sharing mode: unique, this session only, this user only etc. */ u8 share; /* May skip this transfomration if no SA is found */ u8 optional; /* Skip aalgos/ealgos/calgos checks. */ u8 allalgs; /* Bit mask of algos allowed for acquisition */ u32 aalgos; u32 ealgos; u32 calgos; }; #define XFRM_MAX_DEPTH 6 #define XFRM_MAX_OFFLOAD_DEPTH 1 struct xfrm_policy_walk_entry { struct list_head all; u8 dead; }; struct xfrm_policy_walk { struct xfrm_policy_walk_entry walk; u8 type; u32 seq; }; struct xfrm_policy_queue { struct sk_buff_head hold_queue; struct timer_list hold_timer; unsigned long timeout; }; /** * struct xfrm_policy - xfrm policy * @xp_net: network namespace the policy lives in * @bydst: hlist node for SPD hash table or rbtree list * @byidx: hlist node for index hash table * @state_cache_list: hlist head for policy cached xfrm states * @lock: serialize changes to policy structure members * @refcnt: reference count, freed once it reaches 0 * @pos: kernel internal tie-breaker to determine age of policy * @timer: timer * @genid: generation, used to invalidate old policies * @priority: priority, set by userspace * @index: policy index (autogenerated) * @if_id: virtual xfrm interface id * @mark: packet mark * @selector: selector * @lft: liftime configuration data * @curlft: liftime state * @walk: list head on pernet policy list * @polq: queue to hold packets while aqcuire operaion in progress * @bydst_reinsert: policy tree node needs to be merged * @type: XFRM_POLICY_TYPE_MAIN or _SUB * @action: XFRM_POLICY_ALLOW or _BLOCK * @flags: XFRM_POLICY_LOCALOK, XFRM_POLICY_ICMP * @xfrm_nr: number of used templates in @xfrm_vec * @family: protocol family * @security: SELinux security label * @xfrm_vec: array of templates to resolve state * @rcu: rcu head, used to defer memory release * @xdo: hardware offload state */ struct xfrm_policy { possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; struct hlist_head state_cache_list; /* This lock only affects elements except for entry. */ rwlock_t lock; refcount_t refcnt; u32 pos; struct timer_list timer; atomic_t genid; u32 priority; u32 index; u32 if_id; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; struct xfrm_lifetime_cur curlft; struct xfrm_policy_walk_entry walk; struct xfrm_policy_queue polq; bool bydst_reinsert; u8 type; u8 action; u8 flags; u8 xfrm_nr; u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; struct rcu_head rcu; struct xfrm_dev_offload xdo; }; static inline struct net *xp_net(const struct xfrm_policy *xp) { return read_pnet(&xp->xp_net); } struct xfrm_kmaddress { xfrm_address_t local; xfrm_address_t remote; u32 reserved; u16 family; }; struct xfrm_migrate { xfrm_address_t old_daddr; xfrm_address_t old_saddr; xfrm_address_t new_daddr; xfrm_address_t new_saddr; struct xfrm_encap_tmpl *encap; struct xfrm_user_offload *xuo; struct xfrm_mark old_mark; const struct xfrm_mark *new_mark; struct xfrm_mark smark; u8 proto; u8 mode; u16 msg_type; /* XFRM_MSG_MIGRATE or XFRM_MSG_MIGRATE_STATE */ u32 flags; u32 old_reqid; u32 new_reqid; u32 nat_keepalive_interval; u32 mapping_maxage; u16 old_family; u16 new_family; const struct xfrm_selector *new_sel; }; #define XFRM_KM_TIMEOUT 30 /* what happened */ #define XFRM_REPLAY_UPDATE XFRM_AE_CR #define XFRM_REPLAY_TIMEOUT XFRM_AE_CE /* default aevent timeout in units of 100ms */ #define XFRM_AE_ETIME 10 /* Async Event timer multiplier */ #define XFRM_AE_ETH_M 10 /* default seq threshold size */ #define XFRM_AE_SEQT_SIZE 2 struct xfrm_mgr { struct list_head list; int (*notify)(struct xfrm_state *x, const struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp); struct xfrm_policy *(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); int (*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c); int (*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); int (*migrate)(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap); bool (*is_alive)(const struct km_event *c); }; void xfrm_register_km(struct xfrm_mgr *km); void xfrm_unregister_km(struct xfrm_mgr *km); struct xfrm_tunnel_skb_cb { union { struct inet_skb_parm h4; struct inet6_skb_parm h6; } header; union { struct ip_tunnel *ip4; struct ip6_tnl *ip6; } tunnel; }; #define XFRM_TUNNEL_SKB_CB(__skb) ((struct xfrm_tunnel_skb_cb *)&((__skb)->cb[0])) /* * This structure is used for the duration where packets are being * transformed by IPsec. As soon as the packet leaves IPsec the * area beyond the generic IP part may be overwritten. */ struct xfrm_skb_cb { struct xfrm_tunnel_skb_cb header; /* Sequence number for replay protection. */ union { struct { __u32 low; __u32 hi; } output; struct { __be32 low; __be32 hi; } input; } seq; }; #define XFRM_SKB_CB(__skb) ((struct xfrm_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the afinfo prepare_input/prepare_output functions * to transmit header information to the mode input/output functions. */ struct xfrm_mode_skb_cb { struct xfrm_tunnel_skb_cb header; /* Copied from header for IPv4, always set to zero and DF for IPv6. */ __be16 id; __be16 frag_off; /* IP header length (excluding options or extension headers). */ u8 ihl; /* TOS for IPv4, class for IPv6. */ u8 tos; /* TTL for IPv4, hop limitfor IPv6. */ u8 ttl; /* Protocol for IPv4, NH for IPv6. */ u8 protocol; /* Option length for IPv4, zero for IPv6. */ u8 optlen; /* Used by IPv6 only, zero for IPv4. */ u8 flow_lbl[3]; }; #define XFRM_MODE_SKB_CB(__skb) ((struct xfrm_mode_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the input processing to locate the SPI and * related information. */ struct xfrm_spi_skb_cb { struct xfrm_tunnel_skb_cb header; unsigned int daddroff; unsigned int family; __be32 seq; }; #define XFRM_SPI_SKB_CB(__skb) ((struct xfrm_spi_skb_cb *)&((__skb)->cb[0])) #ifdef CONFIG_AUDITSYSCALL static inline struct audit_buffer *xfrm_audit_start(const char *op) { struct audit_buffer *audit_buf = NULL; if (audit_enabled == AUDIT_OFF) return NULL; audit_buf = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_MAC_IPSEC_EVENT); if (audit_buf == NULL) return NULL; audit_log_format(audit_buf, "op=%s", op); return audit_buf; } static inline void xfrm_audit_helper_usrinfo(bool task_valid, struct audit_buffer *audit_buf) { const unsigned int auid = from_kuid(&init_user_ns, task_valid ? audit_get_loginuid(current) : INVALID_UID); const unsigned int ses = task_valid ? audit_get_sessionid(current) : AUDIT_SID_UNSET; audit_log_format(audit_buf, " auid=%u ses=%u", auid, ses); audit_log_task_context(audit_buf); } void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid); void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid); void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid); void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family); void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq); void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto); #else static inline void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { } static inline void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid) { } static inline void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { } static inline void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { } static inline void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { } static inline void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { } static inline void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { } static inline void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq) { } static inline void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto) { } #endif /* CONFIG_AUDITSYSCALL */ static inline void xfrm_pol_hold(struct xfrm_policy *policy) { if (likely(policy != NULL)) refcount_inc(&policy->refcnt); } void xfrm_policy_destroy(struct xfrm_policy *policy); static inline void xfrm_pol_put(struct xfrm_policy *policy) { if (refcount_dec_and_test(&policy->refcnt)) xfrm_policy_destroy(policy); } static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) { int i; for (i = npols - 1; i >= 0; --i) xfrm_pol_put(pols[i]); } void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { refcount_dec(&x->refcnt); } static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) { refcount_inc(&x->refcnt); } static inline bool addr_match(const void *token1, const void *token2, unsigned int prefixlen) { const __be32 *a1 = token1; const __be32 *a2 = token2; unsigned int pdw; unsigned int pbi; if (prefixlen > 128) return false; pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pdw) if (memcmp(a1, a2, pdw << 2)) return false; if (pbi) { __be32 mask; mask = htonl((0xffffffff) << (32 - pbi)); if ((a1[pdw] ^ a2[pdw]) & mask) return false; } return true; } static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen) { /* C99 6.5.7 (3): u32 << 32 is undefined behaviour */ if (sizeof(long) == 4 && prefixlen == 0) return true; if (prefixlen > 32) return false; return !((a1 ^ a2) & htonl(~0UL << (32 - prefixlen))); } static __inline__ __be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = uli->ports.sport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: port = htons(uli->icmpt.type); break; case IPPROTO_MH: port = htons(uli->mht.type); break; case IPPROTO_GRE: port = htons(ntohl(uli->gre_key) >> 16); break; default: port = 0; /*XXX*/ } return port; } static __inline__ __be16 xfrm_flowi_dport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = uli->ports.dport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: port = htons(uli->icmpt.code); break; case IPPROTO_GRE: port = htons(ntohl(uli->gre_key) & 0xffff); break; default: port = 0; /*XXX*/ } return port; } bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, unsigned short family); #ifdef CONFIG_SECURITY_NETWORK_XFRM /* If neither has a context --> match * Otherwise, both must have a context and the sids, doi, alg must match */ static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2) { return ((!s1 && !s2) || (s1 && s2 && (s1->ctx_sid == s2->ctx_sid) && (s1->ctx_doi == s2->ctx_doi) && (s1->ctx_alg == s2->ctx_alg))); } #else static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2) { return true; } #endif /* A struct encoding bundle of transformations to apply to some set of flow. * * xdst->child points to the next element of bundle. * dst->xfrm points to an instanse of transformer. * * Due to unfortunate limitations of current routing cache, which we * have no time to fix, it mirrors struct rtable and bound to the same * routing key, including saddr,daddr. However, we can have many of * bundles differing by session id. All the bundles grow from a parent * policy rule. */ struct xfrm_dst { union { struct dst_entry dst; struct rtable rt; struct rt6_info rt6; } u; struct dst_entry *route; struct dst_entry *child; struct dst_entry *path; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols, num_xfrms; u32 xfrm_genid; u32 policy_genid; u32 route_mtu_cached; u32 child_mtu_cached; u32 route_cookie; u32 path_cookie; }; static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; } #endif return (struct dst_entry *) dst; } static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } #endif return NULL; } #ifdef CONFIG_XFRM static inline void xfrm_dst_set_child(struct xfrm_dst *xdst, struct dst_entry *child) { xdst->child = child; } static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) { xfrm_pols_put(xdst->pols, xdst->num_pols); dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); } #endif void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); struct xfrm_if_parms { int link; /* ifindex of underlying L2 interface */ u32 if_id; /* interface identifier */ bool collect_md; }; struct xfrm_if { struct xfrm_if __rcu *next; /* next interface in list */ struct net_device *dev; /* virtual device associated with interface */ struct net *net; /* netns for packet i/o */ struct xfrm_if_parms p; /* interface parms */ struct gro_cells gro_cells; }; struct xfrm_offload { /* Output sequence number for replay protection on offloading. */ struct { __u32 low; __u32 hi; } seq; __u32 flags; #define SA_DELETE_REQ 1 #define CRYPTO_DONE 2 #define CRYPTO_NEXT_DONE 4 #define CRYPTO_FALLBACK 8 #define XFRM_GSO_SEGMENT 16 #define XFRM_GRO 32 /* 64 is free */ #define XFRM_DEV_RESUME 128 #define XFRM_XMIT 256 __u32 status; #define CRYPTO_SUCCESS 1 #define CRYPTO_GENERIC_ERROR 2 #define CRYPTO_TRANSPORT_AH_AUTH_FAILED 4 #define CRYPTO_TRANSPORT_ESP_AUTH_FAILED 8 #define CRYPTO_TUNNEL_AH_AUTH_FAILED 16 #define CRYPTO_TUNNEL_ESP_AUTH_FAILED 32 #define CRYPTO_INVALID_PACKET_SYNTAX 64 #define CRYPTO_INVALID_PROTOCOL 128 /* Used to keep whole l2 header for transport mode GRO */ __u16 orig_mac_len; __u8 proto; __u8 inner_ipproto; }; struct sec_path { struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; u8 len; u8 olen; u8 verified_cnt; }; struct sec_path *secpath_set(struct sk_buff *skb); static inline void secpath_reset(struct sk_buff *skb) { #ifdef CONFIG_XFRM skb_ext_del(skb, SKB_EXT_SEC_PATH); #endif } static inline int xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) { switch (family) { case AF_INET: return addr->a4 == 0; case AF_INET6: return ipv6_addr_any(&addr->in6); } return 0; } static inline int __xfrm4_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (tmpl->saddr.a4 && tmpl->saddr.a4 != x->props.saddr.a4); } static inline int __xfrm6_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) && !ipv6_addr_equal((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr)); } static inline int xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_cmp(tmpl, x); case AF_INET6: return __xfrm6_state_addr_cmp(tmpl, x); } return !0; } #ifdef CONFIG_XFRM static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) { struct sec_path *sp = skb_sec_path(skb); return sp->xvec[sp->len - 1]; } #endif static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) { #ifdef CONFIG_XFRM struct sec_path *sp = skb_sec_path(skb); if (!sp || !sp->olen || sp->len != sp->olen) return NULL; return &sp->ovec[sp->olen - 1]; #else return NULL; #endif } #ifdef CONFIG_XFRM int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family); static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, int dir) { if (!READ_ONCE(net->xfrm.policy_count[dir]) && !secpath_exists(skb)) return READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_ACCEPT; return false; } static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, int dir, unsigned short family) { if (dir != XFRM_POLICY_OUT && family == AF_INET) { /* same dst may be used for traffic originating from * devices with different policy settings. */ return IPCB(skb)->flags & IPSKB_NOPOLICY; } return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); } static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) { struct net *net = dev_net(skb->dev); int ndir = dir | (reverse ? XFRM_POLICY_MASK + 1 : 0); struct xfrm_offload *xo = xfrm_offload(skb); struct xfrm_state *x; if (sk && sk->sk_policy[XFRM_POLICY_IN]) return __xfrm_policy_check(sk, ndir, skb, family); if (xo) { x = xfrm_input_state(skb); if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) { bool check = (xo->flags & CRYPTO_DONE) && (xo->status & CRYPTO_SUCCESS); /* The packets here are plain ones and secpath was * needed to indicate that hardware already handled * them and there is no need to do nothing in addition. * * Consume secpath which was set by drivers. */ secpath_reset(skb); return check; } } return __xfrm_check_nopolicy(net, skb, dir) || __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { return __xfrm_policy_check2(sk, dir, skb, family, 0); } static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return xfrm_policy_check(sk, dir, skb, AF_INET); } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return xfrm_policy_check(sk, dir, skb, AF_INET6); } static inline int xfrm4_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return __xfrm_policy_check2(sk, dir, skb, AF_INET, 1); } static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return __xfrm_policy_check2(sk, dir, skb, AF_INET6, 1); } int __xfrm_decode_session(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse); static inline int xfrm_decode_session(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family) { return __xfrm_decode_session(net, skb, fl, family, 0); } static inline int xfrm_decode_session_reverse(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family) { return __xfrm_decode_session(net, skb, fl, family, 1); } int __xfrm_route_forward(struct sk_buff *skb, unsigned short family); static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); if (!READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]) && READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]) == XFRM_USERPOLICY_ACCEPT) return true; return (skb_dst(skb)->flags & DST_NOXFRM) || __xfrm_route_forward(skb, family); } static inline int xfrm4_route_forward(struct sk_buff *skb) { return xfrm_route_forward(skb, AF_INET); } static inline int xfrm6_route_forward(struct sk_buff *skb) { return xfrm_route_forward(skb, AF_INET6); } int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { if (!sk_fullsock(osk)) return 0; sk->sk_policy[0] = NULL; sk->sk_policy[1] = NULL; if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) return __xfrm_sk_clone_policy(sk, osk); return 0; } int xfrm_policy_delete(struct xfrm_policy *pol, int dir); static inline void xfrm_sk_free_policy(struct sock *sk) { struct xfrm_policy *pol; pol = rcu_dereference_protected(sk->sk_policy[0], 1); if (unlikely(pol != NULL)) { xfrm_policy_delete(pol, XFRM_POLICY_MAX); sk->sk_policy[0] = NULL; } pol = rcu_dereference_protected(sk->sk_policy[1], 1); if (unlikely(pol != NULL)) { xfrm_policy_delete(pol, XFRM_POLICY_MAX+1); sk->sk_policy[1] = NULL; } } #else static inline void xfrm_sk_free_policy(struct sock *sk) {} static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; } static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { return 1; } static inline int xfrm_decode_session_reverse(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family) { return -ENOSYS; } static inline int xfrm4_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } #endif static __inline__ xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: return (xfrm_address_t *)&fl->u.ip4.daddr; case AF_INET6: return (xfrm_address_t *)&fl->u.ip6.daddr; } return NULL; } static __inline__ xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: return (xfrm_address_t *)&fl->u.ip4.saddr; case AF_INET6: return (xfrm_address_t *)&fl->u.ip6.saddr; } return NULL; } static __inline__ void xfrm_flowi_addr_get(const struct flowi *fl, xfrm_address_t *saddr, xfrm_address_t *daddr, unsigned short family) { switch(family) { case AF_INET: memcpy(&saddr->a4, &fl->u.ip4.saddr, sizeof(saddr->a4)); memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4)); break; case AF_INET6: saddr->in6 = fl->u.ip6.saddr; daddr->in6 = fl->u.ip6.daddr; break; } } static __inline__ int __xfrm4_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (daddr->a4 == x->id.daddr.a4 && (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4)) return 1; return 0; } static __inline__ int __xfrm6_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) && (ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr) || ipv6_addr_any((struct in6_addr *)saddr) || ipv6_addr_any((struct in6_addr *)&x->props.saddr))) return 1; return 0; } static __inline__ int xfrm_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, daddr, saddr); case AF_INET6: return __xfrm6_state_addr_check(x, daddr, saddr); } return 0; } static __inline__ int xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, (const xfrm_address_t *)&fl->u.ip4.daddr, (const xfrm_address_t *)&fl->u.ip4.saddr); case AF_INET6: return __xfrm6_state_addr_check(x, (const xfrm_address_t *)&fl->u.ip6.daddr, (const xfrm_address_t *)&fl->u.ip6.saddr); } return 0; } static inline int xfrm_state_kern(const struct xfrm_state *x) { return atomic_read(&x->tunnel_users); } static inline bool xfrm_id_proto_valid(u8 proto) { switch (proto) { case IPPROTO_AH: case IPPROTO_ESP: case IPPROTO_COMP: #if IS_ENABLED(CONFIG_IPV6) case IPPROTO_ROUTING: case IPPROTO_DSTOPTS: #endif return true; default: return false; } } /* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */ static inline int xfrm_id_proto_match(u8 proto, u8 userproto) { return (!userproto || proto == userproto || (userproto == IPSEC_PROTO_ANY && (proto == IPPROTO_AH || proto == IPPROTO_ESP || proto == IPPROTO_COMP))); } /* * xfrm algorithm information */ struct xfrm_algo_aead_info { char *geniv; u16 icv_truncbits; }; struct xfrm_algo_auth_info { u16 icv_truncbits; u16 icv_fullbits; }; struct xfrm_algo_encr_info { char *geniv; u16 blockbits; u16 defkeybits; }; struct xfrm_algo_comp_info { u16 threshold; }; struct xfrm_algo_desc { char *name; char *compat; u8 available:1; u8 pfkey_supported:1; union { struct xfrm_algo_aead_info aead; struct xfrm_algo_auth_info auth; struct xfrm_algo_encr_info encr; struct xfrm_algo_comp_info comp; } uinfo; struct sadb_alg desc; }; /* XFRM protocol handlers. */ struct xfrm4_protocol { int (*handler)(struct sk_buff *skb); int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm4_protocol __rcu *next; int priority; }; struct xfrm6_protocol { int (*handler)(struct sk_buff *skb); int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); struct xfrm6_protocol __rcu *next; int priority; }; /* XFRM tunnel handlers. */ struct xfrm_tunnel { int (*handler)(struct sk_buff *skb); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm_tunnel __rcu *next; int priority; }; struct xfrm6_tunnel { int (*handler)(struct sk_buff *skb); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); struct xfrm6_tunnel __rcu *next; int priority; }; void xfrm_init(void); void xfrm4_init(void); int xfrm_state_init(struct net *net); void xfrm_state_fini(struct net *net); void xfrm4_state_init(void); void xfrm4_protocol_init(void); #ifdef CONFIG_XFRM int xfrm6_init(void); void xfrm6_fini(void); int xfrm6_state_init(void); void xfrm6_state_fini(void); int xfrm6_protocol_init(void); void xfrm6_protocol_fini(void); #else static inline int xfrm6_init(void) { return 0; } static inline void xfrm6_fini(void) { ; } #endif #ifdef CONFIG_XFRM_STATISTICS int xfrm_proc_init(struct net *net); void xfrm_proc_fini(struct net *net); #endif int xfrm_sysctl_init(struct net *net); #ifdef CONFIG_SYSCTL void xfrm_sysctl_fini(struct net *net); #else static inline void xfrm_sysctl_fini(struct net *net) { } #endif void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, struct xfrm_address_filter *filter); int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net); struct xfrm_state *xfrm_state_alloc(struct net *net); void xfrm_state_free(struct xfrm_state *x); struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family, u32 if_id); struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid); struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family); int xfrm_state_check_expire(struct xfrm_state *x); void xfrm_state_update_stats(struct net *net); #ifdef CONFIG_XFRM_OFFLOAD static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) { struct xfrm_dev_offload *xdo = &x->xso; struct net_device *dev = READ_ONCE(xdo->dev); if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_update_stats) dev->xfrmdev_ops->xdo_dev_state_update_stats(x); } #else static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) {} #endif void xfrm_state_insert(struct xfrm_state *x); int xfrm_state_add(struct xfrm_state *x); int xfrm_state_update(struct xfrm_state *x); struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family); void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family); #else static inline void xfrm_tmpl_sort(struct xfrm_tmpl **d, struct xfrm_tmpl **s, int n, unsigned short family) { } static inline void xfrm_state_sort(struct xfrm_state **d, struct xfrm_state **s, int n, unsigned short family) { } #endif struct xfrmk_sadinfo { u32 sadhcnt; /* current hash bkts */ u32 sadhmcnt; /* max allowed hash bkts */ u32 sadcnt; /* current running count */ }; struct xfrmk_spdinfo { u32 incnt; u32 outcnt; u32 fwdcnt; u32 inscnt; u32 outscnt; u32 fwdscnt; u32 spdhcnt; u32 spdhmcnt; }; struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack); int xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); int xfrm_trans_queue(struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); int xfrm4_tunnel_check_size(struct sk_buff *skb); #if IS_ENABLED(CONFIG_IPV6) int xfrm6_tunnel_check_size(struct sk_buff *skb); #else static inline int xfrm6_tunnel_check_size(struct sk_buff *skb) { return -EMSGSIZE; } #endif #if IS_ENABLED(CONFIG_NET_PKTGEN) int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb); #endif void xfrm_local_error(struct sk_buff *skb, int mtu); int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm4_transport_finish(struct sk_buff *skb, int async); int xfrm4_rcv(struct sk_buff *skb); static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return xfrm_input(skb, nexthdr, spi, 0); } int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); void xfrm4_local_error(struct sk_buff *skb, u32 mtu); int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, struct ip6_tnl *t); int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm6_transport_finish(struct sk_buff *skb, int async); int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t); int xfrm6_rcv(struct sk_buff *skb); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto); void xfrm6_local_error(struct sk_buff *skb, u32 mtu); int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family); __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_XFRM void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu); int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, struct sk_buff *skb); struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, struct sk_buff *skb); int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen); #else static inline int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { return -ENOPROTOOPT; } #endif struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type); int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); struct xfrm_policy *xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi, struct netlink_ext_ack *extack); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap); struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id); struct xfrm_state *xfrm_state_migrate_create(struct xfrm_state *x, const struct xfrm_migrate *m, struct net *net, struct netlink_ext_ack *extack); int xfrm_state_migrate_install(const struct xfrm_state *x, struct xfrm_state *xc, const struct xfrm_migrate *m, struct netlink_ext_ack *extack); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct net *net, struct netlink_ext_ack *extack); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k, struct net *net, struct xfrm_encap_tmpl *encap, u32 if_id, struct netlink_ext_ack *extack, struct xfrm_user_offload *xuo); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid); int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); void xfrm_input_init(void); int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq); void xfrm_probe_algs(void); int xfrm_count_pfkey_auth_supported(void); int xfrm_count_pfkey_enc_supported(void); struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx); struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx); struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len, int probe); static inline bool xfrm6_addr_equal(const xfrm_address_t *a, const xfrm_address_t *b) { return ipv6_addr_equal((const struct in6_addr *)a, (const struct in6_addr *)b); } static inline bool xfrm_addr_equal(const xfrm_address_t *a, const xfrm_address_t *b, sa_family_t family) { switch (family) { default: case AF_INET: return ((__force u32)a->a4 ^ (__force u32)b->a4) == 0; case AF_INET6: return xfrm6_addr_equal(a, b); } } static inline int xfrm_policy_id2dir(u32 index) { return index & 7; } #ifdef CONFIG_XFRM void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq); int xfrm_replay_check(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); void xfrm_replay_notify(struct xfrm_state *x, int event); int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); int xfrm_replay_recheck(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); static inline int xfrm_aevent_is_on(struct net *net) { struct sock *nlsk; int ret = 0; rcu_read_lock(); nlsk = rcu_dereference(net->xfrm.nlsk); if (nlsk) ret = netlink_has_listeners(nlsk, XFRMNLGRP_AEVENTS); rcu_read_unlock(); return ret; } static inline int xfrm_acquire_is_on(struct net *net) { struct sock *nlsk; int ret = 0; rcu_read_lock(); nlsk = rcu_dereference(net->xfrm.nlsk); if (nlsk) ret = netlink_has_listeners(nlsk, XFRMNLGRP_ACQUIRE); rcu_read_unlock(); return ret; } #endif static inline unsigned int aead_len(struct xfrm_algo_aead *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn) { return sizeof(*replay_esn) + replay_esn->bmp_len * sizeof(__u32); } #ifdef CONFIG_XFRM_MIGRATE static inline int xfrm_replay_clone(struct xfrm_state *x, const struct xfrm_state *orig) { /* Counters synced later in xfrm_replay_sync() */ x->replay = orig->replay; x->preplay = orig->preplay; if (orig->replay_esn) { x->replay_esn = kmemdup(orig->replay_esn, xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; x->preplay_esn = kmemdup(orig->preplay_esn, xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); if (!x->preplay_esn) return -ENOMEM; } return 0; } static inline void xfrm_replay_sync(struct xfrm_state *x, const struct xfrm_state *orig) { x->replay = orig->replay; x->preplay = orig->preplay; if (orig->replay_esn) { memcpy(x->replay_esn, orig->replay_esn, xfrm_replay_state_esn_len(orig->replay_esn)); memcpy(x->preplay_esn, orig->preplay_esn, xfrm_replay_state_esn_len(orig->preplay_esn)); } } static inline void xfrm_migrate_sync(struct xfrm_state *x, const struct xfrm_state *orig) { /* called under lock so no race conditions or mallocs allowed */ memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); xfrm_replay_sync(x, orig); } static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig) { return kmemdup(orig, aead_len(orig), GFP_KERNEL); } static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); } static inline struct xfrm_algo_auth *xfrm_algo_auth_clone(struct xfrm_algo_auth *orig) { return kmemdup(orig, xfrm_alg_auth_len(orig), GFP_KERNEL); } static inline void xfrm_states_put(struct xfrm_state **states, int n) { int i; for (i = 0; i < n; i++) xfrm_state_put(*(states + i)); } static inline void xfrm_states_delete(struct xfrm_state **states, int n) { int i; for (i = 0; i < n; i++) xfrm_state_delete(*(states + i)); } #endif void __init xfrm_dev_init(void); #ifdef CONFIG_XFRM_OFFLOAD void xfrm_dev_resume(struct sk_buff *skb); void xfrm_dev_backlog(struct softnet_data *sd); struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, const struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); void xfrm_dev_state_delete(struct xfrm_state *x); void xfrm_dev_state_free(struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev && dev->xfrmdev_ops->xdo_dev_state_advance_esn) dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); } static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { struct xfrm_state *x = dst->xfrm; struct xfrm_dst *xdst; if (!x || !x->type_offload) return false; xdst = (struct xfrm_dst *) dst; if (!x->xso.offload_handle && !xdst->child->xfrm) return true; if (x->xso.offload_handle && (x->xso.dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) return true; return false; } static inline void xfrm_dev_policy_delete(struct xfrm_policy *x) { struct xfrm_dev_offload *xdo = &x->xdo; struct net_device *dev = xdo->dev; if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_policy_delete) dev->xfrmdev_ops->xdo_dev_policy_delete(x); } static inline void xfrm_dev_policy_free(struct xfrm_policy *x) { struct xfrm_dev_offload *xdo = &x->xdo; struct net_device *dev = xdo->dev; if (dev && dev->xfrmdev_ops) { if (dev->xfrmdev_ops->xdo_dev_policy_free) dev->xfrmdev_ops->xdo_dev_policy_free(x); xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); } } #else static inline void xfrm_dev_resume(struct sk_buff *skb) { } static inline void xfrm_dev_backlog(struct softnet_data *sd) { } static inline struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { return skb; } static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, const struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { return 0; } static inline void xfrm_dev_state_delete(struct xfrm_state *x) { } static inline void xfrm_dev_state_free(struct xfrm_state *x) { } static inline int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { return 0; } static inline void xfrm_dev_policy_delete(struct xfrm_policy *x) { } static inline void xfrm_dev_policy_free(struct xfrm_policy *x) { } static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { return false; } static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { } static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { return false; } #endif static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) { if (attrs[XFRMA_MARK]) memcpy(m, nla_data(attrs[XFRMA_MARK]), sizeof(struct xfrm_mark)); else m->v = m->m = 0; return m->v & m->m; } static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) { int ret = 0; if (m->m | m->v) ret = nla_put(skb, XFRMA_MARK, sizeof(struct xfrm_mark), m); return ret; } static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x) { struct xfrm_mark *m = &x->props.smark; return (m->v & m->m) | (mark & ~m->m); } static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id) { int ret = 0; if (if_id) ret = nla_put_u32(skb, XFRMA_IF_ID, if_id); return ret; } static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, unsigned int family) { bool tunnel = false; switch(family) { case AF_INET: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) tunnel = true; break; case AF_INET6: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) tunnel = true; break; } if (tunnel && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL)) return -EINVAL; return 0; } extern const int xfrm_msg_min[XFRM_NR_MSGTYPES]; extern const struct nla_policy xfrma_policy[XFRMA_MAX+1]; struct xfrm_translator { /* Allocate frag_list and put compat translation there */ int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src); /* Allocate nlmsg with 64-bit translaton of received 32-bit message */ struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack); /* Translate 32-bit user_policy from sockptr */ int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen); struct module *owner; }; #if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) extern int xfrm_register_translator(struct xfrm_translator *xtr); extern int xfrm_unregister_translator(struct xfrm_translator *xtr); extern struct xfrm_translator *xfrm_get_translator(void); extern void xfrm_put_translator(struct xfrm_translator *xtr); #else static inline struct xfrm_translator *xfrm_get_translator(void) { return NULL; } static inline void xfrm_put_translator(struct xfrm_translator *xtr) { } #endif #if IS_ENABLED(CONFIG_IPV6) static inline bool xfrm6_local_dontfrag(const struct sock *sk) { int proto; if (!sk || sk->sk_family != AF_INET6) return false; proto = sk->sk_protocol; if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) return inet6_test_bit(DONTFRAG, sk); return false; } #endif #if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) extern struct metadata_dst __percpu *xfrm_bpf_md_dst; int register_xfrm_interface_bpf(void); #else static inline int register_xfrm_interface_bpf(void) { return 0; } #endif #if IS_ENABLED(CONFIG_DEBUG_INFO_BTF) int register_xfrm_state_bpf(void); #else static inline int register_xfrm_state_bpf(void) { return 0; } #endif int xfrm_nat_keepalive_init(unsigned short family); void xfrm_nat_keepalive_fini(unsigned short family); int xfrm_nat_keepalive_net_init(struct net *net); int xfrm_nat_keepalive_net_fini(struct net *net); void xfrm_nat_keepalive_state_updated(struct xfrm_state *x); #endif /* _NET_XFRM_H */ |
| 20 21 21 21 3 3 3 3 3 3 3 3 3 3 3 18 18 18 21 20 21 18 21 21 18 18 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 | // SPDX-License-Identifier: GPL-2.0 /* * From setup-res.c, by: * Dave Rusling (david.rusling@reo.mts.dec.com) * David Mosberger (davidm@cs.arizona.edu) * David Miller (davem@redhat.com) * Ivan Kokshaysky (ink@jurassic.park.msu.ru) */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/cleanup.h> #include <linux/pci.h> #include <linux/errno.h> #include <linux/ioport.h> #include <linux/of.h> #include <linux/of_platform.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/proc_fs.h> #include <linux/slab.h> #include "pci.h" /* * The first PCI_BRIDGE_RESOURCE_NUM PCI bus resources (those that correspond * to P2P or CardBus bridge windows) go in a table. Additional ones (for * buses below host bridges or subtractive decode bridges) go in the list. * Use pci_bus_for_each_resource() to iterate through all the resources. */ struct pci_bus_resource { struct list_head list; struct resource *res; }; void pci_add_resource_offset(struct list_head *resources, struct resource *res, resource_size_t offset) { struct resource_entry *entry; entry = resource_list_create_entry(res, 0); if (!entry) { pr_err("PCI: can't add host bridge window %pR\n", res); return; } entry->offset = offset; resource_list_add_tail(entry, resources); } EXPORT_SYMBOL(pci_add_resource_offset); void pci_add_resource(struct list_head *resources, struct resource *res) { pci_add_resource_offset(resources, res, 0); } EXPORT_SYMBOL(pci_add_resource); void pci_free_resource_list(struct list_head *resources) { resource_list_free(resources); } EXPORT_SYMBOL(pci_free_resource_list); void pci_bus_add_resource(struct pci_bus *bus, struct resource *res) { struct pci_bus_resource *bus_res; bus_res = kzalloc_obj(struct pci_bus_resource); if (!bus_res) { dev_err(&bus->dev, "can't add %pR resource\n", res); return; } bus_res->res = res; list_add_tail(&bus_res->list, &bus->resources); } struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n) { struct pci_bus_resource *bus_res; if (n < PCI_BRIDGE_RESOURCE_NUM) return bus->resource[n]; n -= PCI_BRIDGE_RESOURCE_NUM; list_for_each_entry(bus_res, &bus->resources, list) { if (n-- == 0) return bus_res->res; } return NULL; } EXPORT_SYMBOL_GPL(pci_bus_resource_n); void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res) { struct pci_bus_resource *bus_res, *tmp; int i; for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) { if (bus->resource[i] == res) { bus->resource[i] = NULL; return; } } list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) { if (bus_res->res == res) { list_del(&bus_res->list); kfree(bus_res); return; } } } void pci_bus_remove_resources(struct pci_bus *bus) { int i; struct pci_bus_resource *bus_res, *tmp; for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) bus->resource[i] = NULL; list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) { list_del(&bus_res->list); kfree(bus_res); } } int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources) { struct resource_entry *win; struct resource *parent, *res; int err; resource_list_for_each_entry(win, resources) { res = win->res; switch (resource_type(res)) { case IORESOURCE_IO: parent = &ioport_resource; break; case IORESOURCE_MEM: parent = &iomem_resource; break; default: continue; } err = devm_request_resource(dev, parent, res); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(devm_request_pci_bus_resources); static struct pci_bus_region pci_32_bit = {0, 0xffffffffULL}; #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT static struct pci_bus_region pci_64_bit = {0, (pci_bus_addr_t) 0xffffffffffffffffULL}; static struct pci_bus_region pci_high = {(pci_bus_addr_t) 0x100000000ULL, (pci_bus_addr_t) 0xffffffffffffffffULL}; #endif /* * @res contains CPU addresses. Clip it so the corresponding bus addresses * on @bus are entirely within @region. This is used to control the bus * addresses of resources we allocate, e.g., we may need a resource that * can be mapped by a 32-bit BAR. */ static void pci_clip_resource_to_region(struct pci_bus *bus, struct resource *res, struct pci_bus_region *region) { struct pci_bus_region r; pcibios_resource_to_bus(bus, &r, res); if (r.start < region->start) r.start = region->start; if (r.end > region->end) r.end = region->end; if (r.end < r.start) res->end = res->start - 1; else pcibios_bus_to_resource(bus, res, &r); } static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res, resource_size_t size, resource_size_t align, resource_size_t min, unsigned long type_mask, resource_alignf alignf, void *alignf_data, struct pci_bus_region *region) { struct resource *r, avail; resource_size_t max; int ret; type_mask |= IORESOURCE_TYPE_BITS; pci_bus_for_each_resource(bus, r) { resource_size_t min_used = min; if (!r) continue; if (r->flags & (IORESOURCE_UNSET|IORESOURCE_DISABLED)) continue; /* type_mask must match */ if ((res->flags ^ r->flags) & type_mask) continue; /* We cannot allocate a non-prefetching resource from a pre-fetching area */ if ((r->flags & IORESOURCE_PREFETCH) && !(res->flags & IORESOURCE_PREFETCH)) continue; avail = *r; pci_clip_resource_to_region(bus, &avail, region); /* * "min" is typically PCIBIOS_MIN_IO or PCIBIOS_MIN_MEM to * protect badly documented motherboard resources, but if * this is an already-configured bridge window, its start * overrides "min". */ if (avail.start) min_used = avail.start; max = avail.end; /* Don't bother if available space isn't large enough */ if (size > max - min_used + 1) continue; /* Ok, try it out.. */ ret = allocate_resource(r, res, size, min_used, max, align, alignf, alignf_data); if (ret == 0) return 0; } return -ENOMEM; } /** * pci_bus_alloc_resource - allocate a resource from a parent bus * @bus: PCI bus * @res: resource to allocate * @size: size of resource to allocate * @align: alignment of resource to allocate * @min: minimum /proc/iomem address to allocate * @type_mask: IORESOURCE_* type flags * @alignf: resource alignment function * @alignf_data: data argument for resource alignment function * * Given the PCI bus a device resides on, the size, minimum address, * alignment and type, try to find an acceptable resource allocation * for a specific device resource. */ int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res, resource_size_t size, resource_size_t align, resource_size_t min, unsigned long type_mask, resource_alignf alignf, void *alignf_data) { #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT int rc; if (res->flags & IORESOURCE_MEM_64) { rc = pci_bus_alloc_from_region(bus, res, size, align, min, type_mask, alignf, alignf_data, &pci_high); if (rc == 0) return 0; return pci_bus_alloc_from_region(bus, res, size, align, min, type_mask, alignf, alignf_data, &pci_64_bit); } #endif return pci_bus_alloc_from_region(bus, res, size, align, min, type_mask, alignf, alignf_data, &pci_32_bit); } EXPORT_SYMBOL(pci_bus_alloc_resource); /* * The @idx resource of @dev should be a PCI-PCI bridge window. If this * resource fits inside a window of an upstream bridge, do nothing. If it * overlaps an upstream window but extends outside it, clip the resource so * it fits completely inside. */ bool pci_bus_clip_resource(struct pci_dev *dev, int idx) { struct pci_bus *bus = dev->bus; struct resource *res = &dev->resource[idx]; struct resource orig_res = *res; struct resource *r; pci_bus_for_each_resource(bus, r) { resource_size_t start, end; if (!r) continue; if (resource_type(res) != resource_type(r)) continue; start = max(r->start, res->start); end = min(r->end, res->end); if (start > end) continue; /* no overlap */ if (res->start == start && res->end == end) return false; /* no change */ res->start = start; res->end = end; res->flags &= ~IORESOURCE_UNSET; orig_res.flags &= ~IORESOURCE_UNSET; pci_info(dev, "%pR clipped to %pR\n", &orig_res, res); return true; } return false; } void __weak pcibios_resource_survey_bus(struct pci_bus *bus) { } void __weak pcibios_bus_add_device(struct pci_dev *pdev) { } /** * pci_bus_add_device - start driver for a single device * @dev: device to add * * This adds add sysfs entries and start device drivers */ void pci_bus_add_device(struct pci_dev *dev) { struct device_node *dn = dev->dev.of_node; /* * Can not put in pci_device_add yet because resources * are not assigned yet for some devices. */ pcibios_bus_add_device(dev); pci_fixup_device(pci_fixup_final, dev); if (pci_is_bridge(dev)) of_pci_make_dev_node(dev); pci_proc_attach_device(dev); pci_bridge_d3_update(dev); /* Save config space for error recoverability */ pci_save_state(dev); /* * Enable runtime PM, which potentially allows the device to * suspend immediately, only after the PCI state has been * configured completely. */ pm_runtime_enable(&dev->dev); if (!dn || of_device_is_available(dn)) pci_dev_allow_binding(dev); device_initial_probe(&dev->dev); pci_dev_assign_added(dev); } EXPORT_SYMBOL_GPL(pci_bus_add_device); /** * pci_bus_add_devices - start driver for PCI devices * @bus: bus to check for new devices * * Start driver for PCI devices and add some sysfs entries. */ void pci_bus_add_devices(const struct pci_bus *bus) { struct pci_dev *dev; struct pci_bus *child; list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip already-added devices */ if (pci_dev_is_added(dev)) continue; pci_bus_add_device(dev); } list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip if device attach failed */ if (!pci_dev_is_added(dev)) continue; child = dev->subordinate; if (child) pci_bus_add_devices(child); } } EXPORT_SYMBOL(pci_bus_add_devices); static int __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) { struct pci_dev *dev; int ret = 0; list_for_each_entry(dev, &top->devices, bus_list) { ret = cb(dev, userdata); if (ret) break; if (dev->subordinate) { ret = __pci_walk_bus(dev->subordinate, cb, userdata); if (ret) break; } } return ret; } static int __pci_walk_bus_reverse(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) { struct pci_dev *dev; int ret = 0; list_for_each_entry_reverse(dev, &top->devices, bus_list) { if (dev->subordinate) { ret = __pci_walk_bus_reverse(dev->subordinate, cb, userdata); if (ret) break; } ret = cb(dev, userdata); if (ret) break; } return ret; } /** * pci_walk_bus - walk devices on/under bus, calling callback. * @top: bus whose devices should be walked * @cb: callback to be called for each device found * @userdata: arbitrary pointer to be passed to callback * * Walk the given bus, including any bridged devices * on buses under this bus. Call the provided callback * on each device found. * * We check the return of @cb each time. If it returns anything * other than 0, we break out. */ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) { down_read(&pci_bus_sem); __pci_walk_bus(top, cb, userdata); up_read(&pci_bus_sem); } EXPORT_SYMBOL_GPL(pci_walk_bus); /** * pci_walk_bus_reverse - walk devices on/under bus, calling callback. * @top: bus whose devices should be walked * @cb: callback to be called for each device found * @userdata: arbitrary pointer to be passed to callback * * Same semantics as pci_walk_bus(), but walks the bus in reverse order. */ void pci_walk_bus_reverse(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) { down_read(&pci_bus_sem); __pci_walk_bus_reverse(top, cb, userdata); up_read(&pci_bus_sem); } EXPORT_SYMBOL_GPL(pci_walk_bus_reverse); void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) { lockdep_assert_held(&pci_bus_sem); __pci_walk_bus(top, cb, userdata); } struct pci_bus *pci_bus_get(struct pci_bus *bus) { if (bus) get_device(&bus->dev); return bus; } void pci_bus_put(struct pci_bus *bus) { if (bus) put_device(&bus->dev); } |
| 165 308 1 68 251 251 4 118 194 194 193 151 151 149 151 191 38 170 6 18 167 6 168 32 169 161 161 433 374 251 151 192 42 432 3115 3095 402 3115 9 9 9 549 155 11 148 93 156 155 101 102 56 102 102 69 24 78 78 77 66 93 93 80 3 77 66 12 12 121 130 12 121 167 47 54 12 126 130 13 130 127 3 5 120 4 7 6 2 2 4 117 116 1 117 108 8 13 117 13 98 4 91 27 1 18 18 18 61 6 20 3 58 58 58 42 3 39 38 38 38 4 34 25 25 25 12 12 10 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/mlock.c * * (C) Copyright 1995 Linus Torvalds * (C) Copyright 2002 Christoph Hellwig */ #include <linux/capability.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/sched/user.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/folio_batch.h> #include <linux/pagewalk.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> #include <linux/export.h> #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/secretmem.h> #include "internal.h" struct mlock_fbatch { local_lock_t lock; struct folio_batch fbatch; }; static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = { .lock = INIT_LOCAL_LOCK(lock), }; bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) return true; if (capable(CAP_IPC_LOCK)) return true; return false; } EXPORT_SYMBOL(can_do_mlock); /* * Mlocked folios are marked with the PG_mlocked flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate * statistics. * * An mlocked folio [folio_test_mlocked(folio)] is unevictable. As such, it * will be ostensibly placed on the LRU "unevictable" list (actually no such * list exists), rather than the [in]active lists. PG_unevictable is set to * indicate the unevictable state. */ static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec) { /* There is nothing more we can do while it's off LRU */ if (!folio_test_clear_lru(folio)) return lruvec; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (unlikely(folio_evictable(folio))) { /* * This is a little surprising, but quite possible: PG_mlocked * must have got cleared already by another CPU. Could this * folio be unevictable? I'm not sure, but move it now if so. */ if (folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, folio_nr_pages(folio)); } goto out; } if (folio_test_unevictable(folio)) { if (folio_test_mlocked(folio)) folio->mlock_count++; goto out; } lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: folio_set_lru(folio); return lruvec; } static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); lruvec = folio_lruvec_relock_irq(folio, lruvec); /* As above, this is a little surprising, but possible */ if (unlikely(folio_evictable(folio))) goto out; folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: lruvec_add_folio(lruvec, folio); folio_set_lru(folio); return lruvec; } static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec) { int nr_pages = folio_nr_pages(folio); bool isolated = false; if (!folio_test_clear_lru(folio)) goto munlock; isolated = true; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_test_unevictable(folio)) { /* Then mlock_count is maintained, but might undercount */ if (folio->mlock_count) folio->mlock_count--; if (folio->mlock_count) goto out; } /* else assume that was the last mlock: reclaim will fix it if not */ munlock: if (folio_test_clear_mlocked(folio)) { __zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); if (isolated || !folio_test_unevictable(folio)) __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); else __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); } /* folio_evictable() has to be checked *after* clearing Mlocked */ if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } out: if (isolated) folio_set_lru(folio); return lruvec; } /* * Flags held in the low bits of a struct folio pointer on the mlock_fbatch. */ #define LRU_FOLIO 0x1 #define NEW_FOLIO 0x2 static inline struct folio *mlock_lru(struct folio *folio) { return (struct folio *)((unsigned long)folio + LRU_FOLIO); } static inline struct folio *mlock_new(struct folio *folio) { return (struct folio *)((unsigned long)folio + NEW_FOLIO); } /* * mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can * make use of such folio pointer flags in future, but for now just keep it for * mlock. We could use three separate folio batches instead, but one feels * better (munlocking a full folio batch does not need to drain mlocking folio * batches first). */ static void mlock_folio_batch(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; unsigned long mlock; struct folio *folio; int i; for (i = 0; i < folio_batch_count(fbatch); i++) { folio = fbatch->folios[i]; mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO); folio = (struct folio *)((unsigned long)folio - mlock); fbatch->folios[i] = folio; if (mlock & LRU_FOLIO) lruvec = __mlock_folio(folio, lruvec); else if (mlock & NEW_FOLIO) lruvec = __mlock_new_folio(folio, lruvec); else lruvec = __munlock_folio(folio, lruvec); } if (lruvec) lruvec_unlock_irq(lruvec); folios_put(fbatch); } void mlock_drain_local(void) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } void mlock_drain_remote(int cpu) { struct folio_batch *fbatch; WARN_ON_ONCE(cpu_online(cpu)); fbatch = &per_cpu(mlock_fbatch.fbatch, cpu); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); } bool need_mlock_drain(int cpu) { return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu)); } /** * mlock_folio - mlock a folio already on (or temporarily off) LRU * @folio: folio to be mlocked. */ void mlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (!folio_test_set_mlocked(folio)) { int nr_pages = folio_nr_pages(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * mlock_new_folio - mlock a newly allocated folio not yet on LRU * @folio: folio to be mlocked, either normal or a THP head. */ void mlock_new_folio(struct folio *folio) { struct folio_batch *fbatch; int nr_pages = folio_nr_pages(folio); local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); folio_set_mlocked(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * munlock_folio - munlock a folio * @folio: folio to be munlocked, either normal or a THP head. */ void munlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); /* * folio_test_clear_mlocked(folio) must be left to __munlock_folio(), * which will check whether the folio is multiply mlocked. */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } static inline unsigned int folio_mlock_step(struct folio *folio, pte_t *pte, unsigned long addr, unsigned long end) { unsigned int count = (end - addr) >> PAGE_SHIFT; pte_t ptent = ptep_get(pte); if (!folio_test_large(folio)) return 1; return folio_pte_batch(folio, pte, ptent, count); } static inline bool allow_mlock_munlock(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned int step) { /* * For unlock, allow munlock large folio which is partially * mapped to VMA. As it's possible that large folio is * mlocked and VMA is split later. * * During memory pressure, such kind of large folio can * be split. And the pages are not in VM_LOCKed VMA * can be reclaimed. */ if (!(vma->vm_flags & VM_LOCKED)) return true; /* folio_within_range() cannot take KSM, but any small folio is OK */ if (!folio_test_large(folio)) return true; /* folio not in range [start, end), skip mlock */ if (!folio_within_range(folio, vma, start, end)) return false; /* folio is not fully mapped, skip mlock */ if (step != folio_nr_pages(folio)) return false; return true; } static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; unsigned int step = 1; unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (!pmd_present(*pmd)) goto out; if (is_huge_zero_pmd(*pmd)) goto out; folio = pmd_folio(*pmd); if (folio_is_zone_device(folio)) goto out; if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); goto out; } start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) { walk->action = ACTION_AGAIN; return 0; } for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; step = folio_mlock_step(folio, pte, addr, end); if (!allow_mlock_munlock(folio, vma, start, end, step)) goto next_entry; if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); next_entry: pte += step - 1; addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: spin_unlock(ptl); cond_resched(); return 0; } /* * mlock_vma_pages_range() - mlock any pages already in the range, * or munlock all pages in the range. * @vma - vma containing range to be mlock()ed or munlock()ed * @start - start address in @vma of the range * @end - end of range in @vma * @new_vma_flags - the new set of flags for @vma. * * Called for mlock(), mlock2() and mlockall(), to set @vma VM_LOCKED; * called for munlock() and munlockall(), to clear VM_LOCKED from @vma. */ static void mlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, vma_flags_t *new_vma_flags) { static const struct mm_walk_ops mlock_walk_ops = { .pmd_entry = mlock_pte_range, .walk_lock = PGWALK_WRLOCK_VERIFY, }; /* * There is a slight chance that concurrent page migration, * or page reclaim finding a page of this now-VM_LOCKED vma, * will call mlock_vma_folio() and raise page's mlock_count: * double counting, leaving the page unevictable indefinitely. * Communicate this danger to mlock_vma_folio() with VM_IO, * which is a VM_SPECIAL flag not allowed on VM_LOCKED vmas. * mmap_lock is held in write mode here, so this weird * combination should not be visible to other mmap_lock users; * but WRITE_ONCE so rmap walkers must see VM_IO if VM_LOCKED. */ if (vma_flags_test(new_vma_flags, VMA_LOCKED_BIT)) vma_flags_set(new_vma_flags, VMA_IO_BIT); vma_start_write(vma); vma_flags_reset_once(vma, new_vma_flags); lru_add_drain(); walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); lru_add_drain(); if (vma_flags_test(new_vma_flags, VMA_IO_BIT)) { vma_flags_clear(new_vma_flags, VMA_IO_BIT); vma_flags_reset_once(vma, new_vma_flags); } } /* * mlock_fixup - handle mlock[all]/munlock[all] requests. * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, vm_flags_t newflags) { vma_flags_t new_vma_flags = legacy_to_vma_flags(newflags); const vma_flags_t old_vma_flags = vma->flags; struct mm_struct *mm = vma->vm_mm; int nr_pages; int ret = 0; if (vma_flags_same_pair(&old_vma_flags, &new_vma_flags) || vma_is_secretmem(vma) || !vma_supports_mlock(vma)) { /* * Don't set VM_LOCKED or VM_LOCKONFAULT and don't count. * For secretmem, don't allow the memory to be unlocked. */ goto out; } vma = vma_modify_flags(vmi, *prev, vma, start, end, &new_vma_flags); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } /* * Keep track of amount of locked VM. */ nr_pages = (end - start) >> PAGE_SHIFT; if (!vma_flags_test(&new_vma_flags, VMA_LOCKED_BIT)) nr_pages = -nr_pages; else if (vma_flags_test(&old_vma_flags, VMA_LOCKED_BIT)) nr_pages = 0; mm->locked_vm += nr_pages; /* * vm_flags is protected by the mmap_lock held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ if (vma_flags_test(&new_vma_flags, VMA_LOCKED_BIT) && vma_flags_test(&old_vma_flags, VMA_LOCKED_BIT)) { /* No work to do, and mlocking twice would be wrong */ vma_start_write(vma); vma->flags = new_vma_flags; } else { mlock_vma_pages_range(vma, start, end, &new_vma_flags); } out: *prev = vma; return ret; } static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; struct vm_area_struct *vma, *prev; VMA_ITERATOR(vmi, current->mm, start); VM_BUG_ON(offset_in_page(start)); VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; vma = vma_iter_load(&vmi); if (!vma) return -ENOMEM; prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; nstart = start; tmp = vma->vm_start; for_each_vma_range(vmi, vma, end) { int error; vm_flags_t newflags; if (vma->vm_start != tmp) return -ENOMEM; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= flags; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; if (tmp > end) tmp = end; error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags); if (error) return error; tmp = vma_iter_end(&vmi); nstart = tmp; } if (tmp < end) return -ENOMEM; return 0; } /* * Go through vma areas and sum size of mlocked * vma pages, as return value. * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) * is also counted. * Return value: previously mlocked page counts */ static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; unsigned long count = 0; unsigned long end; VMA_ITERATOR(vmi, mm, start); /* Don't overflow past ULONG_MAX */ if (unlikely(ULONG_MAX - len < start)) end = ULONG_MAX; else end = start + len; for_each_vma_range(vmi, vma, end) { if (vma->vm_flags & VM_LOCKED) { if (start > vma->vm_start) count -= (start - vma->vm_start); if (end < vma->vm_end) { count += end - vma->vm_start; break; } count += vma->vm_end - vma->vm_start; } } return count >> PAGE_SHIFT; } /* * convert get_user_pages() return value to posix mlock() error */ static int __mlock_posix_error_return(long retval) { if (retval == -EFAULT) retval = -ENOMEM; else if (retval == -ENOMEM) retval = -EAGAIN; return retval; } static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; int error = -ENOMEM; start = untagged_addr(start); if (!can_do_mlock()) return -EPERM; len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; locked += current->mm->locked_vm; if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { /* * It is possible that the regions requested intersect with * previously mlocked areas, that part area in "mm->locked_vm" * should not be counted to new mlock increment count. So check * and adjust locked count if necessary. */ locked -= count_mm_mlocked_page_nr(current->mm, start, len); } /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = apply_vma_lock_flags(start, len, flags); mmap_write_unlock(current->mm); if (error) return error; error = __mm_populate(start, len, 0); if (error) return __mlock_posix_error_return(error); return 0; } SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { return do_mlock(start, len, VM_LOCKED); } SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) { vm_flags_t vm_flags = VM_LOCKED; if (flags & ~MLOCK_ONFAULT) return -EINVAL; if (flags & MLOCK_ONFAULT) vm_flags |= VM_LOCKONFAULT; return do_mlock(start, len, vm_flags); } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; start = untagged_addr(start); len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_vma_lock_flags(start, len, 0); mmap_write_unlock(current->mm); return ret; } /* * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) * and translate into the appropriate modifications to mm->def_flags and/or the * flags for all current VMAs. * * There are a couple of subtleties with this. If mlockall() is called multiple * times with different flags, the values do not necessarily stack. If mlockall * is called once including the MCL_FUTURE flag and then a second time without * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. */ static int apply_mlockall_flags(int flags) { VMA_ITERATOR(vmi, current->mm, 0); struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; current->mm->def_flags &= ~VM_LOCKED_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; if (flags & MCL_ONFAULT) current->mm->def_flags |= VM_LOCKONFAULT; if (!(flags & MCL_CURRENT)) goto out; } if (flags & MCL_CURRENT) { to_add |= VM_LOCKED; if (flags & MCL_ONFAULT) to_add |= VM_LOCKONFAULT; } for_each_vma(vmi, vma) { int error; vm_flags_t newflags; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, newflags); /* Ignore errors, but prev needs fixing up. */ if (error) prev = vma; cond_resched(); } out: return 0; } SYSCALL_DEFINE1(mlockall, int, flags) { unsigned long lock_limit; int ret; if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || flags == MCL_ONFAULT) return -EINVAL; if (!can_do_mlock()) return -EPERM; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); mmap_write_unlock(current->mm); if (!ret && (flags & MCL_CURRENT)) mm_populate(0, TASK_SIZE); return ret; } SYSCALL_DEFINE0(munlockall) { int ret; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_mlockall_flags(0); mmap_write_unlock(current->mm); return ret; } /* * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB * shm segments) get accounted against the user_struct instead. */ static DEFINE_SPINLOCK(shmlock_user_lock); int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); if (lock_limit != RLIM_INFINITY) lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; } if (!get_ucounts(ucounts)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); allowed = 0; goto out; } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); put_ucounts(ucounts); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM napi #if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NAPI_H #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #define NO_DEV "(no_device)" TRACE_EVENT(napi_poll, TP_PROTO(struct napi_struct *napi, int work, int budget), TP_ARGS(napi, work, budget), TP_STRUCT__entry( __field( struct napi_struct *, napi) __string( dev_name, napi->dev ? napi->dev->name : NO_DEV) __field( int, work) __field( int, budget) ), TP_fast_assign( __entry->napi = napi; __assign_str(dev_name); __entry->work = work; __entry->budget = budget; ), TP_printk("napi poll on napi struct %p for device %s work %d budget %d", __entry->napi, __get_str(dev_name), __entry->work, __entry->budget) ); TRACE_EVENT(dql_stall_detected, TP_PROTO(unsigned short thrs, unsigned int len, unsigned long last_reap, unsigned long hist_head, unsigned long now, unsigned long *hist), TP_ARGS(thrs, len, last_reap, hist_head, now, hist), TP_STRUCT__entry( __field( unsigned short, thrs) __field( unsigned int, len) __field( unsigned long, last_reap) __field( unsigned long, hist_head) __field( unsigned long, now) __array( unsigned long, hist, 4) ), TP_fast_assign( __entry->thrs = thrs; __entry->len = len; __entry->last_reap = last_reap; __entry->hist_head = hist_head * BITS_PER_LONG; __entry->now = now; memcpy(__entry->hist, hist, sizeof(entry->hist)); ), TP_printk("thrs %u len %u last_reap %lu hist_head %lu now %lu hist %016lx %016lx %016lx %016lx", __entry->thrs, __entry->len, __entry->last_reap, __entry->hist_head, __entry->now, __entry->hist[0], __entry->hist[1], __entry->hist[2], __entry->hist[3]) ); #undef NO_DEV #endif /* _TRACE_NAPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * property.h - Unified device property interface. * * Copyright (C) 2014, Intel Corporation * Authors: Rafael J. Wysocki <rafael.j.wysocki@intel.com> * Mika Westerberg <mika.westerberg@linux.intel.com> */ #ifndef _LINUX_PROPERTY_H_ #define _LINUX_PROPERTY_H_ #include <linux/args.h> #include <linux/array_size.h> #include <linux/bits.h> #include <linux/cleanup.h> #include <linux/fwnode.h> #include <linux/stddef.h> #include <linux/types.h> #include <linux/util_macros.h> struct device; enum dev_prop_type { DEV_PROP_U8, DEV_PROP_U16, DEV_PROP_U32, DEV_PROP_U64, DEV_PROP_STRING, DEV_PROP_REF, }; const struct fwnode_handle *__dev_fwnode_const(const struct device *dev); struct fwnode_handle *__dev_fwnode(struct device *dev); #define dev_fwnode(dev) \ _Generic((dev), \ const struct device *: __dev_fwnode_const, \ struct device *: __dev_fwnode)(dev) bool device_property_present(const struct device *dev, const char *propname); bool device_property_read_bool(const struct device *dev, const char *propname); int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval); int device_property_read_u16_array(const struct device *dev, const char *propname, u16 *val, size_t nval); int device_property_read_u32_array(const struct device *dev, const char *propname, u32 *val, size_t nval); int device_property_read_u64_array(const struct device *dev, const char *propname, u64 *val, size_t nval); int device_property_read_string_array(const struct device *dev, const char *propname, const char **val, size_t nval); int device_property_read_string(const struct device *dev, const char *propname, const char **val); int device_property_match_string(const struct device *dev, const char *propname, const char *string); bool fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname); bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, const char *propname); int fwnode_property_read_u8_array(const struct fwnode_handle *fwnode, const char *propname, u8 *val, size_t nval); int fwnode_property_read_u16_array(const struct fwnode_handle *fwnode, const char *propname, u16 *val, size_t nval); int fwnode_property_read_u32_array(const struct fwnode_handle *fwnode, const char *propname, u32 *val, size_t nval); int fwnode_property_read_u64_array(const struct fwnode_handle *fwnode, const char *propname, u64 *val, size_t nval); int fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval); int fwnode_property_read_string(const struct fwnode_handle *fwnode, const char *propname, const char **val); int fwnode_property_match_string(const struct fwnode_handle *fwnode, const char *propname, const char *string); bool fwnode_device_is_available(const struct fwnode_handle *fwnode); static inline bool fwnode_device_is_big_endian(const struct fwnode_handle *fwnode) { if (fwnode_property_present(fwnode, "big-endian")) return true; if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) && fwnode_property_present(fwnode, "native-endian")) return true; return false; } static inline bool fwnode_device_is_compatible(const struct fwnode_handle *fwnode, const char *compat) { return fwnode_property_match_string(fwnode, "compatible", compat) >= 0; } /** * device_is_big_endian - check if a device has BE registers * @dev: Pointer to the struct device * * Returns: true if the device has a "big-endian" property, or if the kernel * was compiled for BE *and* the device has a "native-endian" property. * Returns false otherwise. * * Callers would nominally use ioread32be/iowrite32be if * device_is_big_endian() == true, or readl/writel otherwise. */ static inline bool device_is_big_endian(const struct device *dev) { return fwnode_device_is_big_endian(dev_fwnode(dev)); } /** * device_is_compatible - match 'compatible' property of the device with a given string * @dev: Pointer to the struct device * @compat: The string to match 'compatible' property with * * Returns: true if matches, otherwise false. */ static inline bool device_is_compatible(const struct device *dev, const char *compat) { return fwnode_device_is_compatible(dev_fwnode(dev), compat); } int fwnode_property_match_property_string(const struct fwnode_handle *fwnode, const char *propname, const char * const *array, size_t n); static inline int device_property_match_property_string(const struct device *dev, const char *propname, const char * const *array, size_t n) { return fwnode_property_match_property_string(dev_fwnode(dev), propname, array, n); } int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, unsigned int nargs, unsigned int index, struct fwnode_reference_args *args); struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *name, unsigned int index); const char *fwnode_get_name(const struct fwnode_handle *fwnode); const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode); bool fwnode_name_eq(const struct fwnode_handle *fwnode, const char *name); struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); #define fwnode_for_each_parent_node(fwnode, parent) \ for (parent = fwnode_get_parent(fwnode); parent; \ parent = fwnode_get_next_parent(parent)) unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); #define fwnode_for_each_child_node(fwnode, child) \ for (child = fwnode_get_next_child_node(fwnode, NULL); child; \ child = fwnode_get_next_child_node(fwnode, child)) #define fwnode_for_each_named_child_node(fwnode, child, name) \ fwnode_for_each_child_node(fwnode, child) \ for_each_if(fwnode_name_eq(child, name)) #define fwnode_for_each_available_child_node(fwnode, child) \ for (child = fwnode_get_next_available_child_node(fwnode, NULL); child;\ child = fwnode_get_next_available_child_node(fwnode, child)) #define fwnode_for_each_child_node_scoped(fwnode, child) \ for (struct fwnode_handle *child __free(fwnode_handle) = \ fwnode_get_next_child_node(fwnode, NULL); \ child; child = fwnode_get_next_child_node(fwnode, child)) #define fwnode_for_each_available_child_node_scoped(fwnode, child) \ for (struct fwnode_handle *child __free(fwnode_handle) = \ fwnode_get_next_available_child_node(fwnode, NULL); \ child; child = fwnode_get_next_available_child_node(fwnode, child)) struct fwnode_handle *device_get_next_child_node(const struct device *dev, struct fwnode_handle *child); #define device_for_each_child_node(dev, child) \ for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) #define device_for_each_named_child_node(dev, child, name) \ device_for_each_child_node(dev, child) \ for_each_if(fwnode_name_eq(child, name)) #define device_for_each_child_node_scoped(dev, child) \ for (struct fwnode_handle *child __free(fwnode_handle) = \ device_get_next_child_node(dev, NULL); \ child; child = device_get_next_child_node(dev, child)) #define device_for_each_named_child_node_scoped(dev, child, name) \ device_for_each_child_node_scoped(dev, child) \ for_each_if(fwnode_name_eq(child, name)) struct fwnode_handle *fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname); struct fwnode_handle *device_get_named_child_node(const struct device *dev, const char *childname); struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); /** * fwnode_handle_put - Drop reference to a device node * @fwnode: Pointer to the device node to drop the reference to. * * This has to be used when terminating device_for_each_child_node() iteration * with break or return to prevent stale device node references from being left * behind. */ static inline void fwnode_handle_put(struct fwnode_handle *fwnode) { fwnode_call_void_op(fwnode, put); } DEFINE_FREE(fwnode_handle, struct fwnode_handle *, fwnode_handle_put(_T)) int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int fwnode_get_child_node_count(const struct fwnode_handle *fwnode); static inline unsigned int device_get_child_node_count(const struct device *dev) { return fwnode_get_child_node_count(dev_fwnode(dev)); } unsigned int fwnode_get_named_child_node_count(const struct fwnode_handle *fwnode, const char *name); static inline unsigned int device_get_named_child_node_count(const struct device *dev, const char *name) { return fwnode_get_named_child_node_count(dev_fwnode(dev), name); } static inline int device_property_read_u8(const struct device *dev, const char *propname, u8 *val) { return device_property_read_u8_array(dev, propname, val, 1); } static inline int device_property_read_u16(const struct device *dev, const char *propname, u16 *val) { return device_property_read_u16_array(dev, propname, val, 1); } static inline int device_property_read_u32(const struct device *dev, const char *propname, u32 *val) { return device_property_read_u32_array(dev, propname, val, 1); } static inline int device_property_read_u64(const struct device *dev, const char *propname, u64 *val) { return device_property_read_u64_array(dev, propname, val, 1); } static inline int device_property_count_u8(const struct device *dev, const char *propname) { return device_property_read_u8_array(dev, propname, NULL, 0); } static inline int device_property_count_u16(const struct device *dev, const char *propname) { return device_property_read_u16_array(dev, propname, NULL, 0); } static inline int device_property_count_u32(const struct device *dev, const char *propname) { return device_property_read_u32_array(dev, propname, NULL, 0); } static inline int device_property_count_u64(const struct device *dev, const char *propname) { return device_property_read_u64_array(dev, propname, NULL, 0); } static inline int device_property_string_array_count(const struct device *dev, const char *propname) { return device_property_read_string_array(dev, propname, NULL, 0); } static inline int fwnode_property_read_u8(const struct fwnode_handle *fwnode, const char *propname, u8 *val) { return fwnode_property_read_u8_array(fwnode, propname, val, 1); } static inline int fwnode_property_read_u16(const struct fwnode_handle *fwnode, const char *propname, u16 *val) { return fwnode_property_read_u16_array(fwnode, propname, val, 1); } static inline int fwnode_property_read_u32(const struct fwnode_handle *fwnode, const char *propname, u32 *val) { return fwnode_property_read_u32_array(fwnode, propname, val, 1); } static inline int fwnode_property_read_u64(const struct fwnode_handle *fwnode, const char *propname, u64 *val) { return fwnode_property_read_u64_array(fwnode, propname, val, 1); } static inline int fwnode_property_count_u8(const struct fwnode_handle *fwnode, const char *propname) { return fwnode_property_read_u8_array(fwnode, propname, NULL, 0); } static inline int fwnode_property_count_u16(const struct fwnode_handle *fwnode, const char *propname) { return fwnode_property_read_u16_array(fwnode, propname, NULL, 0); } static inline int fwnode_property_count_u32(const struct fwnode_handle *fwnode, const char *propname) { return fwnode_property_read_u32_array(fwnode, propname, NULL, 0); } static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode, const char *propname) { return fwnode_property_read_u64_array(fwnode, propname, NULL, 0); } static inline int fwnode_property_string_array_count(const struct fwnode_handle *fwnode, const char *propname) { return fwnode_property_read_string_array(fwnode, propname, NULL, 0); } struct software_node; /** * struct software_node_ref_args - Reference property with additional arguments * @swnode: Reference to a software node * @fwnode: Alternative reference to a firmware node handle * @nargs: Number of elements in @args array * @args: Integer arguments */ struct software_node_ref_args { const struct software_node *swnode; struct fwnode_handle *fwnode; unsigned int nargs; u64 args[NR_FWNODE_REFERENCE_ARGS]; }; #define SOFTWARE_NODE_REFERENCE(_ref_, ...) \ (const struct software_node_ref_args) { \ .swnode = _Generic(_ref_, \ const struct software_node *: _ref_, \ struct software_node *: _ref_, \ default: NULL), \ .fwnode = _Generic(_ref_, \ struct fwnode_handle *: _ref_, \ default: NULL), \ .nargs = COUNT_ARGS(__VA_ARGS__), \ .args = { __VA_ARGS__ }, \ } /** * struct property_entry - "Built-in" device property representation. * @name: Name of the property. * @length: Length of data making up the value. * @is_inline: True when the property value is stored inline. * @type: Type of the data in unions. * @pointer: Pointer to the property when it is not stored inline. * @value: Value of the property when it is stored inline. */ struct property_entry { const char *name; size_t length; bool is_inline; enum dev_prop_type type; union { const void *pointer; union { u8 u8_data[sizeof(u64) / sizeof(u8)]; u16 u16_data[sizeof(u64) / sizeof(u16)]; u32 u32_data[sizeof(u64) / sizeof(u32)]; u64 u64_data[sizeof(u64) / sizeof(u64)]; const char *str[sizeof(u64) / sizeof(char *)]; } value; }; }; /* * Note: the below initializers for the anonymous union are carefully * crafted to avoid gcc-4.4.4's problems with initialization of anon unions * and structs. */ #define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_) \ (struct property_entry) { \ .name = _name_, \ .length = (_len_) * sizeof_field(struct property_entry, value._elem_[0]), \ .type = DEV_PROP_##_Type_, \ { .pointer = _val_ }, \ } #define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, u8_data, U8, _val_, _len_) #define PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, u16_data, U16, _val_, _len_) #define PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, u32_data, U32, _val_, _len_) #define PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, u64_data, U64, _val_, _len_) #define PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, str, STRING, _val_, _len_) #define PROPERTY_ENTRY_REF_ARRAY_LEN(_name_, _val_, _len_) \ (struct property_entry) { \ .name = _name_, \ .length = (_len_) * sizeof(struct software_node_ref_args), \ .type = DEV_PROP_REF, \ { .pointer = _val_ }, \ } #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define PROPERTY_ENTRY_REF_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_REF_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define __PROPERTY_ENTRY_ELEMENT(_name_, _elem_, _Type_, _val_) \ (struct property_entry) { \ .name = _name_, \ .length = sizeof_field(struct property_entry, value._elem_[0]), \ .is_inline = true, \ .type = DEV_PROP_##_Type_, \ { .value = { ._elem_[0] = _val_ } }, \ } #define PROPERTY_ENTRY_U8(_name_, _val_) \ __PROPERTY_ENTRY_ELEMENT(_name_, u8_data, U8, _val_) #define PROPERTY_ENTRY_U16(_name_, _val_) \ __PROPERTY_ENTRY_ELEMENT(_name_, u16_data, U16, _val_) #define PROPERTY_ENTRY_U32(_name_, _val_) \ __PROPERTY_ENTRY_ELEMENT(_name_, u32_data, U32, _val_) #define PROPERTY_ENTRY_U64(_name_, _val_) \ __PROPERTY_ENTRY_ELEMENT(_name_, u64_data, U64, _val_) #define PROPERTY_ENTRY_STRING(_name_, _val_) \ __PROPERTY_ENTRY_ELEMENT(_name_, str, STRING, _val_) #define __PROPERTY_ENTRY_REF_ARGS(_ref_, ...) \ _Generic(_ref_, \ const struct software_node_ref_args *: _ref_, \ struct software_node_ref_args *: _ref_, \ default: &SOFTWARE_NODE_REFERENCE(_ref_, ##__VA_ARGS__)) #define PROPERTY_ENTRY_REF(_name_, _ref_, ...) \ (struct property_entry) { \ .name = _name_, \ .length = sizeof(struct software_node_ref_args), \ .type = DEV_PROP_REF, \ { .pointer = __PROPERTY_ENTRY_REF_ARGS(_ref_, ##__VA_ARGS__) }, \ } #define PROPERTY_ENTRY_BOOL(_name_) \ (struct property_entry) { \ .name = _name_, \ .is_inline = true, \ } struct property_entry * property_entries_dup(const struct property_entry *properties); void property_entries_free(const struct property_entry *properties); bool device_dma_supported(const struct device *dev); enum dev_dma_attr device_get_dma_attr(const struct device *dev); const void *device_get_match_data(const struct device *dev); int device_get_phy_mode(struct device *dev); int fwnode_get_phy_mode(const struct fwnode_handle *fwnode); void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); struct fwnode_handle *fwnode_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev); struct fwnode_handle * fwnode_graph_get_port_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port_parent( const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port( const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_endpoint( const struct fwnode_handle *fwnode); static inline bool fwnode_graph_is_endpoint(const struct fwnode_handle *fwnode) { return fwnode_property_present(fwnode, "remote-endpoint"); } /* * Fwnode lookup flags * * @FWNODE_GRAPH_ENDPOINT_NEXT: In the case of no exact match, look for the * closest endpoint ID greater than the specified * one. * @FWNODE_GRAPH_DEVICE_DISABLED: That the device to which the remote * endpoint of the given endpoint belongs to, * may be disabled, or that the endpoint is not * connected. */ #define FWNODE_GRAPH_ENDPOINT_NEXT BIT(0) #define FWNODE_GRAPH_DEVICE_DISABLED BIT(1) struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags); unsigned int fwnode_graph_get_endpoint_count(const struct fwnode_handle *fwnode, unsigned long flags); #define fwnode_graph_for_each_endpoint(fwnode, child) \ for (child = fwnode_graph_get_next_endpoint(fwnode, NULL); child; \ child = fwnode_graph_get_next_endpoint(fwnode, child)) int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); typedef void *(*devcon_match_fn_t)(const struct fwnode_handle *fwnode, const char *id, void *data); void *fwnode_connection_find_match(const struct fwnode_handle *fwnode, const char *con_id, void *data, devcon_match_fn_t match); static inline void *device_connection_find_match(const struct device *dev, const char *con_id, void *data, devcon_match_fn_t match) { return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match); } int fwnode_connection_find_matches(const struct fwnode_handle *fwnode, const char *con_id, void *data, devcon_match_fn_t match, void **matches, unsigned int matches_len); /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ /** * struct software_node - Software node description * @name: Name of the software node * @parent: Parent of the software node * @properties: Array of device properties */ struct software_node { const char *name; const struct software_node *parent; const struct property_entry *properties; }; #define SOFTWARE_NODE(_name_, _properties_, _parent_) \ (struct software_node) { \ .name = _name_, \ .properties = _properties_, \ .parent = _parent_, \ } bool is_software_node(const struct fwnode_handle *fwnode); const struct software_node * to_software_node(const struct fwnode_handle *fwnode); struct fwnode_handle *software_node_fwnode(const struct software_node *node); const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name); int software_node_register_node_group(const struct software_node * const *node_group); void software_node_unregister_node_group(const struct software_node * const *node_group); int software_node_register(const struct software_node *node); void software_node_unregister(const struct software_node *node); struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent); void fwnode_remove_software_node(struct fwnode_handle *fwnode); int device_add_software_node(struct device *dev, const struct software_node *node); void device_remove_software_node(struct device *dev); int device_create_managed_software_node(struct device *dev, const struct property_entry *properties, const struct software_node *parent); #endif /* _LINUX_PROPERTY_H_ */ |
| 94 93 1 1 3 1 4 1 4 2 3 2 1 4 4 60 1 59 1 6 6 92 95 43 39 11 6 6 91 94 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Helpers for initial module or kernel cmdline parsing * Copyright (C) 2001 Rusty Russell. */ #include <linux/ctype.h> #include <linux/device.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/kstrtox.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/overflow.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/string.h> #ifdef CONFIG_SYSFS /* Protects all built-in parameters, modules use their own param_lock */ static DEFINE_MUTEX(param_lock); /* Use the module's mutex, or if built-in use the built-in mutex */ #ifdef CONFIG_MODULES #define KPARAM_MUTEX(mod) ((mod) ? &(mod)->param_lock : ¶m_lock) #else #define KPARAM_MUTEX(mod) (¶m_lock) #endif static inline void check_kparam_locked(struct module *mod) { BUG_ON(!mutex_is_locked(KPARAM_MUTEX(mod))); } #else static inline void check_kparam_locked(struct module *mod) { } #endif /* !CONFIG_SYSFS */ /* This just allows us to keep track of which parameters are kmalloced. */ struct kmalloced_param { struct list_head list; char val[]; }; static LIST_HEAD(kmalloced_params); static DEFINE_SPINLOCK(kmalloced_params_lock); static void *kmalloc_parameter(unsigned int size) { struct kmalloced_param *p; p = kmalloc(size_add(sizeof(*p), size), GFP_KERNEL); if (!p) return NULL; spin_lock(&kmalloced_params_lock); list_add(&p->list, &kmalloced_params); spin_unlock(&kmalloced_params_lock); return p->val; } /* Does nothing if parameter wasn't kmalloced above. */ static void maybe_kfree_parameter(void *param) { struct kmalloced_param *p; spin_lock(&kmalloced_params_lock); list_for_each_entry(p, &kmalloced_params, list) { if (p->val == param) { list_del(&p->list); kfree(p); break; } } spin_unlock(&kmalloced_params_lock); } static char dash2underscore(char c) { if (c == '-') return '_'; return c; } bool parameqn(const char *a, const char *b, size_t n) { size_t i; for (i = 0; i < n; i++) { if (dash2underscore(a[i]) != dash2underscore(b[i])) return false; } return true; } bool parameq(const char *a, const char *b) { return parameqn(a, b, strlen(a)+1); } static bool param_check_unsafe(const struct kernel_param *kp) { if (kp->flags & KERNEL_PARAM_FL_HWPARAM && security_locked_down(LOCKDOWN_MODULE_PARAMETERS)) return false; if (kp->flags & KERNEL_PARAM_FL_UNSAFE) { pr_notice("Setting dangerous option %s - tainting kernel\n", kp->name); add_taint(TAINT_USER, LOCKDEP_STILL_OK); } return true; } static int parse_one(char *param, char *val, const char *doing, const struct kernel_param *params, unsigned num_params, s16 min_level, s16 max_level, void *arg, parse_unknown_fn handle_unknown) { unsigned int i; int err; /* Find parameter */ for (i = 0; i < num_params; i++) { if (parameq(param, params[i].name)) { if (params[i].level < min_level || params[i].level > max_level) return 0; /* No one handled NULL, so do it here. */ if (!val && !(params[i].ops->flags & KERNEL_PARAM_OPS_FL_NOARG)) return -EINVAL; pr_debug("handling %s with %p\n", param, params[i].ops->set); kernel_param_lock(params[i].mod); if (param_check_unsafe(¶ms[i])) err = params[i].ops->set(val, ¶ms[i]); else err = -EPERM; kernel_param_unlock(params[i].mod); return err; } } if (handle_unknown) { pr_debug("doing %s: %s='%s'\n", doing, param, val); return handle_unknown(param, val, doing, arg); } pr_debug("Unknown argument '%s'\n", param); return -ENOENT; } /* Args looks like "foo=bar,bar2 baz=fuz wiz". */ char *parse_args(const char *doing, char *args, const struct kernel_param *params, unsigned int num, s16 min_level, s16 max_level, void *arg, parse_unknown_fn unknown) { char *param, *val, *err = NULL; /* Chew leading spaces */ args = skip_spaces(args); if (*args) pr_debug("doing %s, parsing ARGS: '%s'\n", doing, args); while (*args) { int ret; int irq_was_disabled; args = next_arg(args, ¶m, &val); /* Stop at -- */ if (!val && strcmp(param, "--") == 0) return err ?: args; irq_was_disabled = irqs_disabled(); ret = parse_one(param, val, doing, params, num, min_level, max_level, arg, unknown); if (irq_was_disabled && !irqs_disabled()) pr_warn("%s: option '%s' enabled irq's!\n", doing, param); switch (ret) { case 0: continue; case -ENOENT: pr_err("%s: Unknown parameter `%s'\n", doing, param); break; case -ENOSPC: pr_err("%s: `%s' too large for parameter `%s'\n", doing, val ?: "", param); break; default: pr_err("%s: `%s' invalid for parameter `%s'\n", doing, val ?: "", param); break; } err = ERR_PTR(ret); } return err; } /* Lazy bastard, eh? */ #define STANDARD_PARAM_DEF(name, type, format, strtolfn) \ int param_set_##name(const char *val, const struct kernel_param *kp) \ { \ return strtolfn(val, 0, (type *)kp->arg); \ } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ .set = param_set_##name, \ .get = param_get_##name, \ }; \ EXPORT_SYMBOL(param_set_##name); \ EXPORT_SYMBOL(param_get_##name); \ EXPORT_SYMBOL(param_ops_##name) STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); STANDARD_PARAM_DEF(long, long, "%li", kstrtol); STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); STANDARD_PARAM_DEF(hexint, unsigned int, "%#08x", kstrtouint); int param_set_uint_minmax(const char *val, const struct kernel_param *kp, unsigned int min, unsigned int max) { unsigned int num; int ret; if (!val) return -EINVAL; ret = kstrtouint(val, 0, &num); if (ret) return ret; if (num < min || num > max) return -EINVAL; *((unsigned int *)kp->arg) = num; return 0; } EXPORT_SYMBOL_GPL(param_set_uint_minmax); int param_set_charp(const char *val, const struct kernel_param *kp) { size_t len, maxlen = 1024; len = strnlen(val, maxlen + 1); if (len == maxlen + 1) { pr_err("%s: string parameter too long\n", kp->name); return -ENOSPC; } maybe_kfree_parameter(*(char **)kp->arg); /* * This is a hack. We can't kmalloc() in early boot, and we * don't need to; this mangled commandline is preserved. */ if (slab_is_available()) { *(char **)kp->arg = kmalloc_parameter(len + 1); if (!*(char **)kp->arg) return -ENOMEM; strcpy(*(char **)kp->arg, val); } else *(const char **)kp->arg = val; return 0; } EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); void param_free_charp(void *arg) { maybe_kfree_parameter(*((char **)arg)); } EXPORT_SYMBOL(param_free_charp); const struct kernel_param_ops param_ops_charp = { .set = param_set_charp, .get = param_get_charp, .free = param_free_charp, }; EXPORT_SYMBOL(param_ops_charp); /* Actually could be a bool or an int, for historical reasons. */ int param_set_bool(const char *val, const struct kernel_param *kp) { /* No equals means "set"... */ if (!val) val = "1"; /* One of =[yYnN01] */ return kstrtobool(val, kp->arg); } EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); const struct kernel_param_ops param_ops_bool = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bool, .get = param_get_bool, }; EXPORT_SYMBOL(param_ops_bool); int param_set_bool_enable_only(const char *val, const struct kernel_param *kp) { int err; bool new_value; bool orig_value = *(bool *)kp->arg; struct kernel_param dummy_kp = *kp; dummy_kp.arg = &new_value; err = param_set_bool(val, &dummy_kp); if (err) return err; /* Don't let them unset it once it's set! */ if (!new_value && orig_value) return -EROFS; if (new_value) err = param_set_bool(val, kp); return err; } EXPORT_SYMBOL_GPL(param_set_bool_enable_only); const struct kernel_param_ops param_ops_bool_enable_only = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bool_enable_only, .get = param_get_bool, }; EXPORT_SYMBOL_GPL(param_ops_bool_enable_only); /* This one must be bool. */ int param_set_invbool(const char *val, const struct kernel_param *kp) { int ret; bool boolval; struct kernel_param dummy; dummy.arg = &boolval; ret = param_set_bool(val, &dummy); if (ret == 0) *(bool *)kp->arg = !boolval; return ret; } EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); const struct kernel_param_ops param_ops_invbool = { .set = param_set_invbool, .get = param_get_invbool, }; EXPORT_SYMBOL(param_ops_invbool); int param_set_bint(const char *val, const struct kernel_param *kp) { /* Match bool exactly, by re-using it. */ struct kernel_param boolkp = *kp; bool v; int ret; boolkp.arg = &v; ret = param_set_bool(val, &boolkp); if (ret == 0) *(int *)kp->arg = v; return ret; } EXPORT_SYMBOL(param_set_bint); const struct kernel_param_ops param_ops_bint = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bint, .get = param_get_int, }; EXPORT_SYMBOL(param_ops_bint); /* We break the rule and mangle the string. */ static int param_array(struct module *mod, const char *name, const char *val, unsigned int min, unsigned int max, void *elem, int elemsize, int (*set)(const char *, const struct kernel_param *kp), s16 level, unsigned int *num) { int ret; struct kernel_param kp; char save; /* Get the name right for errors. */ kp.name = name; kp.arg = elem; kp.level = level; *num = 0; /* We expect a comma-separated list of values. */ do { int len; if (*num == max) { pr_err("%s: can only take %i arguments\n", name, max); return -EINVAL; } len = strcspn(val, ","); /* nul-terminate and parse */ save = val[len]; ((char *)val)[len] = '\0'; check_kparam_locked(mod); ret = set(val, &kp); if (ret != 0) return ret; kp.arg += elemsize; val += len+1; (*num)++; } while (save == ','); if (*num < min) { pr_err("%s: needs at least %i arguments\n", name, min); return -EINVAL; } return 0; } static int param_array_set(const char *val, const struct kernel_param *kp) { const struct kparam_array *arr = kp->arr; unsigned int temp_num; return param_array(kp->mod, kp->name, val, 1, arr->max, arr->elem, arr->elemsize, arr->ops->set, kp->level, arr->num ?: &temp_num); } static int param_array_get(char *buffer, const struct kernel_param *kp) { int i, off, ret; const struct kparam_array *arr = kp->arr; struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { /* Replace \n with comma */ if (i) buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); if (ret < 0) return ret; off += ret; } buffer[off] = '\0'; return off; } static void param_array_free(void *arg) { unsigned int i; const struct kparam_array *arr = arg; if (arr->ops->free) for (i = 0; i < (arr->num ? *arr->num : arr->max); i++) arr->ops->free(arr->elem + arr->elemsize * i); } const struct kernel_param_ops param_array_ops = { .set = param_array_set, .get = param_array_get, .free = param_array_free, }; EXPORT_SYMBOL(param_array_ops); int param_set_copystring(const char *val, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; const size_t len = strnlen(val, kps->maxlen); if (len == kps->maxlen) { pr_err("%s: string doesn't fit in %u chars.\n", kp->name, kps->maxlen-1); return -ENOSPC; } memcpy(kps->string, val, len + 1); return 0; } EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); const struct kernel_param_ops param_ops_string = { .set = param_set_copystring, .get = param_get_string, }; EXPORT_SYMBOL(param_ops_string); /* sysfs output in /sys/modules/XYZ/parameters/ */ #define to_module_attr(n) container_of_const(n, struct module_attribute, attr) #define to_module_kobject(n) container_of(n, struct module_kobject, kobj) struct param_attribute { struct module_attribute mattr; const struct kernel_param *param; }; struct module_param_attrs { unsigned int num; struct attribute_group grp; struct param_attribute attrs[] __counted_by(num); }; #ifdef CONFIG_SYSFS #define to_param_attr(n) container_of_const(n, struct param_attribute, mattr) static ssize_t param_attr_show(const struct module_attribute *mattr, struct module_kobject *mk, char *buf) { int count; const struct param_attribute *attribute = to_param_attr(mattr); if (!attribute->param->ops->get) return -EPERM; kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); return count; } /* sysfs always hands a nul-terminated string in buf. We rely on that. */ static ssize_t param_attr_store(const struct module_attribute *mattr, struct module_kobject *mk, const char *buf, size_t len) { int err; const struct param_attribute *attribute = to_param_attr(mattr); if (!attribute->param->ops->set) return -EPERM; kernel_param_lock(mk->mod); if (param_check_unsafe(attribute->param)) err = attribute->param->ops->set(buf, attribute->param); else err = -EPERM; kernel_param_unlock(mk->mod); if (!err) return len; return err; } #endif #ifdef CONFIG_SYSFS void kernel_param_lock(struct module *mod) { mutex_lock(KPARAM_MUTEX(mod)); } void kernel_param_unlock(struct module *mod) { mutex_unlock(KPARAM_MUTEX(mod)); } EXPORT_SYMBOL(kernel_param_lock); EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and * create file in sysfs. Returns an error on out of memory. Always cleans up * if there's an error. */ static __init_or_module int add_sysfs_param(struct module_kobject *mk, const struct kernel_param *kp, const char *name) { struct module_param_attrs *new_mp; struct attribute **new_attrs; unsigned int i; /* We don't bother calling this with invisible parameters. */ BUG_ON(!kp->perm); if (!mk->mp) { /* First allocation. */ mk->mp = kzalloc_obj(*mk->mp); if (!mk->mp) return -ENOMEM; mk->mp->grp.name = "parameters"; /* NULL-terminated attribute array. */ mk->mp->grp.attrs = kzalloc_obj(mk->mp->grp.attrs[0]); /* Caller will cleanup via free_module_param_attrs */ if (!mk->mp->grp.attrs) return -ENOMEM; } /* Enlarge allocations. */ new_mp = krealloc(mk->mp, struct_size(mk->mp, attrs, mk->mp->num + 1), GFP_KERNEL); if (!new_mp) return -ENOMEM; mk->mp = new_mp; mk->mp->num++; /* Extra pointer for NULL terminator */ new_attrs = krealloc_array(mk->mp->grp.attrs, mk->mp->num + 1, sizeof(mk->mp->grp.attrs[0]), GFP_KERNEL); if (!new_attrs) return -ENOMEM; mk->mp->grp.attrs = new_attrs; /* Tack new one on the end. */ memset(&mk->mp->attrs[mk->mp->num - 1], 0, sizeof(mk->mp->attrs[0])); sysfs_attr_init(&mk->mp->attrs[mk->mp->num - 1].mattr.attr); mk->mp->attrs[mk->mp->num - 1].param = kp; mk->mp->attrs[mk->mp->num - 1].mattr.show = param_attr_show; /* Do not allow runtime DAC changes to make param writable. */ if ((kp->perm & (S_IWUSR | S_IWGRP | S_IWOTH)) != 0) mk->mp->attrs[mk->mp->num - 1].mattr.store = param_attr_store; else mk->mp->attrs[mk->mp->num - 1].mattr.store = NULL; mk->mp->attrs[mk->mp->num - 1].mattr.attr.name = (char *)name; mk->mp->attrs[mk->mp->num - 1].mattr.attr.mode = kp->perm; /* Fix up all the pointers, since krealloc can move us */ for (i = 0; i < mk->mp->num; i++) mk->mp->grp.attrs[i] = &mk->mp->attrs[i].mattr.attr; mk->mp->grp.attrs[mk->mp->num] = NULL; return 0; } #ifdef CONFIG_MODULES static void free_module_param_attrs(struct module_kobject *mk) { if (mk->mp) kfree(mk->mp->grp.attrs); kfree(mk->mp); mk->mp = NULL; } /* * module_param_sysfs_setup - setup sysfs support for one module * @mod: module * @kparam: module parameters (array) * @num_params: number of module parameters * * Adds sysfs entries for module parameters under * /sys/module/[mod->name]/parameters/ */ int module_param_sysfs_setup(struct module *mod, const struct kernel_param *kparam, unsigned int num_params) { int i, err; bool params = false; for (i = 0; i < num_params; i++) { if (kparam[i].perm == 0) continue; err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name); if (err) { free_module_param_attrs(&mod->mkobj); return err; } params = true; } if (!params) return 0; /* Create the param group. */ err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); if (err) free_module_param_attrs(&mod->mkobj); return err; } /* * module_param_sysfs_remove - remove sysfs support for one module * @mod: module * * Remove sysfs entries for module parameters and the corresponding * kobject. */ void module_param_sysfs_remove(struct module *mod) { if (mod->mkobj.mp) { sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); /* * We are positive that no one is using any param * attrs at this point. Deallocate immediately. */ free_module_param_attrs(&mod->mkobj); } } #endif struct module_kobject * __init_or_module lookup_or_create_module_kobject(const char *name) { struct module_kobject *mk; struct kobject *kobj; int err; kobj = kset_find_obj(module_kset, name); if (kobj) return to_module_kobject(kobj); mk = kzalloc_obj(struct module_kobject); if (!mk) return NULL; mk->mod = THIS_MODULE; mk->kobj.kset = module_kset; err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name); if (IS_ENABLED(CONFIG_MODULES) && !err) err = sysfs_create_file(&mk->kobj, &module_uevent.attr); if (err) { kobject_put(&mk->kobj); pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n", name, err); return NULL; } /* So that we hold reference in both cases. */ kobject_get(&mk->kobj); return mk; } static void __init kernel_add_sysfs_param(const char *name, const struct kernel_param *kparam, unsigned int name_skip) { struct module_kobject *mk; int err; mk = lookup_or_create_module_kobject(name); if (!mk) return; /* We need to remove old parameters before adding more. */ if (mk->mp) sysfs_remove_group(&mk->kobj, &mk->mp->grp); /* These should not fail at boot. */ err = add_sysfs_param(mk, kparam, kparam->name + name_skip); BUG_ON(err); err = sysfs_create_group(&mk->kobj, &mk->mp->grp); BUG_ON(err); kobject_uevent(&mk->kobj, KOBJ_ADD); kobject_put(&mk->kobj); } /* * param_sysfs_builtin - add sysfs parameters for built-in modules * * Add module_parameters to sysfs for "modules" built into the kernel. * * The "module" name (KBUILD_MODNAME) is stored before a dot, the * "parameter" name is stored behind a dot in kernel_param->name. So, * extract the "module" name for all built-in kernel_param-eters, * and for all who have the same, call kernel_add_sysfs_param. */ static void __init param_sysfs_builtin(void) { const struct kernel_param *kp; unsigned int name_len; char modname[MODULE_NAME_LEN]; for (kp = __start___param; kp < __stop___param; kp++) { char *dot; if (kp->perm == 0) continue; dot = strchr(kp->name, '.'); if (!dot) { /* This happens for core_param() */ strscpy(modname, "kernel"); name_len = 0; } else { name_len = dot - kp->name + 1; strscpy(modname, kp->name, name_len); } kernel_add_sysfs_param(modname, kp, name_len); } } ssize_t __modver_version_show(const struct module_attribute *mattr, struct module_kobject *mk, char *buf) { const struct module_version_attribute *vattr = container_of_const(mattr, struct module_version_attribute, mattr); return scnprintf(buf, PAGE_SIZE, "%s\n", vattr->version); } extern const struct module_version_attribute __start___modver[]; extern const struct module_version_attribute __stop___modver[]; static void __init version_sysfs_builtin(void) { const struct module_version_attribute *vattr; struct module_kobject *mk; int err; for (vattr = __start___modver; vattr < __stop___modver; vattr++) { mk = lookup_or_create_module_kobject(vattr->module_name); if (mk) { err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr); WARN_ON_ONCE(err); kobject_uevent(&mk->kobj, KOBJ_ADD); kobject_put(&mk->kobj); } } } /* module-related sysfs stuff */ static ssize_t module_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct module_attribute *attribute; struct module_kobject *mk; int ret; attribute = to_module_attr(attr); mk = to_module_kobject(kobj); if (!attribute->show) return -EIO; ret = attribute->show(attribute, mk, buf); return ret; } static ssize_t module_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t len) { const struct module_attribute *attribute; struct module_kobject *mk; int ret; attribute = to_module_attr(attr); mk = to_module_kobject(kobj); if (!attribute->store) return -EIO; ret = attribute->store(attribute, mk, buf, len); return ret; } static const struct sysfs_ops module_sysfs_ops = { .show = module_attr_show, .store = module_attr_store, }; static int uevent_filter(const struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); if (ktype == &module_ktype) return 1; return 0; } static const struct kset_uevent_ops module_uevent_ops = { .filter = uevent_filter, }; struct kset *module_kset; static void module_kobj_release(struct kobject *kobj) { struct module_kobject *mk = to_module_kobject(kobj); if (mk->kobj_completion) complete(mk->kobj_completion); } const struct kobj_type module_ktype = { .release = module_kobj_release, .sysfs_ops = &module_sysfs_ops, }; /* * param_sysfs_init - create "module" kset * * This must be done before any driver registration so that when a driver comes * from a built-in module, the driver core can add the module under /sys/module * and create the associated driver symlinks. */ static int __init param_sysfs_init(void) { module_kset = kset_create_and_add("module", &module_uevent_ops, NULL); if (!module_kset) { printk(KERN_WARNING "%s (%d): error creating kset\n", __FILE__, __LINE__); return -ENOMEM; } return 0; } pure_initcall(param_sysfs_init); /* * param_sysfs_builtin_init - add sysfs version and parameter * attributes for built-in modules */ static int __init param_sysfs_builtin_init(void) { if (!module_kset) return -ENOMEM; version_sysfs_builtin(); param_sysfs_builtin(); return 0; } late_initcall(param_sysfs_builtin_init); #endif /* CONFIG_SYSFS */ #ifdef CONFIG_MODULES /* * module_destroy_params - free all parameters for one module * @params: module parameters (array) * @num: number of module parameters */ void module_destroy_params(const struct kernel_param *params, unsigned int num) { unsigned int i; for (i = 0; i < num; i++) if (params[i].ops->free) params[i].ops->free(params[i].arg); } #endif /* CONFIG_MODULES */ |
| 1 1 1 2019 2001 1125 1809 1811 2017 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 2521 2518 1514 18 593 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Monitoring code for network dropped packet alerts * * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> #include <linux/bitfield.h> #include <linux/percpu.h> #include <linux/timer.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/module.h> #include <net/genetlink.h> #include <net/netevent.h> #include <net/flow_offload.h> #include <net/dropreason.h> #include <net/devlink.h> #include <trace/events/skb.h> #include <trace/events/napi.h> #include <trace/events/devlink.h> #include <linux/unaligned.h> #define TRACE_ON 1 #define TRACE_OFF 0 /* * Globals, our netlink socket pointer * and the work handle that will send up * netlink alerts */ static int trace_state = TRACE_OFF; static bool monitor_hw; /* net_dm_mutex * * An overall lock guarding every operation coming from userspace. */ static DEFINE_MUTEX(net_dm_mutex); struct net_dm_stats { u64_stats_t dropped; struct u64_stats_sync syncp; }; #define NET_DM_MAX_HW_TRAP_NAME_LEN 40 struct net_dm_hw_entry { char trap_name[NET_DM_MAX_HW_TRAP_NAME_LEN]; u32 count; }; struct net_dm_hw_entries { u32 num_entries; struct net_dm_hw_entry entries[]; }; struct per_cpu_dm_data { raw_spinlock_t lock; /* Protects 'skb', 'hw_entries' and * 'send_timer' */ union { struct sk_buff *skb; struct net_dm_hw_entries *hw_entries; }; struct sk_buff_head drop_queue; struct work_struct dm_alert_work; struct timer_list send_timer; struct net_dm_stats stats; }; struct dm_hw_stat_delta { unsigned long last_rx; unsigned long last_drop_val; struct rcu_head rcu; }; static struct genl_family net_drop_monitor_family; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_hw_cpu_data); static int dm_hit_limit = 64; static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY; static u32 net_dm_trunc_len; static u32 net_dm_queue_len = 1000; struct net_dm_alert_ops { void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, const struct sock *rx_sk); void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, int work, int budget); void (*work_item_func)(struct work_struct *work); void (*hw_work_item_func)(struct work_struct *work); void (*hw_trap_probe)(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata); }; struct net_dm_skb_cb { union { struct devlink_trap_metadata *hw_metadata; void *pc; }; enum skb_drop_reason reason; }; #define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; struct sk_buff *skb; unsigned long flags; void *msg_header; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); skb = genlmsg_new(al, GFP_KERNEL); if (!skb) goto err; msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!msg_header) { nlmsg_free(skb); skb = NULL; goto err; } nla = nla_reserve(skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); if (!nla) { nlmsg_free(skb); skb = NULL; goto err; } msg = nla_data(nla); memset(msg, 0, al); goto out; err: mod_timer(&data->send_timer, jiffies + HZ / 10); out: raw_spin_lock_irqsave(&data->lock, flags); swap(data->skb, skb); raw_spin_unlock_irqrestore(&data->lock, flags); if (skb) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh); genlmsg_end(skb, genlmsg_data(gnlh)); } return skb; } static const struct genl_multicast_group dropmon_mcgrps[] = { { .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, }, }; static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; struct per_cpu_dm_data *data; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); skb = reset_per_cpu_data(data); if (skb) genlmsg_multicast(&net_drop_monitor_family, skb, 0, 0, GFP_KERNEL); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the * hysteresis period. */ static void sched_send_work(struct timer_list *t) { struct per_cpu_dm_data *data = timer_container_of(data, t, send_timer); schedule_work(&data->dm_alert_work); } static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; struct sk_buff *dskb; struct per_cpu_dm_data *data; unsigned long flags; local_irq_save(flags); data = this_cpu_ptr(&dm_cpu_data); raw_spin_lock(&data->lock); dskb = data->skb; if (!dskb) goto out; nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); point = msg->points; for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, &point->pc, sizeof(void *))) { point->count++; goto out; } point++; } if (msg->entries == dm_hit_limit) goto out; /* * We need to create a new entry */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(point->pc, &location, sizeof(void *)); point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&data->send_timer); } out: raw_spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, const struct sock *rx_sk) { trace_drop_common(skb, location); } static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { struct net_device *dev = napi->dev; struct dm_hw_stat_delta *stat; /* * Don't check napi structures with no associated device */ if (!dev) return; rcu_read_lock(); stat = rcu_dereference(dev->dm_private); if (stat) { /* * only add a note to our monitor buffer if: * 1) its after the last_rx delta * 2) our rx_dropped count has gone up */ if (time_after(jiffies, stat->last_rx + dm_hw_check_delta) && (dev->stats.rx_dropped != stat->last_drop_val)) { trace_drop_common(NULL, NULL); stat->last_drop_val = dev->stats.rx_dropped; stat->last_rx = jiffies; } } rcu_read_unlock(); } static struct net_dm_hw_entries * net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data) { struct net_dm_hw_entries *hw_entries; unsigned long flags; hw_entries = kzalloc_flex(*hw_entries, entries, dm_hit_limit); if (!hw_entries) { /* If the memory allocation failed, we try to perform another * allocation in 1/10 second. Otherwise, the probe function * will constantly bail out. */ mod_timer(&hw_data->send_timer, jiffies + HZ / 10); } raw_spin_lock_irqsave(&hw_data->lock, flags); swap(hw_data->hw_entries, hw_entries); raw_spin_unlock_irqrestore(&hw_data->lock, flags); return hw_entries; } static int net_dm_hw_entry_put(struct sk_buff *msg, const struct net_dm_hw_entry *hw_entry) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRY); if (!attr) return -EMSGSIZE; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_entry->trap_name)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_HW_TRAP_COUNT, hw_entry->count)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_entries_put(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct nlattr *attr; int i; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRIES); if (!attr) return -EMSGSIZE; for (i = 0; i < hw_entries->num_entries; i++) { int rc; rc = net_dm_hw_entry_put(msg, &hw_entries->entries[i]); if (rc) goto nla_put_failure; } nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_summary_report_fill(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct net_dm_alert_msg anc_hdr = { 0 }; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!hdr) return -EMSGSIZE; /* We need to put the ancillary header in order not to break user * space. */ if (nla_put(msg, NLA_UNSPEC, sizeof(anc_hdr), &anc_hdr)) goto nla_put_failure; rc = net_dm_hw_entries_put(msg, hw_entries); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void net_dm_hw_summary_work(struct work_struct *work) { struct net_dm_hw_entries *hw_entries; struct per_cpu_dm_data *hw_data; struct sk_buff *msg; int rc; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); if (!hw_entries) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_summary_report_fill(msg, hw_entries); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: kfree(hw_entries); } static void net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct net_dm_hw_entries *hw_entries; struct net_dm_hw_entry *hw_entry; struct per_cpu_dm_data *hw_data; unsigned long flags; int i; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; hw_data = this_cpu_ptr(&dm_hw_cpu_data); raw_spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries; if (!hw_entries) goto out; for (i = 0; i < hw_entries->num_entries; i++) { hw_entry = &hw_entries->entries[i]; if (!strncmp(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) { hw_entry->count++; goto out; } } if (WARN_ON_ONCE(hw_entries->num_entries == dm_hit_limit)) goto out; hw_entry = &hw_entries->entries[hw_entries->num_entries]; strscpy(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1); hw_entry->count = 1; hw_entries->num_entries++; if (!timer_pending(&hw_data->send_timer)) { hw_data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&hw_data->send_timer); } out: raw_spin_unlock_irqrestore(&hw_data->lock, flags); } static const struct net_dm_alert_ops net_dm_alert_summary_ops = { .kfree_skb_probe = trace_kfree_skb_hit, .napi_poll_probe = trace_napi_poll_hit, .work_item_func = send_dm_alert, .hw_work_item_func = net_dm_hw_summary_work, .hw_trap_probe = net_dm_hw_trap_summary_probe, }; static void net_dm_packet_trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, const struct sock *rx_sk) { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; struct net_dm_skb_cb *cb; struct sk_buff *nskb; unsigned long flags; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; cb = NET_DM_SKB_CB(nskb); cb->reason = reason; cb->pc = location; /* Override the timestamp because we care about the time when the * packet was dropped. */ nskb->tstamp = tstamp; data = this_cpu_ptr(&dm_cpu_data); spin_lock_irqsave(&data->drop_queue.lock, flags); if (skb_queue_len(&data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&data->drop_queue.lock, flags); schedule_work(&data->dm_alert_work); return; unlock_free: u64_stats_update_begin(&data->stats.syncp); u64_stats_inc(&data->stats.dropped); u64_stats_update_end(&data->stats.syncp); spin_unlock_irqrestore(&data->drop_queue.lock, flags); consume_skb(nskb); } static void net_dm_packet_trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { } static size_t net_dm_in_port_size(void) { /* NET_DM_ATTR_IN_PORT nest */ return nla_total_size(0) + /* NET_DM_ATTR_PORT_NETDEV_IFINDEX */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PORT_NETDEV_NAME */ nla_total_size(IFNAMSIZ + 1); } #define NET_DM_MAX_SYMBOL_LEN 40 #define NET_DM_MAX_REASON_LEN 50 static size_t net_dm_packet_report_size(size_t payload_len) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PC */ nla_total_size_64bit(sizeof(u64)) + /* NET_DM_ATTR_SYMBOL */ nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size_64bit(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_REASON */ nla_total_size(NET_DM_MAX_REASON_LEN + 1) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_packet_report_in_port_put(struct sk_buff *msg, int ifindex, const char *name) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_IN_PORT); if (!attr) return -EMSGSIZE; if (ifindex && nla_put_u32(msg, NET_DM_ATTR_PORT_NETDEV_IFINDEX, ifindex)) goto nla_put_failure; if (name && nla_put_string(msg, NET_DM_ATTR_PORT_NETDEV_NAME, name)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct net_dm_skb_cb *cb = NET_DM_SKB_CB(skb); const struct drop_reason_list *list = NULL; unsigned int subsys, subsys_reason; char buf[NET_DM_MAX_SYMBOL_LEN]; struct nlattr *attr; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_SW)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, (u64)(uintptr_t)cb->pc, NET_DM_ATTR_PAD)) goto nla_put_failure; rcu_read_lock(); subsys = u32_get_bits(cb->reason, SKB_DROP_REASON_SUBSYS_MASK); if (subsys < SKB_DROP_REASON_SUBSYS_NUM) list = rcu_dereference(drop_reasons_by_subsys[subsys]); subsys_reason = cb->reason & ~SKB_DROP_REASON_SUBSYS_MASK; if (!list || subsys_reason >= list->n_reasons || !list->reasons[subsys_reason] || strlen(list->reasons[subsys_reason]) > NET_DM_MAX_REASON_LEN) { list = rcu_dereference(drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_CORE]); subsys_reason = SKB_DROP_REASON_NOT_SPECIFIED; } if (nla_put_string(msg, NET_DM_ATTR_REASON, list->reasons[subsys_reason])) { rcu_read_unlock(); goto nla_put_failure; } rcu_read_unlock(); snprintf(buf, sizeof(buf), "%pS", cb->pc); if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) goto nla_put_failure; rc = net_dm_packet_report_in_port_put(msg, skb->skb_iif, NULL); if (rc) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = __nla_reserve(msg, NET_DM_ATTR_PAYLOAD, payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } #define NET_DM_MAX_PACKET_SIZE (0xffff - NLA_HDRLEN - NLA_ALIGNTO) static void net_dm_packet_report(struct sk_buff *skb) { struct sk_buff *msg; size_t payload_len; int rc; /* Make sure we start copying the packet from the MAC header */ if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); /* Ensure packet fits inside a single netlink attribute */ payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); if (!msg) goto out; rc = net_dm_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: consume_skb(skb); } static void net_dm_packet_work(struct work_struct *work) { struct per_cpu_dm_data *data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&data->drop_queue.lock, flags); skb_queue_splice_tail_init(&data->drop_queue, &list); spin_unlock_irqrestore(&data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_packet_report(skb); } static size_t net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata) { return hw_metadata->fa_cookie ? nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; } static size_t net_dm_hw_packet_report_size(size_t payload_len, const struct devlink_trap_metadata *hw_metadata) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_HW_TRAP_GROUP_NAME */ nla_total_size(strlen(hw_metadata->trap_group_name) + 1) + /* NET_DM_ATTR_HW_TRAP_NAME */ nla_total_size(strlen(hw_metadata->trap_name) + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size_64bit(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_hw_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct devlink_trap_metadata *hw_metadata; struct nlattr *attr; void *hdr; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_HW)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_GROUP_NAME, hw_metadata->trap_group_name)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_metadata->trap_name)) goto nla_put_failure; if (hw_metadata->input_dev) { struct net_device *dev = hw_metadata->input_dev; int rc; rc = net_dm_packet_report_in_port_put(msg, dev->ifindex, dev->name); if (rc) goto nla_put_failure; } if (hw_metadata->fa_cookie && nla_put(msg, NET_DM_ATTR_FLOW_ACTION_COOKIE, hw_metadata->fa_cookie->cookie_len, hw_metadata->fa_cookie->cookie)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = __nla_reserve(msg, NET_DM_ATTR_PAYLOAD, payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static struct devlink_trap_metadata * net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) { const struct flow_action_cookie *fa_cookie; struct devlink_trap_metadata *hw_metadata; const char *trap_group_name; const char *trap_name; hw_metadata = kzalloc_obj(*hw_metadata, GFP_ATOMIC); if (!hw_metadata) return NULL; trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC); if (!trap_group_name) goto free_hw_metadata; hw_metadata->trap_group_name = trap_group_name; trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC); if (!trap_name) goto free_trap_group; hw_metadata->trap_name = trap_name; if (metadata->fa_cookie) { size_t cookie_size = sizeof(*fa_cookie) + metadata->fa_cookie->cookie_len; fa_cookie = kmemdup(metadata->fa_cookie, cookie_size, GFP_ATOMIC); if (!fa_cookie) goto free_trap_name; hw_metadata->fa_cookie = fa_cookie; } hw_metadata->input_dev = metadata->input_dev; netdev_hold(hw_metadata->input_dev, &hw_metadata->dev_tracker, GFP_ATOMIC); return hw_metadata; free_trap_name: kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: kfree(hw_metadata); return NULL; } static void net_dm_hw_metadata_free(struct devlink_trap_metadata *hw_metadata) { netdev_put(hw_metadata->input_dev, &hw_metadata->dev_tracker); kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); kfree(hw_metadata); } static void net_dm_hw_packet_report(struct sk_buff *skb) { struct devlink_trap_metadata *hw_metadata; struct sk_buff *msg; size_t payload_len; int rc; if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; msg = nlmsg_new(net_dm_hw_packet_report_size(payload_len, hw_metadata), GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: net_dm_hw_metadata_free(NET_DM_SKB_CB(skb)->hw_metadata); consume_skb(skb); } static void net_dm_hw_packet_work(struct work_struct *work) { struct per_cpu_dm_data *hw_data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); skb_queue_splice_tail_init(&hw_data->drop_queue, &list); spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_hw_packet_report(skb); } static void net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct devlink_trap_metadata *n_hw_metadata; ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *hw_data; struct sk_buff *nskb; unsigned long flags; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; n_hw_metadata = net_dm_hw_metadata_copy(metadata); if (!n_hw_metadata) goto free; NET_DM_SKB_CB(nskb)->hw_metadata = n_hw_metadata; nskb->tstamp = tstamp; hw_data = this_cpu_ptr(&dm_hw_cpu_data); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); if (skb_queue_len(&hw_data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&hw_data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); schedule_work(&hw_data->dm_alert_work); return; unlock_free: u64_stats_update_begin(&hw_data->stats.syncp); u64_stats_inc(&hw_data->stats.dropped); u64_stats_update_end(&hw_data->stats.syncp); spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); net_dm_hw_metadata_free(n_hw_metadata); free: consume_skb(nskb); } static const struct net_dm_alert_ops net_dm_alert_packet_ops = { .kfree_skb_probe = net_dm_packet_trace_kfree_skb_hit, .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, .work_item_func = net_dm_packet_work, .hw_work_item_func = net_dm_hw_packet_work, .hw_trap_probe = net_dm_hw_trap_packet_probe, }; static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { [NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops, [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, }; #if IS_ENABLED(CONFIG_NET_DEVLINK) static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL); } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL); tracepoint_synchronize_unregister(); } #else static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return -EOPNOTSUPP; } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { } #endif static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; if (monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled"); return -EAGAIN; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_hw_entries *hw_entries; INIT_WORK(&hw_data->dm_alert_work, ops->hw_work_item_func); timer_setup(&hw_data->send_timer, sched_send_work, 0); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); kfree(hw_entries); } rc = net_dm_hw_probe_register(ops); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint"); goto err_module_put; } monitor_hw = true; return 0; err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); return rc; } static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu; if (!monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled"); return; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; monitor_hw = false; net_dm_hw_probe_unregister(ops); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); } static int net_dm_trace_on_set(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; INIT_WORK(&data->dm_alert_work, ops->work_item_func); timer_setup(&data->send_timer, sched_send_work, 0); /* Allocate a new per-CPU skb for the summary alert message and * free the old one which might contain stale data from * previous tracing. */ skb = reset_per_cpu_data(data); consume_skb(skb); } rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint"); goto err_module_put; } rc = register_trace_napi_poll(ops->napi_poll_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint"); goto err_unregister_trace; } return 0; err_unregister_trace: unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); return rc; } static void net_dm_trace_off_set(void) { const struct net_dm_alert_ops *ops; int cpu; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; unregister_trace_napi_poll(ops->napi_poll_probe, NULL); unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); tracepoint_synchronize_unregister(); /* Make sure we do not send notifications to user space after request * to stop tracing returns. */ for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); } static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) { int rc = 0; if (state == trace_state) { NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); return -EAGAIN; } switch (state) { case TRACE_ON: rc = net_dm_trace_on_set(extack); break; case TRACE_OFF: net_dm_trace_off_set(); break; default: rc = 1; break; } if (!rc) trace_state = state; else rc = -EINPROGRESS; return rc; } static bool net_dm_is_monitoring(void) { return trace_state == TRACE_ON || monitor_hw; } static int net_dm_alert_mode_get_from_info(struct genl_info *info, enum net_dm_alert_mode *p_alert_mode) { u8 val; val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); switch (val) { case NET_DM_ALERT_MODE_SUMMARY: case NET_DM_ALERT_MODE_PACKET: *p_alert_mode = val; break; default: return -EINVAL; } return 0; } static int net_dm_alert_mode_set(struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; enum net_dm_alert_mode alert_mode; int rc; if (!info->attrs[NET_DM_ATTR_ALERT_MODE]) return 0; rc = net_dm_alert_mode_get_from_info(info, &alert_mode); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Invalid alert mode"); return -EINVAL; } net_dm_alert_mode = alert_mode; return 0; } static void net_dm_trunc_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_TRUNC_LEN]) return; net_dm_trunc_len = nla_get_u32(info->attrs[NET_DM_ATTR_TRUNC_LEN]); } static void net_dm_queue_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_QUEUE_LEN]) return; net_dm_queue_len = nla_get_u32(info->attrs[NET_DM_ATTR_QUEUE_LEN]); } static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; int rc; if (net_dm_is_monitoring()) { NL_SET_ERR_MSG_MOD(extack, "Cannot configure drop monitor during monitoring"); return -EBUSY; } rc = net_dm_alert_mode_set(info); if (rc) return rc; net_dm_trunc_len_set(info); net_dm_queue_len_set(info); return 0; } static int net_dm_monitor_start(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { bool sw_set = false; int rc; if (set_sw) { rc = set_all_monitor_traces(TRACE_ON, extack); if (rc) return rc; sw_set = true; } if (set_hw) { rc = net_dm_hw_monitor_start(extack); if (rc) goto err_monitor_hw; } return 0; err_monitor_hw: if (sw_set) set_all_monitor_traces(TRACE_OFF, extack); return rc; } static void net_dm_monitor_stop(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { if (set_hw) net_dm_hw_monitor_stop(extack); if (set_sw) set_all_monitor_traces(TRACE_OFF, extack); } static int net_dm_cmd_trace(struct sk_buff *skb, struct genl_info *info) { bool set_sw = !!info->attrs[NET_DM_ATTR_SW_DROPS]; bool set_hw = !!info->attrs[NET_DM_ATTR_HW_DROPS]; struct netlink_ext_ack *extack = info->extack; /* To maintain backward compatibility, we start / stop monitoring of * software drops if no flag is specified. */ if (!set_sw && !set_hw) set_sw = true; switch (info->genlhdr->cmd) { case NET_DM_CMD_START: return net_dm_monitor_start(set_sw, set_hw, extack); case NET_DM_CMD_STOP: net_dm_monitor_stop(set_sw, set_hw, extack); return 0; } return -EOPNOTSUPP; } static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_CONFIG_NEW); if (!hdr) return -EMSGSIZE; if (nla_put_u8(msg, NET_DM_ATTR_ALERT_MODE, net_dm_alert_mode)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_TRUNC_LEN, net_dm_trunc_len)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_QUEUE_LEN, net_dm_queue_len)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_config_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_config_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static void net_dm_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct net_dm_stats *cpu_stats = &data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static void net_dm_hw_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_stats *cpu_stats = &hw_data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_hw_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_hw_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_HW_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_stats_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; int rc; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_STATS_NEW); if (!hdr) return -EMSGSIZE; rc = net_dm_stats_put(msg); if (rc) goto nla_put_failure; rc = net_dm_hw_stats_put(msg); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_stats_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_stats_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static int dropmon_net_event(struct notifier_block *ev_block, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dm_hw_stat_delta *stat; switch (event) { case NETDEV_REGISTER: if (WARN_ON_ONCE(rtnl_dereference(dev->dm_private))) break; stat = kzalloc_obj(*stat); if (!stat) break; stat->last_rx = jiffies; rcu_assign_pointer(dev->dm_private, stat); break; case NETDEV_UNREGISTER: stat = rtnl_dereference(dev->dm_private); if (stat) { rcu_assign_pointer(dev->dm_private, NULL); kfree_rcu(stat, rcu); } break; } return NOTIFY_DONE; } static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { [NET_DM_ATTR_UNSPEC] = { .strict_start_type = NET_DM_ATTR_UNSPEC + 1 }, [NET_DM_ATTR_ALERT_MODE] = { .type = NLA_U8 }, [NET_DM_ATTR_TRUNC_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_SW_DROPS] = {. type = NLA_FLAG }, [NET_DM_ATTR_HW_DROPS] = {. type = NLA_FLAG }, }; static const struct genl_small_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_config, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_CONFIG_GET, .doit = net_dm_cmd_config_get, }, { .cmd = NET_DM_CMD_STATS_GET, .doit = net_dm_cmd_stats_get, }, }; static int net_dm_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_lock(&net_dm_mutex); return 0; } static void net_dm_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_unlock(&net_dm_mutex); } static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, .maxattr = NET_DM_ATTR_MAX, .policy = net_dm_nl_policy, .pre_doit = net_dm_nl_pre_doit, .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .small_ops = dropmon_ops, .n_small_ops = ARRAY_SIZE(dropmon_ops), .resv_start_op = NET_DM_CMD_STATS_GET + 1, .mcgrps = dropmon_mcgrps, .n_mcgrps = ARRAY_SIZE(dropmon_mcgrps), }; static struct notifier_block dropmon_net_notifier = { .notifier_call = dropmon_net_event }; static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data) { raw_spin_lock_init(&data->lock); skb_queue_head_init(&data->drop_queue); u64_stats_init(&data->stats.syncp); } static void __net_dm_cpu_data_fini(struct per_cpu_dm_data *data) { WARN_ON(!skb_queue_empty(&data->drop_queue)); } static void net_dm_cpu_data_init(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); __net_dm_cpu_data_init(data); } static void net_dm_cpu_data_fini(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); /* At this point, we should have exclusive access * to this struct and can free the skb inside it. */ consume_skb(data->skb); __net_dm_cpu_data_fini(data); } static void net_dm_hw_cpu_data_init(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); __net_dm_cpu_data_init(hw_data); } static void net_dm_hw_cpu_data_fini(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); kfree(hw_data->hw_entries); __net_dm_cpu_data_fini(hw_data); } static int __init init_net_drop_monitor(void) { int cpu, rc; pr_info("Initializing network drop monitor service\n"); if (sizeof(void *) > 8) { pr_err("Unable to store program counters on this arch, Drop monitor failed\n"); return -ENOSPC; } for_each_possible_cpu(cpu) { net_dm_cpu_data_init(cpu); net_dm_hw_cpu_data_init(cpu); } rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); return rc; } rc = genl_register_family(&net_drop_monitor_family); if (rc) { pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; goto out; out_unreg: WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } static void exit_net_drop_monitor(void) { int cpu; /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ BUG_ON(genl_unregister_family(&net_drop_monitor_family)); BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } } module_init(init_net_drop_monitor); module_exit(exit_net_drop_monitor); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); MODULE_ALIAS_GENL_FAMILY("NET_DM"); MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts"); |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Universal/legacy platform driver for 8250/16550-type serial ports * * Supports: * ISA-compatible 8250/16550 ports * ACPI 8250/16550 ports * PNP 8250/16550 ports * "serial8250" platform devices */ #include <linux/acpi.h> #include <linux/array_size.h> #include <linux/cleanup.h> #include <linux/io.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/once.h> #include <linux/platform_device.h> #include <linux/serial_8250.h> #ifdef CONFIG_SPARC #include <linux/sunserialcore.h> #endif #include "8250.h" /* * Configuration: * share_irqs: Whether we pass IRQF_SHARED to request_irq(). * This option is unsafe when used on edge-triggered interrupts. */ static bool share_irqs = IS_ENABLED(CONFIG_SERIAL_8250_SHARE_IRQ); unsigned int nr_uarts = CONFIG_SERIAL_8250_RUNTIME_UARTS; #include <asm/serial.h> /* * SERIAL_PORT_DFNS tells us about built-in ports that have no * standard enumeration mechanism. Platforms that can find all * serial ports via mechanisms like ACPI or PCI need not supply it. */ #ifndef SERIAL_PORT_DFNS #define SERIAL_PORT_DFNS #endif static const struct old_serial_port old_serial_port[] = { SERIAL_PORT_DFNS /* defined in asm/serial.h */ }; serial8250_isa_config_fn serial8250_isa_config; void serial8250_set_isa_configurator(serial8250_isa_config_fn v) { serial8250_isa_config = v; } EXPORT_SYMBOL(serial8250_set_isa_configurator); static void __init __serial8250_isa_init_ports(void) { int i; if (nr_uarts > UART_NR) nr_uarts = UART_NR; /* * Set up initial ISA ports based on nr_uart module param, or else * default to CONFIG_SERIAL_8250_RUNTIME_UARTS. Note that we do not * need to increase nr_uarts when setting up the initial ISA ports. */ for (i = 0; i < nr_uarts; i++) serial8250_setup_port(i); /* chain base port ops to support Remote Supervisor Adapter */ univ8250_port_ops = *univ8250_port_base_ops; univ8250_rsa_support(&univ8250_port_ops, univ8250_port_base_ops); for (i = 0; i < ARRAY_SIZE(old_serial_port) && i < nr_uarts; i++) { struct uart_8250_port *up = serial8250_get_port(i); struct uart_port *port = &up->port; port->iobase = old_serial_port[i].port; port->irq = irq_canonicalize(old_serial_port[i].irq); port->irqflags = 0; port->uartclk = old_serial_port[i].baud_base * 16; port->flags = old_serial_port[i].flags; port->hub6 = 0; port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; if (share_irqs) port->irqflags |= IRQF_SHARED; if (serial8250_isa_config != NULL) serial8250_isa_config(i, &up->port, &up->capabilities); } } void __init serial8250_isa_init_ports(void) { DO_ONCE(__serial8250_isa_init_ports); } /* * Generic 16550A platform devices */ static int serial8250_probe_acpi(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct resource *regs; int ret, line; struct uart_8250_port *uart __free(kfree) = kzalloc_obj(*uart); if (!uart) return -ENOMEM; regs = platform_get_mem_or_io(pdev, 0); if (!regs) return dev_err_probe(dev, -EINVAL, "no registers defined\n"); switch (resource_type(regs)) { case IORESOURCE_IO: uart->port.iobase = regs->start; break; case IORESOURCE_MEM: uart->port.mapbase = regs->start; uart->port.mapsize = resource_size(regs); uart->port.flags = UPF_IOREMAP; break; default: return -EINVAL; } /* default clock frequency */ uart->port.uartclk = 1843200; uart->port.type = PORT_16550A; uart->port.dev = &pdev->dev; uart->port.flags |= UPF_SKIP_TEST | UPF_BOOT_AUTOCONF; ret = uart_read_and_validate_port_properties(&uart->port); /* no interrupt -> fall back to polling */ if (ret == -ENXIO) ret = 0; if (ret) return ret; line = serial8250_register_8250_port(uart); if (line < 0) return line; return 0; } static int serial8250_probe_platform(struct platform_device *dev, struct plat_serial8250_port *p) { int ret, i; struct uart_8250_port *uart __free(kfree) = kzalloc_obj(*uart); if (!uart) return -ENOMEM; for (i = 0; p && p->flags != 0; p++, i++) { uart->port.iobase = p->iobase; uart->port.membase = p->membase; uart->port.irq = p->irq; uart->port.irqflags = p->irqflags; uart->port.uartclk = p->uartclk; uart->port.regshift = p->regshift; uart->port.iotype = p->iotype; uart->port.flags = p->flags; uart->port.mapbase = p->mapbase; uart->port.mapsize = p->mapsize; uart->port.hub6 = p->hub6; uart->port.has_sysrq = p->has_sysrq; uart->port.private_data = p->private_data; uart->port.type = p->type; uart->bugs = p->bugs; uart->port.serial_in = p->serial_in; uart->port.serial_out = p->serial_out; uart->dl_read = p->dl_read; uart->dl_write = p->dl_write; uart->port.handle_irq = p->handle_irq; uart->port.handle_break = p->handle_break; uart->port.set_termios = p->set_termios; uart->port.set_ldisc = p->set_ldisc; uart->port.get_mctrl = p->get_mctrl; uart->port.pm = p->pm; uart->port.dev = &dev->dev; if (share_irqs) uart->port.irqflags |= IRQF_SHARED; ret = serial8250_register_8250_port(uart); if (ret < 0) { dev_err(&dev->dev, "unable to register port at index %d " "(IO%lx MEM%llx IRQ%d): %d\n", i, p->iobase, (unsigned long long)p->mapbase, p->irq, ret); } } return 0; } /* * Register a set of serial devices attached to a platform device. * The list is terminated with a zero flags entry, which means we expect * all entries to have at least UPF_BOOT_AUTOCONF set. */ static int serial8250_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct plat_serial8250_port *p; p = dev_get_platdata(dev); if (p) return serial8250_probe_platform(pdev, p); /* * Probe platform UART devices defined using standard hardware * discovery mechanism like ACPI or DT. Support only ACPI based * serial device for now. */ if (has_acpi_companion(dev)) return serial8250_probe_acpi(pdev); return 0; } /* * Remove serial ports registered against a platform device. */ static void serial8250_remove(struct platform_device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = serial8250_get_port(i); if (up->port.dev == &dev->dev) serial8250_unregister_port(i); } } static int serial8250_suspend(struct platform_device *dev, pm_message_t state) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = serial8250_get_port(i); if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) uart_suspend_port(&serial8250_reg, &up->port); } return 0; } static int serial8250_resume(struct platform_device *dev) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = serial8250_get_port(i); if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) serial8250_resume_port(i); } return 0; } static const struct acpi_device_id acpi_platform_serial_table[] = { { "RSCV0003" }, /* RISC-V Generic 16550A UART */ { } }; MODULE_DEVICE_TABLE(acpi, acpi_platform_serial_table); static struct platform_driver serial8250_isa_driver = { .probe = serial8250_probe, .remove = serial8250_remove, .suspend = serial8250_suspend, .resume = serial8250_resume, .driver = { .name = "serial8250", .acpi_match_table = acpi_platform_serial_table, }, }; /* * This "device" covers _all_ ISA 8250-compatible serial devices listed * in the table in include/asm/serial.h. */ struct platform_device *serial8250_isa_devs; static int __init serial8250_init(void) { int ret; if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); pr_info("Serial: 8250/16550 driver, %d ports, IRQ sharing %s\n", nr_uarts, str_enabled_disabled(share_irqs)); #ifdef CONFIG_SPARC ret = sunserial_register_minors(&serial8250_reg, UART_NR); #else serial8250_reg.nr = UART_NR; ret = uart_register_driver(&serial8250_reg); #endif if (ret) goto out; ret = serial8250_pnp_init(); if (ret) goto unreg_uart_drv; serial8250_isa_devs = platform_device_alloc("serial8250", PLAT8250_DEV_LEGACY); if (!serial8250_isa_devs) { ret = -ENOMEM; goto unreg_pnp; } ret = platform_device_add(serial8250_isa_devs); if (ret) goto put_dev; serial8250_register_ports(&serial8250_reg, &serial8250_isa_devs->dev); ret = platform_driver_register(&serial8250_isa_driver); if (ret == 0) goto out; platform_device_del(serial8250_isa_devs); put_dev: platform_device_put(serial8250_isa_devs); unreg_pnp: serial8250_pnp_exit(); unreg_uart_drv: #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif out: return ret; } module_init(serial8250_init); static void __exit serial8250_exit(void) { struct platform_device *isa_dev = serial8250_isa_devs; /* * This tells serial8250_unregister_port() not to re-register * the ports (thereby making serial8250_isa_driver permanently * in use). */ serial8250_isa_devs = NULL; platform_driver_unregister(&serial8250_isa_driver); platform_device_unregister(isa_dev); serial8250_pnp_exit(); #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif } module_exit(serial8250_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic 8250/16x50 serial platform driver"); module_param_hw(share_irqs, bool, other, 0644); MODULE_PARM_DESC(share_irqs, "Share IRQs with other non-8250/16x50 devices (unsafe)"); module_param(nr_uarts, uint, 0644); MODULE_PARM_DESC(nr_uarts, "Maximum number of UARTs supported. (1-" __MODULE_STRING(CONFIG_SERIAL_8250_NR_UARTS) ")"); MODULE_ALIAS_CHARDEV_MAJOR(TTY_MAJOR); |
| 95 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_SECTIONS_H_ #define _ASM_GENERIC_SECTIONS_H_ /* References to section boundaries */ #include <linux/compiler.h> #include <linux/types.h> /* * Usage guidelines: * _text, _data: architecture specific, don't use them in arch-independent code * [_stext, _etext]: contains .text.* sections, may also contain .rodata.* * and/or .init.* sections * [_sdata, _edata]: contains .data.* sections, may also contain .rodata.* * and/or .init.* sections. * [__start_rodata, __end_rodata]: contains .rodata.* sections * [__start_ro_after_init, __end_ro_after_init]: * contains .data..ro_after_init section * [__init_begin, __init_end]: contains .init.* sections, but .init.text.* * may be out of this range on some architectures. * [_sinittext, _einittext]: contains .init.text.* sections * [__bss_start, __bss_stop]: contains BSS sections * * Following global variables are optional and may be unavailable on some * architectures and/or kernel configurations. * _text, _data * __kprobes_text_start, __kprobes_text_end * __entry_text_start, __entry_text_end * __ctors_start, __ctors_end * __irqentry_text_start, __irqentry_text_end * __softirqentry_text_start, __softirqentry_text_end * __start_opd, __end_opd */ extern char _text[], _stext[], _etext[]; extern char _data[], _sdata[], _edata[]; extern char __bss_start[], __bss_stop[]; extern char __init_begin[], __init_end[]; extern char _sinittext[], _einittext[]; extern char __start_ro_after_init[], __end_ro_after_init[]; extern char _end[]; extern char __per_cpu_start[], __per_cpu_end[]; extern char __kprobes_text_start[], __kprobes_text_end[]; extern char __entry_text_start[], __entry_text_end[]; extern char __start_rodata[], __end_rodata[]; extern char __irqentry_text_start[], __irqentry_text_end[]; extern char __softirqentry_text_start[], __softirqentry_text_end[]; extern char __start_once[], __end_once[]; /* Start and end of .ctors section - used for constructor calls. */ extern char __ctors_start[], __ctors_end[]; /* Start and end of .opd section - used for function descriptors. */ extern char __start_opd[], __end_opd[]; /* Start and end of instrumentation protected text section */ extern char __noinstr_text_start[], __noinstr_text_end[]; extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ #ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS void *dereference_function_descriptor(void *ptr); void *dereference_kernel_function_descriptor(void *ptr); #else #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) /* An address is simply the address of the function. */ typedef struct { unsigned long addr; } func_desc_t; #endif static inline bool have_function_descriptors(void) { return IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS); } /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the memory region defined by @begin and @end, false * otherwise. */ static inline bool memory_contains(void *begin, void *end, void *virt, size_t size) { return virt >= begin && virt + size <= end; } /** * memory_intersects - checks if the region occupied by an object intersects * with another memory region * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the region specified by @begin and @end, false otherwise. */ static inline bool memory_intersects(void *begin, void *end, void *virt, size_t size) { void *vend = virt + size; if (virt < end && vend > begin) return true; return false; } /** * init_section_contains - checks if an object is contained within the init * section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the init section, false otherwise. */ static inline bool init_section_contains(void *virt, size_t size) { return memory_contains(__init_begin, __init_end, virt, size); } /** * init_section_intersects - checks if the region occupied by an object * intersects with the init section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the init section, false otherwise. */ static inline bool init_section_intersects(void *virt, size_t size) { return memory_intersects(__init_begin, __init_end, virt, size); } /** * is_kernel_core_data - checks if the pointer address is located in the * .data or .bss section * * @addr: address to check * * Returns: true if the address is located in .data or .bss, false otherwise. * Note: On some archs it may return true for core RODATA, and false * for others. But will always be true for core RW data. */ static inline bool is_kernel_core_data(unsigned long addr) { if (addr >= (unsigned long)_sdata && addr < (unsigned long)_edata) return true; if (addr >= (unsigned long)__bss_start && addr < (unsigned long)__bss_stop) return true; return false; } /** * is_kernel_rodata - checks if the pointer address is located in the * .rodata section * * @addr: address to check * * Returns: true if the address is located in .rodata, false otherwise. */ static inline bool is_kernel_rodata(unsigned long addr) { return addr >= (unsigned long)__start_rodata && addr < (unsigned long)__end_rodata; } static inline bool is_kernel_ro_after_init(unsigned long addr) { return addr >= (unsigned long)__start_ro_after_init && addr < (unsigned long)__end_ro_after_init; } /** * is_kernel_inittext - checks if the pointer address is located in the * .init.text section * * @addr: address to check * * Returns: true if the address is located in .init.text, false otherwise. */ static inline bool is_kernel_inittext(unsigned long addr) { return addr >= (unsigned long)_sinittext && addr < (unsigned long)_einittext; } /** * __is_kernel_text - checks if the pointer address is located in the * .text section * * @addr: address to check * * Returns: true if the address is located in .text, false otherwise. * Note: an internal helper, only check the range of _stext to _etext. */ static inline bool __is_kernel_text(unsigned long addr) { return addr >= (unsigned long)_stext && addr < (unsigned long)_etext; } /** * __is_kernel - checks if the pointer address is located in the kernel range * * @addr: address to check * * Returns: true if the address is located in the kernel range, false otherwise. * Note: an internal helper, check the range of _stext to _end, * and range from __init_begin to __init_end, which can be outside * of the _stext to _end range. */ static inline bool __is_kernel(unsigned long addr) { return ((addr >= (unsigned long)_stext && addr < (unsigned long)_end) || (addr >= (unsigned long)__init_begin && addr < (unsigned long)__init_end)); } #endif /* _ASM_GENERIC_SECTIONS_H_ */ |
| 18 36 2 34 1 32 18 1 10 29 29 27 8 8 4 4 4 4 3 1 1 1 79 8 10 6 2 3 9 2 5 5 5 5 5 5 5 6 20 5 3 4 5 5 8 2 2 8 3 3 6 6 9 9 9 8 16 16 23 15 8 10 10 2 13 13 10 1 1 22 3 13 5 8 1 1 14 6 8 4 4 3 9 10 7 8 2 4 10 26 26 40 40 2 1 1 4 2 3 28 10 3 2 15 4 5 1 1 1 2 6 4 1 7 12 13 2 15 1 11 4 2 9 12 9 4 24 24 33 33 38 38 1 26 26 7 3 2514 2516 1279 288 612 26 25 25 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 | // 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 <linux/local_lock.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; local_lock_t bq_lock; }; 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; lockdep_assert_held(&bq->bq_lock); 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) { local_lock_nested_bh(&bq->dev->xdp_bulkq->bq_lock); bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); local_unlock_nested_bh(&bq->dev->xdp_bulkq->bq_lock); } } /* 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. PREEMPT_RT relies on local_lock_nested_bh() * to serialise access to the per-CPU bq. */ 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; local_lock_nested_bh(&dev->xdp_bulkq->bq_lock); 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; local_unlock_nested_bh(&dev->xdp_bulkq->bq_lock); } 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; /* Frags live outside the linear frame and cannot be cloned safely. */ if (unlikely(xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; 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' elements. * Returns the number of ifindexes added, or -EOVERFLOW if there are too * many upper devices. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes, int max) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { if (n >= max) return -EOVERFLOW; 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, ARRAY_SIZE(excluded_devices) - 1); if (num_excluded < 0) return num_excluded; 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, 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; } } } /* 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; if (dst->xdp_prog && skb_cloned(skb)) { struct sk_buff *nskb; nskb = skb_copy(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; nskb->mac_len = skb->mac_len; consume_skb(skb); skb = nskb; } /* 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; if (unlikely(skb_is_nonlinear(skb))) return -EOPNOTSUPP; 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; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices, ARRAY_SIZE(excluded_devices) - 1); if (num_excluded < 0) return num_excluded; 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_rcu(dst, head, index_hlist, rcu_read_lock_bh_held()) { 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) { struct xdp_dev_bulk_queue *bq; bq = per_cpu_ptr(netdev->xdp_bulkq, cpu); bq->dev = netdev; local_lock_init(&bq->bq_lock); } 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); |
| 3 39 20 20 20 12 20 20 9 62 1 28 3 30 2 55 15 46 29 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 | /* * Copyright (c) 2006 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/percpu.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/export.h> #include <linux/uio.h> #include "rds.h" /* * This file implements a getsockopt() call which copies a set of fixed * sized structs into a user-specified buffer as a means of providing * read-only information about RDS. * * For a given information source there are a given number of fixed sized * structs at a given time. The structs are only copied if the user-specified * buffer is big enough. The destination pages that make up the buffer * are pinned for the duration of the copy. * * This gives us the following benefits: * * - simple implementation, no copy "position" across multiple calls * - consistent snapshot of an info source * - atomic copy works well with whatever locking info source has * - one portable tool to get rds info across implementations * - long-lived tool can get info without allocating * * at the following costs: * * - info source copy must be pinned, may be "large" */ struct rds_info_iterator { struct page **pages; void *addr; unsigned long offset; }; static DEFINE_SPINLOCK(rds_info_lock); static rds_info_func rds_info_funcs[RDS_INFO_LAST - RDS_INFO_FIRST + 1]; void rds_info_register_func(int optname, rds_info_func func) { int offset = optname - RDS_INFO_FIRST; BUG_ON(optname < RDS_INFO_FIRST || optname > RDS_INFO_LAST); spin_lock(&rds_info_lock); BUG_ON(rds_info_funcs[offset]); rds_info_funcs[offset] = func; spin_unlock(&rds_info_lock); } EXPORT_SYMBOL_GPL(rds_info_register_func); void rds_info_deregister_func(int optname, rds_info_func func) { int offset = optname - RDS_INFO_FIRST; BUG_ON(optname < RDS_INFO_FIRST || optname > RDS_INFO_LAST); spin_lock(&rds_info_lock); BUG_ON(rds_info_funcs[offset] != func); rds_info_funcs[offset] = NULL; spin_unlock(&rds_info_lock); } EXPORT_SYMBOL_GPL(rds_info_deregister_func); /* * Typically we hold an atomic kmap across multiple rds_info_copy() calls * because the kmap is so expensive. This must be called before using blocking * operations while holding the mapping and as the iterator is torn down. */ void rds_info_iter_unmap(struct rds_info_iterator *iter) { if (iter->addr) { kunmap_atomic(iter->addr); iter->addr = NULL; } } /* * get_user_pages() called flush_dcache_page() on the pages for us. */ void rds_info_copy(struct rds_info_iterator *iter, void *data, unsigned long bytes) { unsigned long this; while (bytes) { if (!iter->addr) iter->addr = kmap_atomic(*iter->pages); this = min(bytes, PAGE_SIZE - iter->offset); rdsdebug("page %p addr %p offset %lu this %lu data %p " "bytes %lu\n", *iter->pages, iter->addr, iter->offset, this, data, bytes); memcpy(iter->addr + iter->offset, data, this); data += this; bytes -= this; iter->offset += this; if (iter->offset == PAGE_SIZE) { kunmap_atomic(iter->addr); iter->addr = NULL; iter->offset = 0; iter->pages++; } } } EXPORT_SYMBOL_GPL(rds_info_copy); /* * @opt->iter_out describes the buffer that the information snapshot will be * copied into, and @opt->optlen is the size of that buffer on input. On * output @opt->optlen is set to the size of the requested snapshot in bytes. * * This function returns -errno if there is a failure, particularly -ENOSPC * if the given buffer was not large enough to fit the snapshot. On success * it returns the positive number of bytes of each array element in the * snapshot. */ int rds_info_getsockopt(struct socket *sock, int optname, sockopt_t *opt) { struct rds_info_iterator iter; struct rds_info_lengths lens; unsigned long nr_pages = 0; rds_info_func func; struct page **pages = NULL; size_t offset0 = 0; int npages = 0; int ret; int len; int total; len = opt->optlen; /* check for all kinds of wrapping and the like */ if (len < 0 || len > INT_MAX - PAGE_SIZE + 1) { ret = -EINVAL; goto out; } /* The info producers write into the pages with kmap_atomic() while * holding a spinlock, so they need a genuine page-backed user buffer. */ if (!user_backed_iter(&opt->iter_out)) { ret = -EOPNOTSUPP; goto out; } /* a 0 len call is just trying to probe its length */ if (len == 0) goto call_func; /* * Preallocate the page array and pass it in so that * iov_iter_extract_pages() fills it in place rather than allocating * one for us. Handing it a non-NULL array keeps ownership of the * array with us on every return path, instead of depending on the * iterator code to allocate and hand it back. */ npages = iov_iter_npages(&opt->iter_out, INT_MAX); pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out; } ret = iov_iter_extract_pages(&opt->iter_out, &pages, len, npages, 0, &offset0); if (ret < 0) goto out; nr_pages = DIV_ROUND_UP(offset0 + ret, PAGE_SIZE); if (ret != len) { ret = -EAGAIN; /* XXX ? */ goto out; } rdsdebug("len %d nr_pages %lu\n", len, nr_pages); call_func: func = rds_info_funcs[optname - RDS_INFO_FIRST]; if (!func) { ret = -ENOPROTOOPT; goto out; } iter.pages = pages; iter.addr = NULL; iter.offset = offset0; func(sock, len, &iter, &lens); BUG_ON(lens.each == 0); total = lens.nr * lens.each; rds_info_iter_unmap(&iter); if (total > len) { len = total; ret = -ENOSPC; } else { len = total; ret = lens.each; } opt->optlen = len; out: /* * iov_iter_extract_pages() pins only user-backed (ubuf) iters; * iov_iter_extract_will_pin() reports whether an unpin is owed here. */ if (pages && iov_iter_extract_will_pin(&opt->iter_out)) unpin_user_pages_dirty_lock(pages, nr_pages, true); kvfree(pages); return ret; } |
| 18 18 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | /* * linux/fs/nls/nls_ascii.c * * Charset ascii translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ }; static const unsigned char *const page_uni2charset[256] = { page00, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "ascii", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_ascii(void) { return register_nls(&table); } static void __exit exit_nls_ascii(void) { unregister_nls(&table); } module_init(init_nls_ascii) module_exit(exit_nls_ascii) MODULE_DESCRIPTION("NLS ASCII (United States)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 77 77 96 418 412 135 457 72 177 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rpm #if !defined(_TRACE_RUNTIME_POWER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RUNTIME_POWER_H #include <linux/ktime.h> #include <linux/tracepoint.h> struct device; /* * The rpm_internal events are used for tracing some important * runtime pm internal functions. */ DECLARE_EVENT_CLASS(rpm_internal, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags), TP_STRUCT__entry( __string( name, dev_name(dev) ) __field( int, flags ) __field( int , usage_count ) __field( int , disable_depth ) __field( int , runtime_auto ) __field( int , request_pending ) __field( int , irq_safe ) __field( int , child_count ) ), TP_fast_assign( __assign_str(name); __entry->flags = flags; __entry->usage_count = atomic_read( &dev->power.usage_count); __entry->disable_depth = dev->power.disable_depth; __entry->runtime_auto = dev->power.runtime_auto; __entry->request_pending = dev->power.request_pending; __entry->irq_safe = dev->power.irq_safe; __entry->child_count = atomic_read( &dev->power.child_count); ), TP_printk("%s flags-%x cnt-%-2d dep-%-2d auto-%-1d p-%-1d" " irq-%-1d child-%d", __get_str(name), __entry->flags, __entry->usage_count, __entry->disable_depth, __entry->runtime_auto, __entry->request_pending, __entry->irq_safe, __entry->child_count ) ); DEFINE_EVENT(rpm_internal, rpm_suspend, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); DEFINE_EVENT(rpm_internal, rpm_resume, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); DEFINE_EVENT(rpm_internal, rpm_idle, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); DEFINE_EVENT(rpm_internal, rpm_usage, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); TRACE_EVENT(rpm_return_int, TP_PROTO(struct device *dev, unsigned long ip, int ret), TP_ARGS(dev, ip, ret), TP_STRUCT__entry( __string( name, dev_name(dev)) __field( unsigned long, ip ) __field( int, ret ) ), TP_fast_assign( __assign_str(name); __entry->ip = ip; __entry->ret = ret; ), TP_printk("%pS:%s ret=%d", (void *)__entry->ip, __get_str(name), __entry->ret) ); #define RPM_STATUS_STRINGS \ EM(RPM_INVALID, "RPM_INVALID") \ EM(RPM_ACTIVE, "RPM_ACTIVE") \ EM(RPM_RESUMING, "RPM_RESUMING") \ EM(RPM_SUSPENDED, "RPM_SUSPENDED") \ EMe(RPM_SUSPENDING, "RPM_SUSPENDING") /* Enums require being exported to userspace, for user tool parsing. */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); RPM_STATUS_STRINGS /* * Now redefine the EM() and EMe() macros to map the enums to the strings that * will be printed in the output. */ #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } TRACE_EVENT(rpm_status, TP_PROTO(struct device *dev, enum rpm_status status), TP_ARGS(dev, status), TP_STRUCT__entry( __string(name, dev_name(dev)) __field(int, status) ), TP_fast_assign( __assign_str(name); __entry->status = status; ), TP_printk("%s status=%s", __get_str(name), __print_symbolic(__entry->status, RPM_STATUS_STRINGS)) ); #endif /* _TRACE_RUNTIME_POWER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 1 1 5 1 11 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Based on net/wireless/trace.h */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cfg802154 #if !defined(__RDEV_CFG802154_OPS_TRACE) || defined(TRACE_HEADER_MULTI_READ) #define __RDEV_CFG802154_OPS_TRACE #include <linux/tracepoint.h> #include <net/cfg802154.h> #define MAXNAME 32 #define WPAN_PHY_ENTRY __array(char, wpan_phy_name, MAXNAME) #define WPAN_PHY_ASSIGN strscpy(__entry->wpan_phy_name, \ wpan_phy_name(wpan_phy), \ MAXNAME) #define WPAN_PHY_PR_FMT "%s" #define WPAN_PHY_PR_ARG __entry->wpan_phy_name #define WPAN_DEV_ENTRY __field(u32, identifier) #define WPAN_DEV_ASSIGN (__entry->identifier) = (!IS_ERR_OR_NULL(wpan_dev) \ ? wpan_dev->identifier : 0) #define WPAN_DEV_PR_FMT "wpan_dev(%u)" #define WPAN_DEV_PR_ARG (__entry->identifier) #define WPAN_CCA_ENTRY __field(enum nl802154_cca_modes, cca_mode) \ __field(enum nl802154_cca_opts, cca_opt) #define WPAN_CCA_ASSIGN \ do { \ (__entry->cca_mode) = cca->mode; \ (__entry->cca_opt) = cca->opt; \ } while (0) #define WPAN_CCA_PR_FMT "cca_mode: %d, cca_opt: %d" #define WPAN_CCA_PR_ARG __entry->cca_mode, __entry->cca_opt #define BOOL_TO_STR(bo) (bo) ? "true" : "false" /************************************************************* * rdev->ops traces * *************************************************************/ DECLARE_EVENT_CLASS(wpan_phy_only_evt, TP_PROTO(struct wpan_phy *wpan_phy), TP_ARGS(wpan_phy), TP_STRUCT__entry( WPAN_PHY_ENTRY ), TP_fast_assign( WPAN_PHY_ASSIGN; ), TP_printk(WPAN_PHY_PR_FMT, WPAN_PHY_PR_ARG) ); DEFINE_EVENT(wpan_phy_only_evt, 802154_rdev_suspend, TP_PROTO(struct wpan_phy *wpan_phy), TP_ARGS(wpan_phy) ); DEFINE_EVENT(wpan_phy_only_evt, 802154_rdev_resume, TP_PROTO(struct wpan_phy *wpan_phy), TP_ARGS(wpan_phy) ); TRACE_EVENT(802154_rdev_add_virtual_intf, TP_PROTO(struct wpan_phy *wpan_phy, char *name, enum nl802154_iftype type, __le64 extended_addr), TP_ARGS(wpan_phy, name, type, extended_addr), TP_STRUCT__entry( WPAN_PHY_ENTRY __string(vir_intf_name, name ? name : "<noname>") __field(enum nl802154_iftype, type) __field(__le64, extended_addr) ), TP_fast_assign( WPAN_PHY_ASSIGN; __assign_str(vir_intf_name); __entry->type = type; __entry->extended_addr = extended_addr; ), TP_printk(WPAN_PHY_PR_FMT ", virtual intf name: %s, type: %d, extended addr: 0x%llx", WPAN_PHY_PR_ARG, __get_str(vir_intf_name), __entry->type, __le64_to_cpu(__entry->extended_addr)) ); TRACE_EVENT(802154_rdev_del_virtual_intf, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev), TP_ARGS(wpan_phy, wpan_dev), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT, WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG) ); TRACE_EVENT(802154_rdev_set_channel, TP_PROTO(struct wpan_phy *wpan_phy, u8 page, u8 channel), TP_ARGS(wpan_phy, page, channel), TP_STRUCT__entry( WPAN_PHY_ENTRY __field(u8, page) __field(u8, channel) ), TP_fast_assign( WPAN_PHY_ASSIGN; __entry->page = page; __entry->channel = channel; ), TP_printk(WPAN_PHY_PR_FMT ", page: %d, channel: %d", WPAN_PHY_PR_ARG, __entry->page, __entry->channel) ); TRACE_EVENT(802154_rdev_set_tx_power, TP_PROTO(struct wpan_phy *wpan_phy, s32 power), TP_ARGS(wpan_phy, power), TP_STRUCT__entry( WPAN_PHY_ENTRY __field(s32, power) ), TP_fast_assign( WPAN_PHY_ASSIGN; __entry->power = power; ), TP_printk(WPAN_PHY_PR_FMT ", mbm: %d", WPAN_PHY_PR_ARG, __entry->power) ); TRACE_EVENT(802154_rdev_set_cca_mode, TP_PROTO(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca), TP_ARGS(wpan_phy, cca), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_CCA_ENTRY ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_CCA_ASSIGN; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_CCA_PR_FMT, WPAN_PHY_PR_ARG, WPAN_CCA_PR_ARG) ); TRACE_EVENT(802154_rdev_set_cca_ed_level, TP_PROTO(struct wpan_phy *wpan_phy, s32 ed_level), TP_ARGS(wpan_phy, ed_level), TP_STRUCT__entry( WPAN_PHY_ENTRY __field(s32, ed_level) ), TP_fast_assign( WPAN_PHY_ASSIGN; __entry->ed_level = ed_level; ), TP_printk(WPAN_PHY_PR_FMT ", ed level: %d", WPAN_PHY_PR_ARG, __entry->ed_level) ); DECLARE_EVENT_CLASS(802154_le16_template, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 le16arg), TP_ARGS(wpan_phy, wpan_dev, le16arg), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(__le16, le16arg) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->le16arg = le16arg; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", pan id: 0x%04x", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __le16_to_cpu(__entry->le16arg)) ); DEFINE_EVENT(802154_le16_template, 802154_rdev_set_pan_id, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 le16arg), TP_ARGS(wpan_phy, wpan_dev, le16arg) ); DEFINE_EVENT_PRINT(802154_le16_template, 802154_rdev_set_short_addr, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 le16arg), TP_ARGS(wpan_phy, wpan_dev, le16arg), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", short addr: 0x%04x", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __le16_to_cpu(__entry->le16arg)) ); TRACE_EVENT(802154_rdev_set_backoff_exponent, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 min_be, u8 max_be), TP_ARGS(wpan_phy, wpan_dev, min_be, max_be), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(u8, min_be) __field(u8, max_be) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->min_be = min_be; __entry->max_be = max_be; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", min be: %d, max be: %d", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->min_be, __entry->max_be) ); TRACE_EVENT(802154_rdev_set_csma_backoffs, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, u8 max_csma_backoffs), TP_ARGS(wpan_phy, wpan_dev, max_csma_backoffs), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(u8, max_csma_backoffs) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->max_csma_backoffs = max_csma_backoffs; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", max csma backoffs: %d", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->max_csma_backoffs) ); TRACE_EVENT(802154_rdev_set_max_frame_retries, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, s8 max_frame_retries), TP_ARGS(wpan_phy, wpan_dev, max_frame_retries), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(s8, max_frame_retries) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->max_frame_retries = max_frame_retries; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", max frame retries: %d", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->max_frame_retries) ); TRACE_EVENT(802154_rdev_set_lbt_mode, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool mode), TP_ARGS(wpan_phy, wpan_dev, mode), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(bool, mode) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->mode = mode; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", lbt mode: %s", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, BOOL_TO_STR(__entry->mode)) ); TRACE_EVENT(802154_rdev_set_ackreq_default, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool ackreq), TP_ARGS(wpan_phy, wpan_dev, ackreq), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(bool, ackreq) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->ackreq = ackreq; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", ackreq default: %s", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, BOOL_TO_STR(__entry->ackreq)) ); TRACE_EVENT(802154_rdev_trigger_scan, TP_PROTO(struct wpan_phy *wpan_phy, struct cfg802154_scan_request *request), TP_ARGS(wpan_phy, request), TP_STRUCT__entry( WPAN_PHY_ENTRY __field(u8, page) __field(u32, channels) __field(u8, duration) ), TP_fast_assign( WPAN_PHY_ASSIGN; __entry->page = request->page; __entry->channels = request->channels; __entry->duration = request->duration; ), TP_printk(WPAN_PHY_PR_FMT ", scan, page: %d, channels: %x, duration %d", WPAN_PHY_PR_ARG, __entry->page, __entry->channels, __entry->duration) ); TRACE_EVENT(802154_rdev_send_beacons, TP_PROTO(struct wpan_phy *wpan_phy, struct cfg802154_beacon_request *request), TP_ARGS(wpan_phy, request), TP_STRUCT__entry( WPAN_PHY_ENTRY __field(u8, interval) ), TP_fast_assign( WPAN_PHY_ASSIGN; __entry->interval = request->interval; ), TP_printk(WPAN_PHY_PR_FMT ", sending beacons (interval order: %d)", WPAN_PHY_PR_ARG, __entry->interval) ); DECLARE_EVENT_CLASS(802154_wdev_template, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev), TP_ARGS(wpan_phy, wpan_dev), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT, WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG) ); DEFINE_EVENT(802154_wdev_template, 802154_rdev_abort_scan, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev), TP_ARGS(wpan_phy, wpan_dev) ); DEFINE_EVENT(802154_wdev_template, 802154_rdev_stop_beacons, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev), TP_ARGS(wpan_phy, wpan_dev) ); TRACE_EVENT(802154_rdev_associate, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, struct ieee802154_addr *coord), TP_ARGS(wpan_phy, wpan_dev, coord), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(__le64, addr) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->addr = coord->extended_addr; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", associating with: 0x%llx", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->addr) ); TRACE_EVENT(802154_rdev_disassociate, TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, struct ieee802154_addr *target), TP_ARGS(wpan_phy, wpan_dev, target), TP_STRUCT__entry( WPAN_PHY_ENTRY WPAN_DEV_ENTRY __field(__le64, addr) ), TP_fast_assign( WPAN_PHY_ASSIGN; WPAN_DEV_ASSIGN; __entry->addr = target->extended_addr; ), TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", disassociating with: 0x%llx", WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->addr) ); TRACE_EVENT(802154_rdev_return_int, TP_PROTO(struct wpan_phy *wpan_phy, int ret), TP_ARGS(wpan_phy, ret), TP_STRUCT__entry( WPAN_PHY_ENTRY __field(int, ret) ), TP_fast_assign( WPAN_PHY_ASSIGN; __entry->ret = ret; ), TP_printk(WPAN_PHY_PR_FMT ", returned: %d", WPAN_PHY_PR_ARG, __entry->ret) ); #endif /* !__RDEV_CFG802154_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 6 6 6 6 6 5 6 6 6 5 6 4 5 6 6 6 6 6 6 5 6 6 5 6 5 6 6 5 5 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /****************************************************************************** * * Module Name: psparse - Parser top level AML parse routines * * Copyright (C) 2000 - 2026, Intel Corp. * *****************************************************************************/ /* * Parse the AML and build an operation tree as most interpreters, * like Perl, do. Parsing is done by hand rather than with a YACC * generated parser to tightly constrain stack and dynamic memory * usage. At the same time, parsing is kept flexible and the code * fairly compact by parsing based on a list of AML opcode * templates in aml_op_info[] */ #include <acpi/acpi.h> #include "accommon.h" #include "acparser.h" #include "acdispat.h" #include "amlcode.h" #include "acinterp.h" #include "acnamesp.h" #define _COMPONENT ACPI_PARSER ACPI_MODULE_NAME("psparse") /******************************************************************************* * * FUNCTION: acpi_ps_get_opcode_size * * PARAMETERS: opcode - An AML opcode * * RETURN: Size of the opcode, in bytes (1 or 2) * * DESCRIPTION: Get the size of the current opcode. * ******************************************************************************/ u32 acpi_ps_get_opcode_size(u32 opcode) { /* Extended (2-byte) opcode if > 255 */ if (opcode > 0x00FF) { return (2); } /* Otherwise, just a single byte opcode */ return (1); } /******************************************************************************* * * FUNCTION: acpi_ps_peek_opcode * * PARAMETERS: parser_state - A parser state object * * RETURN: Next AML opcode * * DESCRIPTION: Get next AML opcode (without incrementing AML pointer) * ******************************************************************************/ u16 acpi_ps_peek_opcode(struct acpi_parse_state * parser_state) { u8 *aml; u16 opcode; aml = parser_state->aml; if (aml >= parser_state->aml_end) { return (0xFFFF); } opcode = (u16) ACPI_GET8(aml); if (opcode == AML_EXTENDED_PREFIX) { /* Extended opcode, get the second opcode byte */ aml++; if (aml >= parser_state->aml_end) { return (0xFFFF); } opcode = (u16) ((opcode << 8) | ACPI_GET8(aml)); } return (opcode); } /******************************************************************************* * * FUNCTION: acpi_ps_complete_this_op * * PARAMETERS: walk_state - Current State * op - Op to complete * * RETURN: Status * * DESCRIPTION: Perform any cleanup at the completion of an Op. * ******************************************************************************/ acpi_status acpi_ps_complete_this_op(struct acpi_walk_state *walk_state, union acpi_parse_object *op) { union acpi_parse_object *prev; union acpi_parse_object *next; const struct acpi_opcode_info *parent_info; union acpi_parse_object *replacement_op = NULL; acpi_status status = AE_OK; ACPI_FUNCTION_TRACE_PTR(ps_complete_this_op, op); /* Check for null Op, can happen if AML code is corrupt */ if (!op) { return_ACPI_STATUS(AE_OK); /* OK for now */ } acpi_ex_stop_trace_opcode(op, walk_state); /* Delete this op and the subtree below it if asked to */ if (((walk_state->parse_flags & ACPI_PARSE_TREE_MASK) != ACPI_PARSE_DELETE_TREE) || (walk_state->op_info->class == AML_CLASS_ARGUMENT)) { return_ACPI_STATUS(AE_OK); } /* Make sure that we only delete this subtree */ if (op->common.parent) { prev = op->common.parent->common.value.arg; if (!prev) { /* Nothing more to do */ goto cleanup; } /* * Check if we need to replace the operator and its subtree * with a return value op (placeholder op) */ parent_info = acpi_ps_get_opcode_info(op->common.parent->common. aml_opcode); switch (parent_info->class) { case AML_CLASS_CONTROL: break; case AML_CLASS_CREATE: /* * These opcodes contain term_arg operands. The current * op must be replaced by a placeholder return op */ replacement_op = acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP, op->common.aml); if (!replacement_op) { status = AE_NO_MEMORY; } break; case AML_CLASS_NAMED_OBJECT: /* * These opcodes contain term_arg operands. The current * op must be replaced by a placeholder return op */ if ((op->common.parent->common.aml_opcode == AML_REGION_OP) || (op->common.parent->common.aml_opcode == AML_DATA_REGION_OP) || (op->common.parent->common.aml_opcode == AML_BUFFER_OP) || (op->common.parent->common.aml_opcode == AML_PACKAGE_OP) || (op->common.parent->common.aml_opcode == AML_BANK_FIELD_OP) || (op->common.parent->common.aml_opcode == AML_VARIABLE_PACKAGE_OP)) { replacement_op = acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP, op->common.aml); if (!replacement_op) { status = AE_NO_MEMORY; } } else if ((op->common.parent->common.aml_opcode == AML_NAME_OP) && (walk_state->pass_number <= ACPI_IMODE_LOAD_PASS2)) { if ((op->common.aml_opcode == AML_BUFFER_OP) || (op->common.aml_opcode == AML_PACKAGE_OP) || (op->common.aml_opcode == AML_VARIABLE_PACKAGE_OP)) { replacement_op = acpi_ps_alloc_op(op->common. aml_opcode, op->common.aml); if (!replacement_op) { status = AE_NO_MEMORY; } else { replacement_op->named.data = op->named.data; replacement_op->named.length = op->named.length; } } } break; default: replacement_op = acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP, op->common.aml); if (!replacement_op) { status = AE_NO_MEMORY; } } /* We must unlink this op from the parent tree */ if (prev == op) { /* This op is the first in the list */ if (replacement_op) { replacement_op->common.parent = op->common.parent; replacement_op->common.value.arg = NULL; replacement_op->common.node = op->common.node; op->common.parent->common.value.arg = replacement_op; replacement_op->common.next = op->common.next; } else { op->common.parent->common.value.arg = op->common.next; } } /* Search the parent list */ else while (prev) { /* Traverse all siblings in the parent's argument list */ next = prev->common.next; if (next == op) { if (replacement_op) { replacement_op->common.parent = op->common.parent; replacement_op->common.value. arg = NULL; replacement_op->common.node = op->common.node; prev->common.next = replacement_op; replacement_op->common.next = op->common.next; next = NULL; } else { prev->common.next = op->common.next; next = NULL; } } prev = next; } } cleanup: /* Now we can actually delete the subtree rooted at Op */ acpi_ps_delete_parse_tree(op); return_ACPI_STATUS(status); } /******************************************************************************* * * FUNCTION: acpi_ps_next_parse_state * * PARAMETERS: walk_state - Current state * op - Current parse op * callback_status - Status from previous operation * * RETURN: Status * * DESCRIPTION: Update the parser state based upon the return exception from * the parser callback. * ******************************************************************************/ acpi_status acpi_ps_next_parse_state(struct acpi_walk_state *walk_state, union acpi_parse_object *op, acpi_status callback_status) { struct acpi_parse_state *parser_state = &walk_state->parser_state; acpi_status status = AE_CTRL_PENDING; u8 *aml; ACPI_FUNCTION_TRACE_PTR(ps_next_parse_state, op); switch (callback_status) { case AE_CTRL_TERMINATE: /* * A control method was terminated via a RETURN statement. * The walk of this method is complete. */ parser_state->aml = parser_state->aml_end; status = AE_CTRL_TERMINATE; break; case AE_CTRL_BREAK: parser_state->aml = walk_state->aml_last_while; walk_state->control_state->common.value = FALSE; status = AE_CTRL_BREAK; break; case AE_CTRL_CONTINUE: parser_state->aml = walk_state->aml_last_while; status = AE_CTRL_CONTINUE; break; case AE_CTRL_PENDING: parser_state->aml = walk_state->aml_last_while; break; #if 0 case AE_CTRL_SKIP: parser_state->aml = parser_state->scope->parse_scope.pkg_end; status = AE_OK; break; #endif case AE_CTRL_TRUE: /* * Predicate of an IF was true, and we are at the matching ELSE. * Just close out this package */ aml = parser_state->aml; parser_state->aml = acpi_ps_get_next_package_end(parser_state); if ((parser_state->aml > parser_state->aml_end) || (parser_state->aml < aml)) { status = AE_AML_PACKAGE_LIMIT; break; } status = AE_CTRL_PENDING; break; case AE_CTRL_FALSE: /* * Either an IF/WHILE Predicate was false or we encountered a BREAK * opcode. In both cases, we do not execute the rest of the * package; We simply close out the parent (finishing the walk of * this branch of the tree) and continue execution at the parent * level. */ parser_state->aml = parser_state->scope->parse_scope.pkg_end; /* In the case of a BREAK, just force a predicate (if any) to FALSE */ walk_state->control_state->common.value = FALSE; status = AE_CTRL_END; break; case AE_CTRL_TRANSFER: /* A method call (invocation) -- transfer control */ status = AE_CTRL_TRANSFER; walk_state->prev_op = op; walk_state->method_call_op = op; walk_state->method_call_node = (op->common.value.arg)->common.node; /* Will return value (if any) be used by the caller? */ walk_state->return_used = acpi_ds_is_result_used(op, walk_state); break; default: status = callback_status; if (ACPI_CNTL_EXCEPTION(callback_status)) { status = AE_OK; } break; } return_ACPI_STATUS(status); } /******************************************************************************* * * FUNCTION: acpi_ps_parse_aml * * PARAMETERS: walk_state - Current state * * * RETURN: Status * * DESCRIPTION: Parse raw AML and return a tree of ops * ******************************************************************************/ acpi_status acpi_ps_parse_aml(struct acpi_walk_state *walk_state) { acpi_status status; struct acpi_thread_state *thread; struct acpi_thread_state *prev_walk_list = acpi_gbl_current_walk_list; struct acpi_walk_state *previous_walk_state; ACPI_FUNCTION_TRACE(ps_parse_aml); ACPI_DEBUG_PRINT((ACPI_DB_PARSE, "Entered with WalkState=%p Aml=%p size=%X\n", walk_state, walk_state->parser_state.aml, walk_state->parser_state.aml_size)); if (!walk_state->parser_state.aml) { return_ACPI_STATUS(AE_BAD_ADDRESS); } /* Create and initialize a new thread state */ thread = acpi_ut_create_thread_state(); if (!thread) { if (walk_state->method_desc) { /* Executing a control method - additional cleanup */ acpi_ds_terminate_control_method(walk_state-> method_desc, walk_state); } acpi_ds_delete_walk_state(walk_state); return_ACPI_STATUS(AE_NO_MEMORY); } walk_state->thread = thread; /* * If executing a method, the starting sync_level is this method's * sync_level */ if (walk_state->method_desc) { walk_state->thread->current_sync_level = walk_state->method_desc->method.sync_level; } acpi_ds_push_walk_state(walk_state, thread); /* * This global allows the AML debugger to get a handle to the currently * executing control method. */ acpi_gbl_current_walk_list = thread; /* * Execute the walk loop as long as there is a valid Walk State. This * handles nested control method invocations without recursion. */ ACPI_DEBUG_PRINT((ACPI_DB_PARSE, "State=%p\n", walk_state)); status = AE_OK; while (walk_state) { if (ACPI_SUCCESS(status)) { /* * The parse_loop executes AML until the method terminates * or calls another method. */ status = acpi_ps_parse_loop(walk_state); } ACPI_DEBUG_PRINT((ACPI_DB_PARSE, "Completed one call to walk loop, %s State=%p\n", acpi_format_exception(status), walk_state)); if (walk_state->method_pathname && walk_state->method_is_nested) { /* Optional object evaluation log */ ACPI_DEBUG_PRINT_RAW((ACPI_DB_EVALUATION, "%-26s: %*s%s\n", " Exit nested method", (walk_state-> method_nesting_depth + 1) * 3, " ", &walk_state->method_pathname[1])); ACPI_FREE(walk_state->method_pathname); walk_state->method_is_nested = FALSE; } if (status == AE_CTRL_TRANSFER) { /* * A method call was detected. * Transfer control to the called control method */ status = acpi_ds_call_control_method(thread, walk_state, NULL); if (ACPI_FAILURE(status)) { status = acpi_ds_method_error(status, walk_state); } /* * If the transfer to the new method method call worked, * a new walk state was created -- get it */ walk_state = acpi_ds_get_current_walk_state(thread); continue; } else if (status == AE_CTRL_TERMINATE) { status = AE_OK; } else if ((status != AE_OK) && (walk_state->method_desc)) { /* Either the method parse or actual execution failed */ acpi_ex_exit_interpreter(); if (status == AE_ABORT_METHOD) { acpi_ns_print_node_pathname(walk_state-> method_node, "Aborting method"); acpi_os_printf("\n"); } else { ACPI_ERROR_METHOD("Aborting method", walk_state->method_node, NULL, status); } acpi_ex_enter_interpreter(); /* Check for possible multi-thread reentrancy problem */ if ((status == AE_ALREADY_EXISTS) && (!(walk_state->method_desc->method.info_flags & ACPI_METHOD_SERIALIZED))) { /* * Method is not serialized and tried to create an object * twice. The probable cause is that the method cannot * handle reentrancy. Mark as "pending serialized" now, and * then mark "serialized" when the last thread exits. */ walk_state->method_desc->method.info_flags |= ACPI_METHOD_SERIALIZED_PENDING; } } /* We are done with this walk, move on to the parent if any */ walk_state = acpi_ds_pop_walk_state(thread); /* Reset the current scope to the beginning of scope stack */ acpi_ds_scope_stack_clear(walk_state); /* * If we just returned from the execution of a control method or if we * encountered an error during the method parse phase, there's lots of * cleanup to do */ if (((walk_state->parse_flags & ACPI_PARSE_MODE_MASK) == ACPI_PARSE_EXECUTE && !(walk_state->parse_flags & ACPI_PARSE_MODULE_LEVEL)) || (ACPI_FAILURE(status))) { acpi_ds_terminate_control_method(walk_state-> method_desc, walk_state); } /* Delete this walk state and all linked control states */ acpi_ps_cleanup_scope(&walk_state->parser_state); previous_walk_state = walk_state; ACPI_DEBUG_PRINT((ACPI_DB_PARSE, "ReturnValue=%p, ImplicitValue=%p State=%p\n", walk_state->return_desc, walk_state->implicit_return_obj, walk_state)); /* Check if we have restarted a preempted walk */ walk_state = acpi_ds_get_current_walk_state(thread); if (walk_state) { if (ACPI_SUCCESS(status)) { /* * There is another walk state, restart it. * If the method return value is not used by the parent, * The object is deleted */ if (!previous_walk_state->return_desc) { /* * In slack mode execution, if there is no return value * we should implicitly return zero (0) as a default value. */ if (acpi_gbl_enable_interpreter_slack && !previous_walk_state-> implicit_return_obj) { previous_walk_state-> implicit_return_obj = acpi_ut_create_integer_object ((u64) 0); if (!previous_walk_state-> implicit_return_obj) { return_ACPI_STATUS (AE_NO_MEMORY); } } /* Restart the calling control method */ status = acpi_ds_restart_control_method (walk_state, previous_walk_state-> implicit_return_obj); } else { /* * We have a valid return value, delete any implicit * return value. */ acpi_ds_clear_implicit_return (previous_walk_state); status = acpi_ds_restart_control_method (walk_state, previous_walk_state->return_desc); } if (ACPI_SUCCESS(status)) { walk_state->walk_type |= ACPI_WALK_METHOD_RESTART; } } else { /* On error, delete any return object or implicit return */ acpi_ut_remove_reference(previous_walk_state-> return_desc); acpi_ds_clear_implicit_return (previous_walk_state); } } /* * Just completed a 1st-level method, save the final internal return * value (if any) */ else if (previous_walk_state->caller_return_desc) { if (previous_walk_state->implicit_return_obj) { *(previous_walk_state->caller_return_desc) = previous_walk_state->implicit_return_obj; } else { /* NULL if no return value */ *(previous_walk_state->caller_return_desc) = previous_walk_state->return_desc; } } else { if (previous_walk_state->return_desc) { /* Caller doesn't want it, must delete it */ acpi_ut_remove_reference(previous_walk_state-> return_desc); } if (previous_walk_state->implicit_return_obj) { /* Caller doesn't want it, must delete it */ acpi_ut_remove_reference(previous_walk_state-> implicit_return_obj); } } acpi_ds_delete_walk_state(previous_walk_state); } /* Normal exit */ acpi_ex_release_all_mutexes(thread); acpi_ut_delete_generic_state(ACPI_CAST_PTR (union acpi_generic_state, thread)); acpi_gbl_current_walk_list = prev_walk_list; return_ACPI_STATUS(status); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 | /* * Copyright (C) 2009 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * For licencing details see kernel-base/COPYING */ #include <linux/dmi.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/export.h> #include <linux/pci.h> #include <linux/acpi.h> #include <linux/sizes.h> #include <asm/acpi.h> #include <asm/bios_ebda.h> #include <asm/paravirt.h> #include <asm/pci_x86.h> #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/apic.h> #include <asm/e820/api.h> #include <asm/time.h> #include <asm/irq.h> #include <asm/io_apic.h> #include <asm/hpet.h> #include <asm/memtype.h> #include <asm/tsc.h> #include <asm/iommu.h> #include <asm/mach_traps.h> #include <asm/irqdomain.h> #include <asm/realmode.h> void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } void get_rtc_noop(struct timespec64 *now) { } static __initconst const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818" }, {} }; /* * Allow devicetree configured systems to disable the RTC by setting the * corresponding DT node's status property to disabled. Code is optimized * out for CONFIG_OF=n builds. */ static __init void x86_wallclock_init(void) { struct device_node *node = of_find_matching_node(NULL, of_cmos_match); if (node && !of_device_is_available(node)) { x86_platform.get_wallclock = get_rtc_noop; x86_platform.set_wallclock = set_rtc_noop; } } /* * The platform setup functions are preset with the default functions * for standard PC hardware. */ struct x86_init_ops x86_init __initdata = { .resources = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, .memory_setup = e820__memory_setup_default, .dmi_setup = dmi_setup, /* Has to be under 1M so we can execute real-mode AP code. */ .realmode_limit = SZ_1M, }, .mpparse = { .setup_ioapic_ids = x86_init_noop, .find_mptable = mpparse_find_mptable, .early_parse_smp_cfg = mpparse_parse_early_smp_config, .parse_smp_cfg = mpparse_parse_smp_config, }, .irqs = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, .intr_mode_select = apic_intr_mode_select, .intr_mode_init = apic_intr_mode_init, .create_pci_msi_domain = native_create_pci_msi_domain, }, .oem = { .arch_setup = x86_init_noop, .banner = default_banner, }, .paging = { .pagetable_init = native_pagetable_init, }, .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, .timer_init = hpet_time_init, .wallclock_init = x86_wallclock_init, }, .iommu = { .iommu_init = iommu_init_noop, }, .pci = { .init = x86_default_pci_init, .init_irq = x86_default_pci_init_irq, .fixup_irqs = x86_default_pci_fixup_irqs, }, .hyper = { .init_platform = x86_init_noop, .guest_late_init = x86_init_noop, .x2apic_available = bool_x86_init_noop, .msi_ext_dest_id = bool_x86_init_noop, .init_mem_mapping = x86_init_noop, .init_after_bootmem = x86_init_noop, }, .acpi = { .set_root_pointer = x86_default_set_root_pointer, .get_root_pointer = x86_default_get_root_pointer, .reduced_hw_early_init = acpi_generic_reduced_hw_init, }, }; struct x86_cpuinit_ops x86_cpuinit = { .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, .parallel_bringup = true, }; static void default_nmi_init(void) { }; static int enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return 0; } static int enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return 0; } static bool enc_tlb_flush_required_noop(bool enc) { return false; } static bool enc_cache_flush_required_noop(void) { return false; } static void enc_kexec_begin_noop(void) {} static void enc_kexec_finish_noop(void) {} static bool is_private_mmio_noop(u64 addr) {return false; } struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu_early, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_cmos_time, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, .get_nmi_reason = default_get_nmi_reason, .save_sched_clock_state = tsc_save_sched_clock_state, .restore_sched_clock_state = tsc_restore_sched_clock_state, .realmode_reserve = reserve_real_mode, .realmode_init = init_real_mode, .hyper.pin_vcpu = x86_op_int_noop, .hyper.is_private_mmio = is_private_mmio_noop, .guest = { .enc_status_change_prepare = enc_status_change_prepare_noop, .enc_status_change_finish = enc_status_change_finish_noop, .enc_tlb_flush_required = enc_tlb_flush_required_noop, .enc_cache_flush_required = enc_cache_flush_required_noop, .enc_kexec_begin = enc_kexec_begin_noop, .enc_kexec_finish = enc_kexec_finish_noop, }, }; EXPORT_SYMBOL_GPL(x86_platform); struct x86_apic_ops x86_apic_ops __ro_after_init = { .io_apic_read = native_io_apic_read, .restore = native_restore_boot_irq_mode, }; |
| 3 3 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KCOV_H #define _LINUX_KCOV_H #include <linux/sched.h> #include <uapi/linux/kcov.h> struct task_struct; #ifdef CONFIG_KCOV enum kcov_mode { /* Coverage collection is not enabled yet. */ KCOV_MODE_DISABLED = 0, /* KCOV was initialized, but tracing mode hasn't been chosen yet. */ KCOV_MODE_INIT = 1, /* * Tracing coverage collection mode. * Covered PCs are collected in a per-task buffer. */ KCOV_MODE_TRACE_PC = 2, /* Collecting comparison operands mode. */ KCOV_MODE_TRACE_CMP = 3, }; #define KCOV_IN_CTXSW (1 << 30) void kcov_task_init(struct task_struct *t); void kcov_task_exit(struct task_struct *t); #define kcov_prepare_switch(t) \ do { \ (t)->kcov_mode |= KCOV_IN_CTXSW; \ } while (0) #define kcov_finish_switch(t) \ do { \ (t)->kcov_mode &= ~KCOV_IN_CTXSW; \ } while (0) /* See Documentation/dev-tools/kcov.rst for usage details. */ void kcov_remote_start(u64 handle); void kcov_remote_stop(void); struct kcov_common_handle_id kcov_common_handle(void); static inline void kcov_remote_start_common(struct kcov_common_handle_id id) { kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_COMMON, id.val)); } static inline void kcov_remote_start_usb(u64 id) { kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_USB, id)); } /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary * work around for kcov's lack of nested remote coverage sections support in * task context. Adding support for nested sections is tracked in: * https://bugzilla.kernel.org/show_bug.cgi?id=210337 */ static inline void kcov_remote_start_usb_softirq(u64 id) { if (in_serving_softirq() && !in_hardirq()) kcov_remote_start_usb(id); } static inline void kcov_remote_stop_softirq(void) { if (in_serving_softirq() && !in_hardirq()) kcov_remote_stop(); } #ifdef CONFIG_64BIT typedef unsigned long kcov_u64; #else typedef unsigned long long kcov_u64; #endif void __sanitizer_cov_trace_pc(void); void __sanitizer_cov_trace_cmp1(u8 arg1, u8 arg2); void __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2); void __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2); void __sanitizer_cov_trace_cmp8(kcov_u64 arg1, kcov_u64 arg2); void __sanitizer_cov_trace_const_cmp1(u8 arg1, u8 arg2); void __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2); void __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2); void __sanitizer_cov_trace_const_cmp8(kcov_u64 arg1, kcov_u64 arg2); void __sanitizer_cov_trace_switch(kcov_u64 val, void *cases); #else static inline void kcov_task_init(struct task_struct *t) {} static inline void kcov_task_exit(struct task_struct *t) {} static inline void kcov_prepare_switch(struct task_struct *t) {} static inline void kcov_finish_switch(struct task_struct *t) {} static inline void kcov_remote_start(u64 handle) {} static inline void kcov_remote_stop(void) {} static inline struct kcov_common_handle_id kcov_common_handle(void) { return (struct kcov_common_handle_id){}; } static inline void kcov_remote_start_common(struct kcov_common_handle_id id) {} static inline void kcov_remote_start_usb(u64 id) {} static inline void kcov_remote_start_usb_softirq(u64 id) {} static inline void kcov_remote_stop_softirq(void) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ |
| 4329 3900 805 13280 5578 6260 456 638 11 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 | // SPDX-License-Identifier: GPL-2.0-only /* * Netlink message type permission tables, for user generated messages. * * Author: James Morris <jmorris@redhat.com> * * Copyright (C) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> #include <linux/if.h> #include <linux/inet_diag.h> #include <linux/xfrm.h> #include <linux/audit.h> #include <linux/sock_diag.h> #include "flask.h" #include "av_permissions.h" #include "security.h" struct nlmsg_perm { u16 nlmsg_type; u32 perm; }; static const struct nlmsg_perm nlmsg_route_perms[] = { { RTM_NEWLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETLINK, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_SETLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_NEWADDR, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELADDR, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETADDR, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWROUTE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELROUTE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETROUTE, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWNEIGH, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNEIGH, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETNEIGH, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWRULE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELRULE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETRULE, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWQDISC, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELQDISC, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETQDISC, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWTCLASS, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELTCLASS, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETTCLASS, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWTFILTER, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELTFILTER, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETTFILTER, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWACTION, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELACTION, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETACTION, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWPREFIX, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETMULTICAST, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETANYCAST, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_SETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_NEWADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETDCB, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_SETDCB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_NEWNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWMDB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELMDB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETMDB, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWNSID, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNSID, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETNSID, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_SETSTATS, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_NEWCACHEREPORT, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_NEWVLAN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELVLAN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETVLAN, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, }; static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = { { TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ }, { SOCK_DIAG_BY_FAMILY, NETLINK_TCPDIAG_SOCKET__NLMSG_READ }, { SOCK_DESTROY, NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE }, }; static const struct nlmsg_perm nlmsg_xfrm_perms[] = { { XFRM_MSG_NEWSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_DELSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETSA, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_NEWPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_DELPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETPOLICY, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_ALLOCSPI, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_ACQUIRE, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_EXPIRE, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_UPDPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_UPDSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_POLEXPIRE, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_FLUSHSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_FLUSHPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_NEWAE, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETAE, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_REPORT, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_MIGRATE, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_NEWSADINFO, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_GETSADINFO, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_NEWSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_MAPPING, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_SETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_MIGRATE_STATE, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, }; static const struct nlmsg_perm nlmsg_audit_perms[] = { { AUDIT_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ }, { AUDIT_SET, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_LIST, NETLINK_AUDIT_SOCKET__NLMSG_READPRIV }, { AUDIT_ADD, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_DEL, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_LIST_RULES, NETLINK_AUDIT_SOCKET__NLMSG_READPRIV }, { AUDIT_ADD_RULE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_DEL_RULE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_USER, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, { AUDIT_SIGNAL_INFO, NETLINK_AUDIT_SOCKET__NLMSG_READ }, { AUDIT_TRIM, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_MAKE_EQUIV, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_TTY_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ }, { AUDIT_TTY_SET, NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT }, { AUDIT_GET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_READ }, { AUDIT_SET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, }; static int nlmsg_perm(u16 nlmsg_type, u32 *perm, const struct nlmsg_perm *tab, size_t tabsize) { unsigned int i; int err = -EINVAL; for (i = 0; i < tabsize / sizeof(struct nlmsg_perm); i++) if (nlmsg_type == tab[i].nlmsg_type) { *perm = tab[i].perm; err = 0; break; } return err; } int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) { /* While it is possible to add a similar permission to other netlink * classes, note that the extended permission value is matched against * the nlmsg_type field. Notably, SECCLASS_NETLINK_GENERIC_SOCKET uses * dynamic values for this field, which means that it cannot be added * as-is. */ switch (sclass) { case SECCLASS_NETLINK_ROUTE_SOCKET: /* RTM_MAX always points to RTM_SETxxxx, ie RTM_NEWxxx + 3. * If the BUILD_BUG_ON() below fails you must update the * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ BUILD_BUG_ON(RTM_MAX != (RTM_NEWTUNNEL + 3)); if (selinux_policycap_netlink_xperm()) { *perm = NETLINK_ROUTE_SOCKET__NLMSG; return 0; } return nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms, sizeof(nlmsg_route_perms)); break; case SECCLASS_NETLINK_TCPDIAG_SOCKET: if (selinux_policycap_netlink_xperm()) { *perm = NETLINK_TCPDIAG_SOCKET__NLMSG; return 0; } return nlmsg_perm(nlmsg_type, perm, nlmsg_tcpdiag_perms, sizeof(nlmsg_tcpdiag_perms)); break; case SECCLASS_NETLINK_XFRM_SOCKET: /* If the BUILD_BUG_ON() below fails you must update the * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_MIGRATE_STATE); if (selinux_policycap_netlink_xperm()) { *perm = NETLINK_XFRM_SOCKET__NLMSG; return 0; } return nlmsg_perm(nlmsg_type, perm, nlmsg_xfrm_perms, sizeof(nlmsg_xfrm_perms)); break; case SECCLASS_NETLINK_AUDIT_SOCKET: if (selinux_policycap_netlink_xperm()) { *perm = NETLINK_AUDIT_SOCKET__NLMSG; return 0; } else if ((nlmsg_type >= AUDIT_FIRST_USER_MSG && nlmsg_type <= AUDIT_LAST_USER_MSG) || (nlmsg_type >= AUDIT_FIRST_USER_MSG2 && nlmsg_type <= AUDIT_LAST_USER_MSG2)) { *perm = NETLINK_AUDIT_SOCKET__NLMSG_RELAY; return 0; } return nlmsg_perm(nlmsg_type, perm, nlmsg_audit_perms, sizeof(nlmsg_audit_perms)); break; } /* No messaging from userspace, or class unknown/unhandled */ return -ENOENT; } |
| 1 2 2 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /******************************************************************************* * Filename: target_core_alua.c * * This file contains SPC-3 compliant asymmetric logical unit assigntment (ALUA) * * (c) Copyright 2009-2013 Datera, Inc. * * Nicholas A. Bellinger <nab@kernel.org> * ******************************************************************************/ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/configfs.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/fs_struct.h> #include <linux/kthread.h> #include <scsi/scsi_proto.h> #include <linux/unaligned.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> #include <target/target_core_fabric.h> #include "target_core_internal.h" #include "target_core_alua.h" #include "target_core_ua.h" static sense_reason_t core_alua_check_transition(int state, int valid, int *primary, int explicit); static int core_alua_set_tg_pt_secondary_state( struct se_lun *lun, int explicit, int offline); static char *core_alua_dump_state(int state); static void __target_attach_tg_pt_gp(struct se_lun *lun, struct t10_alua_tg_pt_gp *tg_pt_gp); static u16 alua_lu_gps_counter; static u32 alua_lu_gps_count; static DEFINE_SPINLOCK(lu_gps_lock); static LIST_HEAD(lu_gps_list); struct t10_alua_lu_gp *default_lu_gp; /* * REPORT REFERRALS * * See sbc3r35 section 5.23 */ sense_reason_t target_emulate_report_referrals(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct t10_alua_lba_map *map; struct t10_alua_lba_map_member *map_mem; unsigned char *buf; u32 rd_len = 0, off; if (cmd->data_length < 4) { pr_warn("REPORT REFERRALS allocation length %u too" " small\n", cmd->data_length); return TCM_INVALID_CDB_FIELD; } buf = transport_kmap_data_sg(cmd); if (!buf) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; off = 4; spin_lock(&dev->t10_alua.lba_map_lock); if (list_empty(&dev->t10_alua.lba_map_list)) { spin_unlock(&dev->t10_alua.lba_map_lock); transport_kunmap_data_sg(cmd); return TCM_UNSUPPORTED_SCSI_OPCODE; } list_for_each_entry(map, &dev->t10_alua.lba_map_list, lba_map_list) { int desc_num = off + 3; int pg_num; off += 4; if (cmd->data_length > off) put_unaligned_be64(map->lba_map_first_lba, &buf[off]); off += 8; if (cmd->data_length > off) put_unaligned_be64(map->lba_map_last_lba, &buf[off]); off += 8; rd_len += 20; pg_num = 0; list_for_each_entry(map_mem, &map->lba_map_mem_list, lba_map_mem_list) { int alua_state = map_mem->lba_map_mem_alua_state; int alua_pg_id = map_mem->lba_map_mem_alua_pg_id; if (cmd->data_length > off) buf[off] = alua_state & 0x0f; off += 2; if (cmd->data_length > off) buf[off] = (alua_pg_id >> 8) & 0xff; off++; if (cmd->data_length > off) buf[off] = (alua_pg_id & 0xff); off++; rd_len += 4; pg_num++; } if (cmd->data_length > desc_num) buf[desc_num] = pg_num; } spin_unlock(&dev->t10_alua.lba_map_lock); /* * Set the RETURN DATA LENGTH set in the header of the DataIN Payload */ put_unaligned_be16(rd_len, &buf[2]); transport_kunmap_data_sg(cmd); target_complete_cmd(cmd, SAM_STAT_GOOD); return 0; } /* * REPORT_TARGET_PORT_GROUPS * * See spc4r17 section 6.27 */ sense_reason_t target_emulate_report_target_port_groups(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct t10_alua_tg_pt_gp *tg_pt_gp; struct se_lun *lun; unsigned char *buf; u32 rd_len = 0, off; int ext_hdr = (cmd->t_task_cdb[1] & 0x20); /* * Skip over RESERVED area to first Target port group descriptor * depending on the PARAMETER DATA FORMAT type.. */ if (ext_hdr != 0) off = 8; else off = 4; if (cmd->data_length < off) { pr_warn("REPORT TARGET PORT GROUPS allocation length %u too" " small for %s header\n", cmd->data_length, (ext_hdr) ? "extended" : "normal"); return TCM_INVALID_CDB_FIELD; } buf = transport_kmap_data_sg(cmd); if (!buf) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; spin_lock(&dev->t10_alua.tg_pt_gps_lock); list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list, tg_pt_gp_list) { /* Skip empty port groups */ if (!tg_pt_gp->tg_pt_gp_members) continue; /* * Check if the Target port group and Target port descriptor list * based on tg_pt_gp_members count will fit into the response payload. * Otherwise, bump rd_len to let the initiator know we have exceeded * the allocation length and the response is truncated. */ if ((off + 8 + (tg_pt_gp->tg_pt_gp_members * 4)) > cmd->data_length) { rd_len += 8 + (tg_pt_gp->tg_pt_gp_members * 4); continue; } /* * PREF: Preferred target port bit, determine if this * bit should be set for port group. */ if (tg_pt_gp->tg_pt_gp_pref) buf[off] = 0x80; /* * Set the ASYMMETRIC ACCESS State */ buf[off++] |= tg_pt_gp->tg_pt_gp_alua_access_state & 0xff; /* * Set supported ASYMMETRIC ACCESS State bits */ buf[off++] |= tg_pt_gp->tg_pt_gp_alua_supported_states; /* * TARGET PORT GROUP */ put_unaligned_be16(tg_pt_gp->tg_pt_gp_id, &buf[off]); off += 2; off++; /* Skip over Reserved */ /* * STATUS CODE */ buf[off++] = (tg_pt_gp->tg_pt_gp_alua_access_status & 0xff); /* * Vendor Specific field */ buf[off++] = 0x00; /* * TARGET PORT COUNT */ buf[off++] = (tg_pt_gp->tg_pt_gp_members & 0xff); rd_len += 8; spin_lock(&tg_pt_gp->tg_pt_gp_lock); list_for_each_entry(lun, &tg_pt_gp->tg_pt_gp_lun_list, lun_tg_pt_gp_link) { /* * Start Target Port descriptor format * * See spc4r17 section 6.2.7 Table 247 */ off += 2; /* Skip over Obsolete */ /* * Set RELATIVE TARGET PORT IDENTIFIER */ put_unaligned_be16(lun->lun_tpg->tpg_rtpi, &buf[off]); off += 2; rd_len += 4; } spin_unlock(&tg_pt_gp->tg_pt_gp_lock); } spin_unlock(&dev->t10_alua.tg_pt_gps_lock); /* * Set the RETURN DATA LENGTH set in the header of the DataIN Payload */ put_unaligned_be32(rd_len, &buf[0]); /* * Fill in the Extended header parameter data format if requested */ if (ext_hdr != 0) { buf[4] = 0x10; /* * Set the implicit transition time (in seconds) for the application * client to use as a base for it's transition timeout value. * * Use the current tg_pt_gp_mem -> tg_pt_gp membership from the LUN * this CDB was received upon to determine this value individually * for ALUA target port group. */ rcu_read_lock(); tg_pt_gp = rcu_dereference(cmd->se_lun->lun_tg_pt_gp); if (tg_pt_gp) buf[5] = tg_pt_gp->tg_pt_gp_implicit_trans_secs; rcu_read_unlock(); } transport_kunmap_data_sg(cmd); target_complete_cmd_with_length(cmd, SAM_STAT_GOOD, rd_len + 4); return 0; } /* * SET_TARGET_PORT_GROUPS for explicit ALUA operation. * * See spc4r17 section 6.35 */ sense_reason_t target_emulate_set_target_port_groups(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct se_lun *l_lun = cmd->se_lun; struct se_node_acl *nacl = cmd->se_sess->se_node_acl; struct t10_alua_tg_pt_gp *tg_pt_gp = NULL, *l_tg_pt_gp; unsigned char *buf; unsigned char *ptr; sense_reason_t rc = TCM_NO_SENSE; u32 len = 4; /* Skip over RESERVED area in header */ int alua_access_state, primary = 0, valid_states; u16 tg_pt_id, rtpi; if (cmd->data_length < 4) { pr_warn("SET TARGET PORT GROUPS parameter list length %u too" " small\n", cmd->data_length); return TCM_INVALID_PARAMETER_LIST; } buf = transport_kmap_data_sg(cmd); if (!buf) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; /* * Determine if explicit ALUA via SET_TARGET_PORT_GROUPS is allowed * for the local tg_pt_gp. */ rcu_read_lock(); l_tg_pt_gp = rcu_dereference(l_lun->lun_tg_pt_gp); if (!l_tg_pt_gp) { rcu_read_unlock(); pr_err("Unable to access l_lun->tg_pt_gp\n"); rc = TCM_UNSUPPORTED_SCSI_OPCODE; goto out; } if (!(l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA)) { rcu_read_unlock(); pr_debug("Unable to process SET_TARGET_PORT_GROUPS" " while TPGS_EXPLICIT_ALUA is disabled\n"); rc = TCM_UNSUPPORTED_SCSI_OPCODE; goto out; } valid_states = l_tg_pt_gp->tg_pt_gp_alua_supported_states; rcu_read_unlock(); ptr = &buf[4]; /* Skip over RESERVED area in header */ while (len < cmd->data_length) { bool found = false; alua_access_state = (ptr[0] & 0x0f); /* * Check the received ALUA access state, and determine if * the state is a primary or secondary target port asymmetric * access state. */ rc = core_alua_check_transition(alua_access_state, valid_states, &primary, 1); if (rc) { /* * If the SET TARGET PORT GROUPS attempts to establish * an invalid combination of target port asymmetric * access states or attempts to establish an * unsupported target port asymmetric access state, * then the command shall be terminated with CHECK * CONDITION status, with the sense key set to ILLEGAL * REQUEST, and the additional sense code set to INVALID * FIELD IN PARAMETER LIST. */ goto out; } /* * If the ASYMMETRIC ACCESS STATE field (see table 267) * specifies a primary target port asymmetric access state, * then the TARGET PORT GROUP OR TARGET PORT field specifies * a primary target port group for which the primary target * port asymmetric access state shall be changed. If the * ASYMMETRIC ACCESS STATE field specifies a secondary target * port asymmetric access state, then the TARGET PORT GROUP OR * TARGET PORT field specifies the relative target port * identifier (see 3.1.120) of the target port for which the * secondary target port asymmetric access state shall be * changed. */ if (primary) { tg_pt_id = get_unaligned_be16(ptr + 2); /* * Locate the matching target port group ID from * the global tg_pt_gp list */ spin_lock(&dev->t10_alua.tg_pt_gps_lock); list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list, tg_pt_gp_list) { if (!tg_pt_gp->tg_pt_gp_valid_id) continue; if (tg_pt_id != tg_pt_gp->tg_pt_gp_id) continue; atomic_inc_mb(&tg_pt_gp->tg_pt_gp_ref_cnt); spin_unlock(&dev->t10_alua.tg_pt_gps_lock); if (!core_alua_do_port_transition(tg_pt_gp, dev, l_lun, nacl, alua_access_state, 1)) found = true; spin_lock(&dev->t10_alua.tg_pt_gps_lock); atomic_dec_mb(&tg_pt_gp->tg_pt_gp_ref_cnt); break; } spin_unlock(&dev->t10_alua.tg_pt_gps_lock); } else { struct se_lun *lun; /* * Extract the RELATIVE TARGET PORT IDENTIFIER to identify * the Target Port in question for the incoming * SET_TARGET_PORT_GROUPS op. */ rtpi = get_unaligned_be16(ptr + 2); /* * Locate the matching relative target port identifier * for the struct se_device storage object. */ spin_lock(&dev->se_port_lock); list_for_each_entry(lun, &dev->dev_sep_list, lun_dev_link) { if (lun->lun_tpg->tpg_rtpi != rtpi) continue; // XXX: racy unlock spin_unlock(&dev->se_port_lock); if (!core_alua_set_tg_pt_secondary_state( lun, 1, 1)) found = true; spin_lock(&dev->se_port_lock); break; } spin_unlock(&dev->se_port_lock); } if (!found) { rc = TCM_INVALID_PARAMETER_LIST; goto out; } ptr += 4; len += 4; } out: transport_kunmap_data_sg(cmd); if (!rc) target_complete_cmd(cmd, SAM_STAT_GOOD); return rc; } static inline void core_alua_state_nonoptimized( struct se_cmd *cmd, unsigned char *cdb, int nonop_delay_msecs) { /* * Set SCF_ALUA_NON_OPTIMIZED here, this value will be checked * later to determine if processing of this cmd needs to be * temporarily delayed for the Active/NonOptimized primary access state. */ cmd->se_cmd_flags |= SCF_ALUA_NON_OPTIMIZED; cmd->alua_nonop_delay = nonop_delay_msecs; } static inline sense_reason_t core_alua_state_lba_dependent( struct se_cmd *cmd, u16 tg_pt_gp_id) { struct se_device *dev = cmd->se_dev; u64 segment_size, segment_mult, sectors, lba; /* Only need to check for cdb actually containing LBAs */ if (!(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB)) return 0; spin_lock(&dev->t10_alua.lba_map_lock); segment_size = dev->t10_alua.lba_map_segment_size; segment_mult = dev->t10_alua.lba_map_segment_multiplier; sectors = cmd->data_length / dev->dev_attrib.block_size; lba = cmd->t_task_lba; while (lba < cmd->t_task_lba + sectors) { struct t10_alua_lba_map *cur_map = NULL, *map; struct t10_alua_lba_map_member *map_mem; list_for_each_entry(map, &dev->t10_alua.lba_map_list, lba_map_list) { u64 start_lba, last_lba; u64 first_lba = map->lba_map_first_lba; if (segment_mult) { u64 tmp = lba; start_lba = do_div(tmp, segment_size * segment_mult); last_lba = first_lba + segment_size - 1; if (start_lba >= first_lba && start_lba <= last_lba) { lba += segment_size; cur_map = map; break; } } else { last_lba = map->lba_map_last_lba; if (lba >= first_lba && lba <= last_lba) { lba = last_lba + 1; cur_map = map; break; } } } if (!cur_map) { spin_unlock(&dev->t10_alua.lba_map_lock); return TCM_ALUA_TG_PT_UNAVAILABLE; } list_for_each_entry(map_mem, &cur_map->lba_map_mem_list, lba_map_mem_list) { if (map_mem->lba_map_mem_alua_pg_id != tg_pt_gp_id) continue; switch(map_mem->lba_map_mem_alua_state) { case ALUA_ACCESS_STATE_STANDBY: spin_unlock(&dev->t10_alua.lba_map_lock); return TCM_ALUA_TG_PT_STANDBY; case ALUA_ACCESS_STATE_UNAVAILABLE: spin_unlock(&dev->t10_alua.lba_map_lock); return TCM_ALUA_TG_PT_UNAVAILABLE; default: break; } } } spin_unlock(&dev->t10_alua.lba_map_lock); return 0; } static inline sense_reason_t core_alua_state_standby( struct se_cmd *cmd, unsigned char *cdb) { /* * Allowed CDBs for ALUA_ACCESS_STATE_STANDBY as defined by * spc4r17 section 5.9.2.4.4 */ switch (cdb[0]) { case INQUIRY: case LOG_SELECT: case LOG_SENSE: case MODE_SELECT: case MODE_SENSE: case REPORT_LUNS: case RECEIVE_DIAGNOSTIC: case SEND_DIAGNOSTIC: case READ_CAPACITY: return 0; case SERVICE_ACTION_IN_16: switch (cdb[1] & 0x1f) { case SAI_READ_CAPACITY_16: return 0; default: return TCM_ALUA_TG_PT_STANDBY; } case MAINTENANCE_IN: switch (cdb[1] & 0x1f) { case MI_REPORT_TARGET_PGS: return 0; default: return TCM_ALUA_TG_PT_STANDBY; } case MAINTENANCE_OUT: switch (cdb[1]) { case MO_SET_TARGET_PGS: return 0; default: return TCM_ALUA_TG_PT_STANDBY; } case REQUEST_SENSE: case PERSISTENT_RESERVE_IN: case PERSISTENT_RESERVE_OUT: case READ_BUFFER: case WRITE_BUFFER: return 0; default: return TCM_ALUA_TG_PT_STANDBY; } return 0; } static inline sense_reason_t core_alua_state_unavailable( struct se_cmd *cmd, unsigned char *cdb) { /* * Allowed CDBs for ALUA_ACCESS_STATE_UNAVAILABLE as defined by * spc4r17 section 5.9.2.4.5 */ switch (cdb[0]) { case INQUIRY: case REPORT_LUNS: return 0; case MAINTENANCE_IN: switch (cdb[1] & 0x1f) { case MI_REPORT_TARGET_PGS: return 0; default: return TCM_ALUA_TG_PT_UNAVAILABLE; } case MAINTENANCE_OUT: switch (cdb[1]) { case MO_SET_TARGET_PGS: return 0; default: return TCM_ALUA_TG_PT_UNAVAILABLE; } case REQUEST_SENSE: case READ_BUFFER: case WRITE_BUFFER: return 0; default: return TCM_ALUA_TG_PT_UNAVAILABLE; } return 0; } static inline sense_reason_t core_alua_state_transition( struct se_cmd *cmd, unsigned char *cdb) { /* * Allowed CDBs for ALUA_ACCESS_STATE_TRANSITION as defined by * spc4r17 section 5.9.2.5 */ switch (cdb[0]) { case INQUIRY: case REPORT_LUNS: return 0; case MAINTENANCE_IN: switch (cdb[1] & 0x1f) { case MI_REPORT_TARGET_PGS: return 0; default: return TCM_ALUA_STATE_TRANSITION; } case REQUEST_SENSE: case READ_BUFFER: case WRITE_BUFFER: return 0; default: return TCM_ALUA_STATE_TRANSITION; } return 0; } /* * return 1: Is used to signal LUN not accessible, and check condition/not ready * return 0: Used to signal success * return -1: Used to signal failure, and invalid cdb field */ sense_reason_t target_alua_state_check(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; unsigned char *cdb = cmd->t_task_cdb; struct se_lun *lun = cmd->se_lun; struct t10_alua_tg_pt_gp *tg_pt_gp; int out_alua_state, nonop_delay_msecs; u16 tg_pt_gp_id; sense_reason_t rc = TCM_NO_SENSE; if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE) return 0; if (dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA) return 0; /* * First, check for a struct se_port specific secondary ALUA target port * access state: OFFLINE */ if (atomic_read(&lun->lun_tg_pt_secondary_offline)) { pr_debug("ALUA: Got secondary offline status for local" " target port\n"); return TCM_ALUA_OFFLINE; } rcu_read_lock(); tg_pt_gp = rcu_dereference(lun->lun_tg_pt_gp); if (!tg_pt_gp) { rcu_read_unlock(); return 0; } out_alua_state = tg_pt_gp->tg_pt_gp_alua_access_state; nonop_delay_msecs = tg_pt_gp->tg_pt_gp_nonop_delay_msecs; tg_pt_gp_id = tg_pt_gp->tg_pt_gp_id; rcu_read_unlock(); /* * Process ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED in a separate conditional * statement so the compiler knows explicitly to check this case first. * For the Optimized ALUA access state case, we want to process the * incoming fabric cmd ASAP.. */ if (out_alua_state == ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED) return 0; switch (out_alua_state) { case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED: core_alua_state_nonoptimized(cmd, cdb, nonop_delay_msecs); break; case ALUA_ACCESS_STATE_STANDBY: rc = core_alua_state_standby(cmd, cdb); break; case ALUA_ACCESS_STATE_UNAVAILABLE: rc = core_alua_state_unavailable(cmd, cdb); break; case ALUA_ACCESS_STATE_TRANSITION: rc = core_alua_state_transition(cmd, cdb); break; case ALUA_ACCESS_STATE_LBA_DEPENDENT: rc = core_alua_state_lba_dependent(cmd, tg_pt_gp_id); break; /* * OFFLINE is a secondary ALUA target port group access state, that is * handled above with struct se_lun->lun_tg_pt_secondary_offline=1 */ case ALUA_ACCESS_STATE_OFFLINE: default: pr_err("Unknown ALUA access state: 0x%02x\n", out_alua_state); rc = TCM_INVALID_CDB_FIELD; } if (rc && rc != TCM_INVALID_CDB_FIELD) { pr_debug("[%s]: ALUA TG Port not available, " "SenseKey: NOT_READY, ASC/rc: 0x04/%d\n", cmd->se_tfo->fabric_name, rc); } return rc; } /* * Check implicit and explicit ALUA state change request. */ static sense_reason_t core_alua_check_transition(int state, int valid, int *primary, int explicit) { /* * OPTIMIZED, NON-OPTIMIZED, STANDBY and UNAVAILABLE are * defined as primary target port asymmetric access states. */ switch (state) { case ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED: if (!(valid & ALUA_AO_SUP)) goto not_supported; *primary = 1; break; case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED: if (!(valid & ALUA_AN_SUP)) goto not_supported; *primary = 1; break; case ALUA_ACCESS_STATE_STANDBY: if (!(valid & ALUA_S_SUP)) goto not_supported; *primary = 1; break; case ALUA_ACCESS_STATE_UNAVAILABLE: if (!(valid & ALUA_U_SUP)) goto not_supported; *primary = 1; break; case ALUA_ACCESS_STATE_LBA_DEPENDENT: if (!(valid & ALUA_LBD_SUP)) goto not_supported; *primary = 1; break; case ALUA_ACCESS_STATE_OFFLINE: /* * OFFLINE state is defined as a secondary target port * asymmetric access state. */ if (!(valid & ALUA_O_SUP)) goto not_supported; *primary = 0; break; case ALUA_ACCESS_STATE_TRANSITION: if (!(valid & ALUA_T_SUP) || explicit) /* * Transitioning is set internally and by tcmu daemon, * and cannot be selected through a STPG. */ goto not_supported; *primary = 0; break; default: pr_err("Unknown ALUA access state: 0x%02x\n", state); return TCM_INVALID_PARAMETER_LIST; } return 0; not_supported: pr_err("ALUA access state %s not supported", core_alua_dump_state(state)); return TCM_INVALID_PARAMETER_LIST; } static char *core_alua_dump_state(int state) { switch (state) { case ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED: return "Active/Optimized"; case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED: return "Active/NonOptimized"; case ALUA_ACCESS_STATE_LBA_DEPENDENT: return "LBA Dependent"; case ALUA_ACCESS_STATE_STANDBY: return "Standby"; case ALUA_ACCESS_STATE_UNAVAILABLE: return "Unavailable"; case ALUA_ACCESS_STATE_OFFLINE: return "Offline"; case ALUA_ACCESS_STATE_TRANSITION: return "Transitioning"; default: return "Unknown"; } return NULL; } char *core_alua_dump_status(int status) { switch (status) { case ALUA_STATUS_NONE: return "None"; case ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG: return "Altered by Explicit STPG"; case ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA: return "Altered by Implicit ALUA"; default: return "Unknown"; } return NULL; } /* * Used by fabric modules to determine when we need to delay processing * for the Active/NonOptimized paths.. */ int core_alua_check_nonop_delay( struct se_cmd *cmd) { if (!(cmd->se_cmd_flags & SCF_ALUA_NON_OPTIMIZED)) return 0; /* * The ALUA Active/NonOptimized access state delay can be disabled * in via configfs with a value of zero */ if (!cmd->alua_nonop_delay) return 0; /* * struct se_cmd->alua_nonop_delay gets set by a target port group * defined interval in core_alua_state_nonoptimized() */ msleep_interruptible(cmd->alua_nonop_delay); return 0; } static int core_alua_write_tpg_metadata( const char *path, unsigned char *md_buf, u32 md_buf_len) { struct file *file; loff_t pos = 0; int ret; if (tsk_is_kthread(current)) { scoped_with_init_fs() file = filp_open(path, O_RDWR | O_CREAT | O_TRUNC, 0600); } else { file = filp_open(path, O_RDWR | O_CREAT | O_TRUNC, 0600); } if (IS_ERR(file)) { pr_err("filp_open(%s) for ALUA metadata failed\n", path); return -ENODEV; } ret = kernel_write(file, md_buf, md_buf_len, &pos); if (ret < 0) pr_err("Error writing ALUA metadata file: %s\n", path); fput(file); return (ret < 0) ? -EIO : 0; } static int core_alua_update_tpg_primary_metadata( struct t10_alua_tg_pt_gp *tg_pt_gp) { unsigned char *md_buf; struct t10_wwn *wwn = &tg_pt_gp->tg_pt_gp_dev->t10_wwn; char *path; int len, rc; lockdep_assert_held(&tg_pt_gp->tg_pt_gp_transition_mutex); md_buf = kzalloc(ALUA_MD_BUF_LEN, GFP_KERNEL); if (!md_buf) { pr_err("Unable to allocate buf for ALUA metadata\n"); return -ENOMEM; } len = snprintf(md_buf, ALUA_MD_BUF_LEN, "tg_pt_gp_id=%hu\n" "alua_access_state=0x%02x\n" "alua_access_status=0x%02x\n", tg_pt_gp->tg_pt_gp_id, tg_pt_gp->tg_pt_gp_alua_access_state, tg_pt_gp->tg_pt_gp_alua_access_status); rc = -ENOMEM; path = kasprintf(GFP_KERNEL, "%s/alua/tpgs_%s/%s", db_root, &wwn->unit_serial[0], config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item)); if (path) { rc = core_alua_write_tpg_metadata(path, md_buf, len); kfree(path); } kfree(md_buf); return rc; } static void core_alua_queue_state_change_ua(struct t10_alua_tg_pt_gp *tg_pt_gp) { struct se_dev_entry *se_deve; struct se_lun *lun; struct se_lun_acl *lacl; spin_lock(&tg_pt_gp->tg_pt_gp_lock); list_for_each_entry(lun, &tg_pt_gp->tg_pt_gp_lun_list, lun_tg_pt_gp_link) { /* * After an implicit target port asymmetric access state * change, a device server shall establish a unit attention * condition for the initiator port associated with every I_T * nexus with the additional sense code set to ASYMMETRIC * ACCESS STATE CHANGED. * * After an explicit target port asymmetric access state * change, a device server shall establish a unit attention * condition with the additional sense code set to ASYMMETRIC * ACCESS STATE CHANGED for the initiator port associated with * every I_T nexus other than the I_T nexus on which the SET * TARGET PORT GROUPS command */ if (!percpu_ref_tryget_live(&lun->lun_ref)) continue; spin_unlock(&tg_pt_gp->tg_pt_gp_lock); spin_lock(&lun->lun_deve_lock); list_for_each_entry(se_deve, &lun->lun_deve_list, lun_link) { lacl = se_deve->se_lun_acl; /* * spc4r37 p.242: * After an explicit target port asymmetric access * state change, a device server shall establish a * unit attention condition with the additional sense * code set to ASYMMETRIC ACCESS STATE CHANGED for * the initiator port associated with every I_T nexus * other than the I_T nexus on which the SET TARGET * PORT GROUPS command was received. */ if ((tg_pt_gp->tg_pt_gp_alua_access_status == ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) && (tg_pt_gp->tg_pt_gp_alua_lun != NULL) && (tg_pt_gp->tg_pt_gp_alua_lun == lun)) continue; /* * se_deve->se_lun_acl pointer may be NULL for a * entry created without explicit Node+MappedLUN ACLs */ if (lacl && (tg_pt_gp->tg_pt_gp_alua_nacl != NULL) && (tg_pt_gp->tg_pt_gp_alua_nacl == lacl->se_lun_nacl)) continue; core_scsi3_ua_allocate(se_deve, 0x2A, ASCQ_2AH_ASYMMETRIC_ACCESS_STATE_CHANGED); } spin_unlock(&lun->lun_deve_lock); spin_lock(&tg_pt_gp->tg_pt_gp_lock); percpu_ref_put(&lun->lun_ref); } spin_unlock(&tg_pt_gp->tg_pt_gp_lock); } static int core_alua_do_transition_tg_pt( struct t10_alua_tg_pt_gp *tg_pt_gp, int new_state, int explicit) { int prev_state; mutex_lock(&tg_pt_gp->tg_pt_gp_transition_mutex); /* Nothing to be done here */ if (tg_pt_gp->tg_pt_gp_alua_access_state == new_state) { mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return 0; } if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION) { mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return -EAGAIN; } /* * Save the old primary ALUA access state, and set the current state * to ALUA_ACCESS_STATE_TRANSITION. */ prev_state = tg_pt_gp->tg_pt_gp_alua_access_state; tg_pt_gp->tg_pt_gp_alua_access_state = ALUA_ACCESS_STATE_TRANSITION; tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ? ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG : ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA; core_alua_queue_state_change_ua(tg_pt_gp); if (new_state == ALUA_ACCESS_STATE_TRANSITION) { mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return 0; } /* * Check for the optional ALUA primary state transition delay */ if (tg_pt_gp->tg_pt_gp_trans_delay_msecs != 0) msleep_interruptible(tg_pt_gp->tg_pt_gp_trans_delay_msecs); /* * Set the current primary ALUA access state to the requested new state */ tg_pt_gp->tg_pt_gp_alua_access_state = new_state; /* * Update the ALUA metadata buf that has been allocated in * core_alua_do_port_transition(), this metadata will be written * to struct file. * * Note that there is the case where we do not want to update the * metadata when the saved metadata is being parsed in userspace * when setting the existing port access state and access status. * * Also note that the failure to write out the ALUA metadata to * struct file does NOT affect the actual ALUA transition. */ if (tg_pt_gp->tg_pt_gp_write_metadata) { core_alua_update_tpg_primary_metadata(tg_pt_gp); } pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu" " from primary access state %s to %s\n", (explicit) ? "explicit" : "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item), tg_pt_gp->tg_pt_gp_id, core_alua_dump_state(prev_state), core_alua_dump_state(new_state)); core_alua_queue_state_change_ua(tg_pt_gp); mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex); return 0; } int core_alua_do_port_transition( struct t10_alua_tg_pt_gp *l_tg_pt_gp, struct se_device *l_dev, struct se_lun *l_lun, struct se_node_acl *l_nacl, int new_state, int explicit) { struct se_device *dev; struct t10_alua_lu_gp *lu_gp; struct t10_alua_lu_gp_member *lu_gp_mem, *local_lu_gp_mem; struct t10_alua_tg_pt_gp *tg_pt_gp; int primary, valid_states, rc = 0; if (l_dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA) return -ENODEV; valid_states = l_tg_pt_gp->tg_pt_gp_alua_supported_states; if (core_alua_check_transition(new_state, valid_states, &primary, explicit) != 0) return -EINVAL; local_lu_gp_mem = l_dev->dev_alua_lu_gp_mem; spin_lock(&local_lu_gp_mem->lu_gp_mem_lock); lu_gp = local_lu_gp_mem->lu_gp; atomic_inc(&lu_gp->lu_gp_ref_cnt); spin_unlock(&local_lu_gp_mem->lu_gp_mem_lock); /* * For storage objects that are members of the 'default_lu_gp', * we only do transition on the passed *l_tp_pt_gp, and not * on all of the matching target port groups IDs in default_lu_gp. */ if (!lu_gp->lu_gp_id) { /* * core_alua_do_transition_tg_pt() will always return * success. */ l_tg_pt_gp->tg_pt_gp_alua_lun = l_lun; l_tg_pt_gp->tg_pt_gp_alua_nacl = l_nacl; rc = core_alua_do_transition_tg_pt(l_tg_pt_gp, new_state, explicit); atomic_dec_mb(&lu_gp->lu_gp_ref_cnt); return rc; } /* * For all other LU groups aside from 'default_lu_gp', walk all of * the associated storage objects looking for a matching target port * group ID from the local target port group. */ spin_lock(&lu_gp->lu_gp_lock); list_for_each_entry(lu_gp_mem, &lu_gp->lu_gp_mem_list, lu_gp_mem_list) { dev = lu_gp_mem->lu_gp_mem_dev; atomic_inc_mb(&lu_gp_mem->lu_gp_mem_ref_cnt); spin_unlock(&lu_gp->lu_gp_lock); spin_lock(&dev->t10_alua.tg_pt_gps_lock); list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list, tg_pt_gp_list) { if (!tg_pt_gp->tg_pt_gp_valid_id) continue; /* * If the target behavior port asymmetric access state * is changed for any target port group accessible via * a logical unit within a LU group, the target port * behavior group asymmetric access states for the same * target port group accessible via other logical units * in that LU group will also change. */ if (l_tg_pt_gp->tg_pt_gp_id != tg_pt_gp->tg_pt_gp_id) continue; if (l_tg_pt_gp == tg_pt_gp) { tg_pt_gp->tg_pt_gp_alua_lun = l_lun; tg_pt_gp->tg_pt_gp_alua_nacl = l_nacl; } else { tg_pt_gp->tg_pt_gp_alua_lun = NULL; tg_pt_gp->tg_pt_gp_alua_nacl = NULL; } atomic_inc_mb(&tg_pt_gp->tg_pt_gp_ref_cnt); spin_unlock(&dev->t10_alua.tg_pt_gps_lock); /* * core_alua_do_transition_tg_pt() will always return * success. */ rc = core_alua_do_transition_tg_pt(tg_pt_gp, new_state, explicit); spin_lock(&dev->t10_alua.tg_pt_gps_lock); atomic_dec_mb(&tg_pt_gp->tg_pt_gp_ref_cnt); if (rc) break; } spin_unlock(&dev->t10_alua.tg_pt_gps_lock); spin_lock(&lu_gp->lu_gp_lock); atomic_dec_mb(&lu_gp_mem->lu_gp_mem_ref_cnt); } spin_unlock(&lu_gp->lu_gp_lock); if (!rc) { pr_debug("Successfully processed LU Group: %s all ALUA TG PT" " Group IDs: %hu %s transition to primary state: %s\n", config_item_name(&lu_gp->lu_gp_group.cg_item), l_tg_pt_gp->tg_pt_gp_id, (explicit) ? "explicit" : "implicit", core_alua_dump_state(new_state)); } atomic_dec_mb(&lu_gp->lu_gp_ref_cnt); return rc; } static int core_alua_update_tpg_secondary_metadata(struct se_lun *lun) { struct se_portal_group *se_tpg = lun->lun_tpg; unsigned char *md_buf; char *path; int len, rc; mutex_lock(&lun->lun_tg_pt_md_mutex); md_buf = kzalloc(ALUA_MD_BUF_LEN, GFP_KERNEL); if (!md_buf) { pr_err("Unable to allocate buf for ALUA metadata\n"); rc = -ENOMEM; goto out_unlock; } len = snprintf(md_buf, ALUA_MD_BUF_LEN, "alua_tg_pt_offline=%d\n" "alua_tg_pt_status=0x%02x\n", atomic_read(&lun->lun_tg_pt_secondary_offline), lun->lun_tg_pt_secondary_stat); if (se_tpg->se_tpg_tfo->tpg_get_tag != NULL) { path = kasprintf(GFP_KERNEL, "%s/alua/%s/%s+%hu/lun_%llu", db_root, se_tpg->se_tpg_tfo->fabric_name, se_tpg->se_tpg_tfo->tpg_get_wwn(se_tpg), se_tpg->se_tpg_tfo->tpg_get_tag(se_tpg), lun->unpacked_lun); } else { path = kasprintf(GFP_KERNEL, "%s/alua/%s/%s/lun_%llu", db_root, se_tpg->se_tpg_tfo->fabric_name, se_tpg->se_tpg_tfo->tpg_get_wwn(se_tpg), lun->unpacked_lun); } if (!path) { rc = -ENOMEM; goto out_free; } rc = core_alua_write_tpg_metadata(path, md_buf, len); kfree(path); out_free: kfree(md_buf); out_unlock: mutex_unlock(&lun->lun_tg_pt_md_mutex); return rc; } static int core_alua_set_tg_pt_secondary_state( struct se_lun *lun, int explicit, int offline) { struct t10_alua_tg_pt_gp *tg_pt_gp; int trans_delay_msecs; rcu_read_lock(); tg_pt_gp = rcu_dereference(lun->lun_tg_pt_gp); if (!tg_pt_gp) { rcu_read_unlock(); pr_err("Unable to complete secondary state" " transition\n"); return -EINVAL; } trans_delay_msecs = tg_pt_gp->tg_pt_gp_trans_delay_msecs; /* * Set the secondary ALUA target port access state to OFFLINE * or release the previously secondary state for struct se_lun */ if (offline) atomic_set(&lun->lun_tg_pt_secondary_offline, 1); else atomic_set(&lun->lun_tg_pt_secondary_offline, 0); lun->lun_tg_pt_secondary_stat = (explicit) ? ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG : ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA; pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu" " to secondary access state: %s\n", (explicit) ? "explicit" : "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item), tg_pt_gp->tg_pt_gp_id, (offline) ? "OFFLINE" : "ONLINE"); rcu_read_unlock(); /* * Do the optional transition delay after we set the secondary * ALUA access state. */ if (trans_delay_msecs != 0) msleep_interruptible(trans_delay_msecs); /* * See if we need to update the ALUA fabric port metadata for * secondary state and status */ if (lun->lun_tg_pt_secondary_write_md) core_alua_update_tpg_secondary_metadata(lun); return 0; } struct t10_alua_lba_map * core_alua_allocate_lba_map(struct list_head *list, u64 first_lba, u64 last_lba) { struct t10_alua_lba_map *lba_map; lba_map = kmem_cache_zalloc(t10_alua_lba_map_cache, GFP_KERNEL); if (!lba_map) { pr_err("Unable to allocate struct t10_alua_lba_map\n"); return ERR_PTR(-ENOMEM); } INIT_LIST_HEAD(&lba_map->lba_map_mem_list); lba_map->lba_map_first_lba = first_lba; lba_map->lba_map_last_lba = last_lba; list_add_tail(&lba_map->lba_map_list, list); return lba_map; } int core_alua_allocate_lba_map_mem(struct t10_alua_lba_map *lba_map, int pg_id, int state) { struct t10_alua_lba_map_member *lba_map_mem; list_for_each_entry(lba_map_mem, &lba_map->lba_map_mem_list, lba_map_mem_list) { if (lba_map_mem->lba_map_mem_alua_pg_id == pg_id) { pr_err("Duplicate pg_id %d in lba_map\n", pg_id); return -EINVAL; } } lba_map_mem = kmem_cache_zalloc(t10_alua_lba_map_mem_cache, GFP_KERNEL); if (!lba_map_mem) { pr_err("Unable to allocate struct t10_alua_lba_map_mem\n"); return -ENOMEM; } lba_map_mem->lba_map_mem_alua_state = state; lba_map_mem->lba_map_mem_alua_pg_id = pg_id; list_add_tail(&lba_map_mem->lba_map_mem_list, &lba_map->lba_map_mem_list); return 0; } void core_alua_free_lba_map(struct list_head *lba_list) { struct t10_alua_lba_map *lba_map, *lba_map_tmp; struct t10_alua_lba_map_member *lba_map_mem, *lba_map_mem_tmp; list_for_each_entry_safe(lba_map, lba_map_tmp, lba_list, lba_map_list) { list_for_each_entry_safe(lba_map_mem, lba_map_mem_tmp, &lba_map->lba_map_mem_list, lba_map_mem_list) { list_del(&lba_map_mem->lba_map_mem_list); kmem_cache_free(t10_alua_lba_map_mem_cache, lba_map_mem); } list_del(&lba_map->lba_map_list); kmem_cache_free(t10_alua_lba_map_cache, lba_map); } } void core_alua_set_lba_map(struct se_device *dev, struct list_head *lba_map_list, int segment_size, int segment_mult) { struct list_head old_lba_map_list; struct t10_alua_tg_pt_gp *tg_pt_gp; int activate = 0, supported; INIT_LIST_HEAD(&old_lba_map_list); spin_lock(&dev->t10_alua.lba_map_lock); dev->t10_alua.lba_map_segment_size = segment_size; dev->t10_alua.lba_map_segment_multiplier = segment_mult; list_splice_init(&dev->t10_alua.lba_map_list, &old_lba_map_list); if (lba_map_list) { list_splice_init(lba_map_list, &dev->t10_alua.lba_map_list); activate = 1; } spin_unlock(&dev->t10_alua.lba_map_lock); spin_lock(&dev->t10_alua.tg_pt_gps_lock); list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list, tg_pt_gp_list) { if (!tg_pt_gp->tg_pt_gp_valid_id) continue; supported = tg_pt_gp->tg_pt_gp_alua_supported_states; if (activate) supported |= ALUA_LBD_SUP; else supported &= ~ALUA_LBD_SUP; tg_pt_gp->tg_pt_gp_alua_supported_states = supported; } spin_unlock(&dev->t10_alua.tg_pt_gps_lock); core_alua_free_lba_map(&old_lba_map_list); } struct t10_alua_lu_gp * core_alua_allocate_lu_gp(const char *name, int def_group) { struct t10_alua_lu_gp *lu_gp; lu_gp = kmem_cache_zalloc(t10_alua_lu_gp_cache, GFP_KERNEL); if (!lu_gp) { pr_err("Unable to allocate struct t10_alua_lu_gp\n"); return ERR_PTR(-ENOMEM); } INIT_LIST_HEAD(&lu_gp->lu_gp_node); INIT_LIST_HEAD(&lu_gp->lu_gp_mem_list); spin_lock_init(&lu_gp->lu_gp_lock); atomic_set(&lu_gp->lu_gp_ref_cnt, 0); if (def_group) { lu_gp->lu_gp_id = alua_lu_gps_counter++; lu_gp->lu_gp_valid_id = 1; alua_lu_gps_count++; } return lu_gp; } int core_alua_set_lu_gp_id(struct t10_alua_lu_gp *lu_gp, u16 lu_gp_id) { struct t10_alua_lu_gp *lu_gp_tmp; u16 lu_gp_id_tmp; /* * The lu_gp->lu_gp_id may only be set once.. */ if (lu_gp->lu_gp_valid_id) { pr_warn("ALUA LU Group already has a valid ID," " ignoring request\n"); return -EINVAL; } spin_lock(&lu_gps_lock); if (alua_lu_gps_count == 0x0000ffff) { pr_err("Maximum ALUA alua_lu_gps_count:" " 0x0000ffff reached\n"); spin_unlock(&lu_gps_lock); kmem_cache_free(t10_alua_lu_gp_cache, lu_gp); return -ENOSPC; } again: lu_gp_id_tmp = (lu_gp_id != 0) ? lu_gp_id : alua_lu_gps_counter++; list_for_each_entry(lu_gp_tmp, &lu_gps_list, lu_gp_node) { if (lu_gp_tmp->lu_gp_id == lu_gp_id_tmp) { if (!lu_gp_id) goto again; pr_warn("ALUA Logical Unit Group ID: %hu" " already exists, ignoring request\n", lu_gp_id); spin_unlock(&lu_gps_lock); return -EINVAL; } } lu_gp->lu_gp_id = lu_gp_id_tmp; lu_gp->lu_gp_valid_id = 1; list_add_tail(&lu_gp->lu_gp_node, &lu_gps_list); alua_lu_gps_count++; spin_unlock(&lu_gps_lock); return 0; } static struct t10_alua_lu_gp_member * core_alua_allocate_lu_gp_mem(struct se_device *dev) { struct t10_alua_lu_gp_member *lu_gp_mem; lu_gp_mem = kmem_cache_zalloc(t10_alua_lu_gp_mem_cache, GFP_KERNEL); if (!lu_gp_mem) { pr_err("Unable to allocate struct t10_alua_lu_gp_member\n"); return ERR_PTR(-ENOMEM); } INIT_LIST_HEAD(&lu_gp_mem->lu_gp_mem_list); spin_lock_init(&lu_gp_mem->lu_gp_mem_lock); atomic_set(&lu_gp_mem->lu_gp_mem_ref_cnt, 0); lu_gp_mem->lu_gp_mem_dev = dev; dev->dev_alua_lu_gp_mem = lu_gp_mem; return lu_gp_mem; } void core_alua_free_lu_gp(struct t10_alua_lu_gp *lu_gp) { struct t10_alua_lu_gp_member *lu_gp_mem, *lu_gp_mem_tmp; /* * Once we have reached this point, config_item_put() has * already been called from target_core_alua_drop_lu_gp(). * * Here, we remove the *lu_gp from the global list so that * no associations can be made while we are releasing * struct t10_alua_lu_gp. */ spin_lock(&lu_gps_lock); list_del(&lu_gp->lu_gp_node); alua_lu_gps_count--; spin_unlock(&lu_gps_lock); /* * Allow struct t10_alua_lu_gp * referenced by core_alua_get_lu_gp_by_name() * in target_core_configfs.c:target_core_store_alua_lu_gp() to be * released with core_alua_put_lu_gp_from_name() */ while (atomic_read(&lu_gp->lu_gp_ref_cnt)) cpu_relax(); /* * Release reference to struct t10_alua_lu_gp * from all associated * struct se_device. */ spin_lock(&lu_gp->lu_gp_lock); list_for_each_entry_safe(lu_gp_mem, lu_gp_mem_tmp, &lu_gp->lu_gp_mem_list, lu_gp_mem_list) { if (lu_gp_mem->lu_gp_assoc) { list_del(&lu_gp_mem->lu_gp_mem_list); lu_gp->lu_gp_members--; lu_gp_mem->lu_gp_assoc = 0; } spin_unlock(&lu_gp->lu_gp_lock); /* * * lu_gp_mem is associated with a single * struct se_device->dev_alua_lu_gp_mem, and is released when * struct se_device is released via core_alua_free_lu_gp_mem(). * * If the passed lu_gp does NOT match the default_lu_gp, assume * we want to re-associate a given lu_gp_mem with default_lu_gp. */ spin_lock(&lu_gp_mem->lu_gp_mem_lock); if (lu_gp != default_lu_gp) __core_alua_attach_lu_gp_mem(lu_gp_mem, default_lu_gp); else lu_gp_mem->lu_gp = NULL; spin_unlock(&lu_gp_mem->lu_gp_mem_lock); spin_lock(&lu_gp->lu_gp_lock); } spin_unlock(&lu_gp->lu_gp_lock); kmem_cache_free(t10_alua_lu_gp_cache, lu_gp); } void core_alua_free_lu_gp_mem(struct se_device *dev) { struct t10_alua_lu_gp *lu_gp; struct t10_alua_lu_gp_member *lu_gp_mem; lu_gp_mem = dev->dev_alua_lu_gp_mem; if (!lu_gp_mem) return; while (atomic_read(&lu_gp_mem->lu_gp_mem_ref_cnt)) cpu_relax(); spin_lock(&lu_gp_mem->lu_gp_mem_lock); lu_gp = lu_gp_mem->lu_gp; if (lu_gp) { spin_lock(&lu_gp->lu_gp_lock); if (lu_gp_mem->lu_gp_assoc) { list_del(&lu_gp_mem->lu_gp_mem_list); lu_gp->lu_gp_members--; lu_gp_mem->lu_gp_assoc = 0; } spin_unlock(&lu_gp->lu_gp_lock); lu_gp_mem->lu_gp = NULL; } spin_unlock(&lu_gp_mem->lu_gp_mem_lock); kmem_cache_free(t10_alua_lu_gp_mem_cache, lu_gp_mem); } struct t10_alua_lu_gp *core_alua_get_lu_gp_by_name(const char *name) { struct t10_alua_lu_gp *lu_gp; struct config_item *ci; spin_lock(&lu_gps_lock); list_for_each_entry(lu_gp, &lu_gps_list, lu_gp_node) { if (!lu_gp->lu_gp_valid_id) continue; ci = &lu_gp->lu_gp_group.cg_item; if (!strcmp(config_item_name(ci), name)) { atomic_inc(&lu_gp->lu_gp_ref_cnt); spin_unlock(&lu_gps_lock); return lu_gp; } } spin_unlock(&lu_gps_lock); return NULL; } void core_alua_put_lu_gp_from_name(struct t10_alua_lu_gp *lu_gp) { spin_lock(&lu_gps_lock); atomic_dec(&lu_gp->lu_gp_ref_cnt); spin_unlock(&lu_gps_lock); } /* * Called with struct t10_alua_lu_gp_member->lu_gp_mem_lock */ void __core_alua_attach_lu_gp_mem( struct t10_alua_lu_gp_member *lu_gp_mem, struct t10_alua_lu_gp *lu_gp) { spin_lock(&lu_gp->lu_gp_lock); lu_gp_mem->lu_gp = lu_gp; lu_gp_mem->lu_gp_assoc = 1; list_add_tail(&lu_gp_mem->lu_gp_mem_list, &lu_gp->lu_gp_mem_list); lu_gp->lu_gp_members++; spin_unlock(&lu_gp->lu_gp_lock); } /* * Called with struct t10_alua_lu_gp_member->lu_gp_mem_lock */ void __core_alua_drop_lu_gp_mem( struct t10_alua_lu_gp_member *lu_gp_mem, struct t10_alua_lu_gp *lu_gp) { spin_lock(&lu_gp->lu_gp_lock); list_del(&lu_gp_mem->lu_gp_mem_list); lu_gp_mem->lu_gp = NULL; lu_gp_mem->lu_gp_assoc = 0; lu_gp->lu_gp_members--; spin_unlock(&lu_gp->lu_gp_lock); } struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev, const char *name, int def_group) { struct t10_alua_tg_pt_gp *tg_pt_gp; tg_pt_gp = kmem_cache_zalloc(t10_alua_tg_pt_gp_cache, GFP_KERNEL); if (!tg_pt_gp) { pr_err("Unable to allocate struct t10_alua_tg_pt_gp\n"); return NULL; } INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_list); INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_lun_list); mutex_init(&tg_pt_gp->tg_pt_gp_transition_mutex); spin_lock_init(&tg_pt_gp->tg_pt_gp_lock); atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0); tg_pt_gp->tg_pt_gp_dev = dev; tg_pt_gp->tg_pt_gp_alua_access_state = ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED; /* * Enable both explicit and implicit ALUA support by default */ tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_EXPLICIT_ALUA | TPGS_IMPLICIT_ALUA; /* * Set the default Active/NonOptimized Delay in milliseconds */ tg_pt_gp->tg_pt_gp_nonop_delay_msecs = ALUA_DEFAULT_NONOP_DELAY_MSECS; tg_pt_gp->tg_pt_gp_trans_delay_msecs = ALUA_DEFAULT_TRANS_DELAY_MSECS; tg_pt_gp->tg_pt_gp_implicit_trans_secs = ALUA_DEFAULT_IMPLICIT_TRANS_SECS; /* * Enable all supported states */ tg_pt_gp->tg_pt_gp_alua_supported_states = ALUA_T_SUP | ALUA_O_SUP | ALUA_U_SUP | ALUA_S_SUP | ALUA_AN_SUP | ALUA_AO_SUP; if (def_group) { spin_lock(&dev->t10_alua.tg_pt_gps_lock); tg_pt_gp->tg_pt_gp_id = dev->t10_alua.alua_tg_pt_gps_counter++; tg_pt_gp->tg_pt_gp_valid_id = 1; dev->t10_alua.alua_tg_pt_gps_count++; list_add_tail(&tg_pt_gp->tg_pt_gp_list, &dev->t10_alua.tg_pt_gps_list); spin_unlock(&dev->t10_alua.tg_pt_gps_lock); } return tg_pt_gp; } int core_alua_set_tg_pt_gp_id( struct t10_alua_tg_pt_gp *tg_pt_gp, u16 tg_pt_gp_id) { struct se_device *dev = tg_pt_gp->tg_pt_gp_dev; struct t10_alua_tg_pt_gp *tg_pt_gp_tmp; u16 tg_pt_gp_id_tmp; /* * The tg_pt_gp->tg_pt_gp_id may only be set once.. */ if (tg_pt_gp->tg_pt_gp_valid_id) { pr_warn("ALUA TG PT Group already has a valid ID," " ignoring request\n"); return -EINVAL; } spin_lock(&dev->t10_alua.tg_pt_gps_lock); if (dev->t10_alua.alua_tg_pt_gps_count == 0x0000ffff) { pr_err("Maximum ALUA alua_tg_pt_gps_count:" " 0x0000ffff reached\n"); spin_unlock(&dev->t10_alua.tg_pt_gps_lock); return -ENOSPC; } again: tg_pt_gp_id_tmp = (tg_pt_gp_id != 0) ? tg_pt_gp_id : dev->t10_alua.alua_tg_pt_gps_counter++; list_for_each_entry(tg_pt_gp_tmp, &dev->t10_alua.tg_pt_gps_list, tg_pt_gp_list) { if (tg_pt_gp_tmp->tg_pt_gp_id == tg_pt_gp_id_tmp) { if (!tg_pt_gp_id) goto again; pr_err("ALUA Target Port Group ID: %hu already" " exists, ignoring request\n", tg_pt_gp_id); spin_unlock(&dev->t10_alua.tg_pt_gps_lock); return -EINVAL; } } tg_pt_gp->tg_pt_gp_id = tg_pt_gp_id_tmp; tg_pt_gp->tg_pt_gp_valid_id = 1; list_add_tail(&tg_pt_gp->tg_pt_gp_list, &dev->t10_alua.tg_pt_gps_list); dev->t10_alua.alua_tg_pt_gps_count++; spin_unlock(&dev->t10_alua.tg_pt_gps_lock); return 0; } void core_alua_free_tg_pt_gp( struct t10_alua_tg_pt_gp *tg_pt_gp) { struct se_device *dev = tg_pt_gp->tg_pt_gp_dev; struct se_lun *lun, *next; /* * Once we have reached this point, config_item_put() has already * been called from target_core_alua_drop_tg_pt_gp(). * * Here we remove *tg_pt_gp from the global list so that * no associations *OR* explicit ALUA via SET_TARGET_PORT_GROUPS * can be made while we are releasing struct t10_alua_tg_pt_gp. */ spin_lock(&dev->t10_alua.tg_pt_gps_lock); if (tg_pt_gp->tg_pt_gp_valid_id) { list_del(&tg_pt_gp->tg_pt_gp_list); dev->t10_alua.alua_tg_pt_gps_count--; } spin_unlock(&dev->t10_alua.tg_pt_gps_lock); /* * Allow a struct t10_alua_tg_pt_gp_member * referenced by * core_alua_get_tg_pt_gp_by_name() in * target_core_configfs.c:target_core_store_alua_tg_pt_gp() * to be released with core_alua_put_tg_pt_gp_from_name(). */ while (atomic_read(&tg_pt_gp->tg_pt_gp_ref_cnt)) cpu_relax(); /* * Release reference to struct t10_alua_tg_pt_gp from all associated * struct se_port. */ spin_lock(&tg_pt_gp->tg_pt_gp_lock); list_for_each_entry_safe(lun, next, &tg_pt_gp->tg_pt_gp_lun_list, lun_tg_pt_gp_link) { list_del_init(&lun->lun_tg_pt_gp_link); tg_pt_gp->tg_pt_gp_members--; spin_unlock(&tg_pt_gp->tg_pt_gp_lock); /* * If the passed tg_pt_gp does NOT match the default_tg_pt_gp, * assume we want to re-associate a given tg_pt_gp_mem with * default_tg_pt_gp. */ spin_lock(&lun->lun_tg_pt_gp_lock); if (tg_pt_gp != dev->t10_alua.default_tg_pt_gp) { __target_attach_tg_pt_gp(lun, dev->t10_alua.default_tg_pt_gp); } else rcu_assign_pointer(lun->lun_tg_pt_gp, NULL); spin_unlock(&lun->lun_tg_pt_gp_lock); spin_lock(&tg_pt_gp->tg_pt_gp_lock); } spin_unlock(&tg_pt_gp->tg_pt_gp_lock); synchronize_rcu(); kmem_cache_free(t10_alua_tg_pt_gp_cache, tg_pt_gp); } static struct t10_alua_tg_pt_gp *core_alua_get_tg_pt_gp_by_name( struct se_device *dev, const char *name) { struct t10_alua_tg_pt_gp *tg_pt_gp; struct config_item *ci; spin_lock(&dev->t10_alua.tg_pt_gps_lock); list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list, tg_pt_gp_list) { if (!tg_pt_gp->tg_pt_gp_valid_id) continue; ci = &tg_pt_gp->tg_pt_gp_group.cg_item; if (!strcmp(config_item_name(ci), name)) { atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt); spin_unlock(&dev->t10_alua.tg_pt_gps_lock); return tg_pt_gp; } } spin_unlock(&dev->t10_alua.tg_pt_gps_lock); return NULL; } static void core_alua_put_tg_pt_gp_from_name( struct t10_alua_tg_pt_gp *tg_pt_gp) { struct se_device *dev = tg_pt_gp->tg_pt_gp_dev; spin_lock(&dev->t10_alua.tg_pt_gps_lock); atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt); spin_unlock(&dev->t10_alua.tg_pt_gps_lock); } static void __target_attach_tg_pt_gp(struct se_lun *lun, struct t10_alua_tg_pt_gp *tg_pt_gp) { struct se_dev_entry *se_deve; assert_spin_locked(&lun->lun_tg_pt_gp_lock); spin_lock(&tg_pt_gp->tg_pt_gp_lock); rcu_assign_pointer(lun->lun_tg_pt_gp, tg_pt_gp); list_add_tail(&lun->lun_tg_pt_gp_link, &tg_pt_gp->tg_pt_gp_lun_list); tg_pt_gp->tg_pt_gp_members++; spin_lock(&lun->lun_deve_lock); list_for_each_entry(se_deve, &lun->lun_deve_list, lun_link) core_scsi3_ua_allocate(se_deve, 0x3f, ASCQ_3FH_INQUIRY_DATA_HAS_CHANGED); spin_unlock(&lun->lun_deve_lock); spin_unlock(&tg_pt_gp->tg_pt_gp_lock); } void target_attach_tg_pt_gp(struct se_lun *lun, struct t10_alua_tg_pt_gp *tg_pt_gp) { spin_lock(&lun->lun_tg_pt_gp_lock); __target_attach_tg_pt_gp(lun, tg_pt_gp); spin_unlock(&lun->lun_tg_pt_gp_lock); synchronize_rcu(); } static void __target_detach_tg_pt_gp(struct se_lun *lun, struct t10_alua_tg_pt_gp *tg_pt_gp) { assert_spin_locked(&lun->lun_tg_pt_gp_lock); spin_lock(&tg_pt_gp->tg_pt_gp_lock); list_del_init(&lun->lun_tg_pt_gp_link); tg_pt_gp->tg_pt_gp_members--; spin_unlock(&tg_pt_gp->tg_pt_gp_lock); } void target_detach_tg_pt_gp(struct se_lun *lun) { struct t10_alua_tg_pt_gp *tg_pt_gp; spin_lock(&lun->lun_tg_pt_gp_lock); tg_pt_gp = rcu_dereference_check(lun->lun_tg_pt_gp, lockdep_is_held(&lun->lun_tg_pt_gp_lock)); if (tg_pt_gp) { __target_detach_tg_pt_gp(lun, tg_pt_gp); rcu_assign_pointer(lun->lun_tg_pt_gp, NULL); } spin_unlock(&lun->lun_tg_pt_gp_lock); synchronize_rcu(); } static void target_swap_tg_pt_gp(struct se_lun *lun, struct t10_alua_tg_pt_gp *old_tg_pt_gp, struct t10_alua_tg_pt_gp *new_tg_pt_gp) { assert_spin_locked(&lun->lun_tg_pt_gp_lock); if (old_tg_pt_gp) __target_detach_tg_pt_gp(lun, old_tg_pt_gp); __target_attach_tg_pt_gp(lun, new_tg_pt_gp); } ssize_t core_alua_show_tg_pt_gp_info(struct se_lun *lun, char *page) { struct config_item *tg_pt_ci; struct t10_alua_tg_pt_gp *tg_pt_gp; ssize_t len = 0; rcu_read_lock(); tg_pt_gp = rcu_dereference(lun->lun_tg_pt_gp); if (tg_pt_gp) { tg_pt_ci = &tg_pt_gp->tg_pt_gp_group.cg_item; len += sprintf(page, "TG Port Alias: %s\nTG Port Group ID:" " %hu\nTG Port Primary Access State: %s\nTG Port " "Primary Access Status: %s\nTG Port Secondary Access" " State: %s\nTG Port Secondary Access Status: %s\n", config_item_name(tg_pt_ci), tg_pt_gp->tg_pt_gp_id, core_alua_dump_state( tg_pt_gp->tg_pt_gp_alua_access_state), core_alua_dump_status( tg_pt_gp->tg_pt_gp_alua_access_status), atomic_read(&lun->lun_tg_pt_secondary_offline) ? "Offline" : "None", core_alua_dump_status(lun->lun_tg_pt_secondary_stat)); } rcu_read_unlock(); return len; } ssize_t core_alua_store_tg_pt_gp_info( struct se_lun *lun, const char *page, size_t count) { struct se_portal_group *tpg = lun->lun_tpg; /* * rcu_dereference_raw protected by se_lun->lun_group symlink * reference to se_device->dev_group. */ struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev); struct t10_alua_tg_pt_gp *tg_pt_gp = NULL, *tg_pt_gp_new = NULL; unsigned char buf[TG_PT_GROUP_NAME_BUF]; int move = 0; if (dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA || (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) return -ENODEV; if (count > TG_PT_GROUP_NAME_BUF) { pr_err("ALUA Target Port Group alias too large!\n"); return -EINVAL; } memset(buf, 0, TG_PT_GROUP_NAME_BUF); memcpy(buf, page, count); /* * Any ALUA target port group alias besides "NULL" means we will be * making a new group association. */ if (strcmp(strstrip(buf), "NULL")) { /* * core_alua_get_tg_pt_gp_by_name() will increment reference to * struct t10_alua_tg_pt_gp. This reference is released with * core_alua_put_tg_pt_gp_from_name() below. */ tg_pt_gp_new = core_alua_get_tg_pt_gp_by_name(dev, strstrip(buf)); if (!tg_pt_gp_new) return -ENODEV; } spin_lock(&lun->lun_tg_pt_gp_lock); tg_pt_gp = rcu_dereference_check(lun->lun_tg_pt_gp, lockdep_is_held(&lun->lun_tg_pt_gp_lock)); if (tg_pt_gp) { /* * Clearing an existing tg_pt_gp association, and replacing * with the default_tg_pt_gp. */ if (!tg_pt_gp_new) { pr_debug("Target_Core_ConfigFS: Moving" " %s/tpgt_%hu/%s from ALUA Target Port Group:" " alua/%s, ID: %hu back to" " default_tg_pt_gp\n", tpg->se_tpg_tfo->tpg_get_wwn(tpg), tpg->se_tpg_tfo->tpg_get_tag(tpg), config_item_name(&lun->lun_group.cg_item), config_item_name( &tg_pt_gp->tg_pt_gp_group.cg_item), tg_pt_gp->tg_pt_gp_id); target_swap_tg_pt_gp(lun, tg_pt_gp, dev->t10_alua.default_tg_pt_gp); spin_unlock(&lun->lun_tg_pt_gp_lock); goto sync_rcu; } move = 1; } target_swap_tg_pt_gp(lun, tg_pt_gp, tg_pt_gp_new); spin_unlock(&lun->lun_tg_pt_gp_lock); pr_debug("Target_Core_ConfigFS: %s %s/tpgt_%hu/%s to ALUA" " Target Port Group: alua/%s, ID: %hu\n", (move) ? "Moving" : "Adding", tpg->se_tpg_tfo->tpg_get_wwn(tpg), tpg->se_tpg_tfo->tpg_get_tag(tpg), config_item_name(&lun->lun_group.cg_item), config_item_name(&tg_pt_gp_new->tg_pt_gp_group.cg_item), tg_pt_gp_new->tg_pt_gp_id); core_alua_put_tg_pt_gp_from_name(tg_pt_gp_new); sync_rcu: synchronize_rcu(); return count; } ssize_t core_alua_show_access_type( struct t10_alua_tg_pt_gp *tg_pt_gp, char *page) { if ((tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA) && (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA)) return sprintf(page, "Implicit and Explicit\n"); else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA) return sprintf(page, "Implicit\n"); else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA) return sprintf(page, "Explicit\n"); else return sprintf(page, "None\n"); } ssize_t core_alua_store_access_type( struct t10_alua_tg_pt_gp *tg_pt_gp, const char *page, size_t count) { unsigned long tmp; int ret; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract alua_access_type\n"); return ret; } if ((tmp != 0) && (tmp != 1) && (tmp != 2) && (tmp != 3)) { pr_err("Illegal value for alua_access_type:" " %lu\n", tmp); return -EINVAL; } if (tmp == 3) tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_IMPLICIT_ALUA | TPGS_EXPLICIT_ALUA; else if (tmp == 2) tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_EXPLICIT_ALUA; else if (tmp == 1) tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_IMPLICIT_ALUA; else tg_pt_gp->tg_pt_gp_alua_access_type = 0; return count; } ssize_t core_alua_show_nonop_delay_msecs( struct t10_alua_tg_pt_gp *tg_pt_gp, char *page) { return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_nonop_delay_msecs); } ssize_t core_alua_store_nonop_delay_msecs( struct t10_alua_tg_pt_gp *tg_pt_gp, const char *page, size_t count) { unsigned long tmp; int ret; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract nonop_delay_msecs\n"); return ret; } if (tmp > ALUA_MAX_NONOP_DELAY_MSECS) { pr_err("Passed nonop_delay_msecs: %lu, exceeds" " ALUA_MAX_NONOP_DELAY_MSECS: %d\n", tmp, ALUA_MAX_NONOP_DELAY_MSECS); return -EINVAL; } tg_pt_gp->tg_pt_gp_nonop_delay_msecs = (int)tmp; return count; } ssize_t core_alua_show_trans_delay_msecs( struct t10_alua_tg_pt_gp *tg_pt_gp, char *page) { return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_trans_delay_msecs); } ssize_t core_alua_store_trans_delay_msecs( struct t10_alua_tg_pt_gp *tg_pt_gp, const char *page, size_t count) { unsigned long tmp; int ret; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract trans_delay_msecs\n"); return ret; } if (tmp > ALUA_MAX_TRANS_DELAY_MSECS) { pr_err("Passed trans_delay_msecs: %lu, exceeds" " ALUA_MAX_TRANS_DELAY_MSECS: %d\n", tmp, ALUA_MAX_TRANS_DELAY_MSECS); return -EINVAL; } tg_pt_gp->tg_pt_gp_trans_delay_msecs = (int)tmp; return count; } ssize_t core_alua_show_implicit_trans_secs( struct t10_alua_tg_pt_gp *tg_pt_gp, char *page) { return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_implicit_trans_secs); } ssize_t core_alua_store_implicit_trans_secs( struct t10_alua_tg_pt_gp *tg_pt_gp, const char *page, size_t count) { unsigned long tmp; int ret; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract implicit_trans_secs\n"); return ret; } if (tmp > ALUA_MAX_IMPLICIT_TRANS_SECS) { pr_err("Passed implicit_trans_secs: %lu, exceeds" " ALUA_MAX_IMPLICIT_TRANS_SECS: %d\n", tmp, ALUA_MAX_IMPLICIT_TRANS_SECS); return -EINVAL; } tg_pt_gp->tg_pt_gp_implicit_trans_secs = (int)tmp; return count; } ssize_t core_alua_show_preferred_bit( struct t10_alua_tg_pt_gp *tg_pt_gp, char *page) { return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_pref); } ssize_t core_alua_store_preferred_bit( struct t10_alua_tg_pt_gp *tg_pt_gp, const char *page, size_t count) { unsigned long tmp; int ret; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract preferred ALUA value\n"); return ret; } if ((tmp != 0) && (tmp != 1)) { pr_err("Illegal value for preferred ALUA: %lu\n", tmp); return -EINVAL; } tg_pt_gp->tg_pt_gp_pref = (int)tmp; return count; } ssize_t core_alua_show_offline_bit(struct se_lun *lun, char *page) { return sprintf(page, "%d\n", atomic_read(&lun->lun_tg_pt_secondary_offline)); } ssize_t core_alua_store_offline_bit( struct se_lun *lun, const char *page, size_t count) { /* * rcu_dereference_raw protected by se_lun->lun_group symlink * reference to se_device->dev_group. */ struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev); unsigned long tmp; int ret; if (dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA || (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) return -ENODEV; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract alua_tg_pt_offline value\n"); return ret; } if ((tmp != 0) && (tmp != 1)) { pr_err("Illegal value for alua_tg_pt_offline: %lu\n", tmp); return -EINVAL; } ret = core_alua_set_tg_pt_secondary_state(lun, 0, (int)tmp); if (ret < 0) return -EINVAL; return count; } ssize_t core_alua_show_secondary_status( struct se_lun *lun, char *page) { return sprintf(page, "%d\n", lun->lun_tg_pt_secondary_stat); } ssize_t core_alua_store_secondary_status( struct se_lun *lun, const char *page, size_t count) { unsigned long tmp; int ret; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract alua_tg_pt_status\n"); return ret; } if ((tmp != ALUA_STATUS_NONE) && (tmp != ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) && (tmp != ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA)) { pr_err("Illegal value for alua_tg_pt_status: %lu\n", tmp); return -EINVAL; } lun->lun_tg_pt_secondary_stat = (int)tmp; return count; } ssize_t core_alua_show_secondary_write_metadata( struct se_lun *lun, char *page) { return sprintf(page, "%d\n", lun->lun_tg_pt_secondary_write_md); } ssize_t core_alua_store_secondary_write_metadata( struct se_lun *lun, const char *page, size_t count) { unsigned long tmp; int ret; ret = kstrtoul(page, 0, &tmp); if (ret < 0) { pr_err("Unable to extract alua_tg_pt_write_md\n"); return ret; } if ((tmp != 0) && (tmp != 1)) { pr_err("Illegal value for alua_tg_pt_write_md:" " %lu\n", tmp); return -EINVAL; } lun->lun_tg_pt_secondary_write_md = (int)tmp; return count; } int core_setup_alua(struct se_device *dev) { if (!(dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA) && !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) { struct t10_alua_lu_gp_member *lu_gp_mem; /* * Associate this struct se_device with the default ALUA * LUN Group. */ lu_gp_mem = core_alua_allocate_lu_gp_mem(dev); if (IS_ERR(lu_gp_mem)) return PTR_ERR(lu_gp_mem); spin_lock(&lu_gp_mem->lu_gp_mem_lock); __core_alua_attach_lu_gp_mem(lu_gp_mem, default_lu_gp); spin_unlock(&lu_gp_mem->lu_gp_mem_lock); pr_debug("%s: Adding to default ALUA LU Group:" " core/alua/lu_gps/default_lu_gp\n", dev->transport->name); } return 0; } |
| 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 | // SPDX-License-Identifier: GPL-2.0-only /* ----------------------------------------------------------------------- * * * Copyright 2014 Intel Corporation; author: H. Peter Anvin * * ----------------------------------------------------------------------- */ /* * The IRET instruction, when returning to a 16-bit segment, only * restores the bottom 16 bits of the user space stack pointer. This * causes some 16-bit software to break, but it also leaks kernel state * to user space. * * This works around this by creating percpu "ministacks", each of which * is mapped 2^16 times 64K apart. When we detect that the return SS is * on the LDT, we copy the IRET frame to the ministack and use the * relevant alias to return to userspace. The ministacks are mapped * readonly, so if the IRET fault we promote #GP to #DF which is an IST * vector and thus has its own stack; we then do the fixup in the #DF * handler. * * This file sets up the ministacks and the related page tables. The * actual ministack invocation is in entry_64.S. */ #include <linux/init.h> #include <linux/init_task.h> #include <linux/kernel.h> #include <linux/percpu.h> #include <linux/gfp.h> #include <linux/random.h> #include <linux/pgtable.h> #include <asm/pgalloc.h> #include <asm/setup.h> #include <asm/espfix.h> /* * Note: we only need 6*8 = 48 bytes for the espfix stack, but round * it up to a cache line to avoid unnecessary sharing. */ #define ESPFIX_STACK_SIZE (8*8UL) #define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) /* There is address space for how many espfix pages? */ #define ESPFIX_PAGE_SPACE (1UL << (P4D_SHIFT-PAGE_SHIFT-16)) #define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) #if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS # error "Need more virtual address space for the ESPFIX hack" #endif #define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) /* This contains the *bottom* address of the espfix stack */ DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); /* Initialization mutex - should this be a spinlock? */ static DEFINE_MUTEX(espfix_init_mutex); /* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ #define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) static void *espfix_pages[ESPFIX_MAX_PAGES]; static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] __aligned(PAGE_SIZE); static unsigned int page_random, slot_random; /* * This returns the bottom address of the espfix stack for a specific CPU. * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case * we have to account for some amount of padding at the end of each page. */ static inline unsigned long espfix_base_addr(unsigned int cpu) { unsigned long page, slot; unsigned long addr; page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); addr += ESPFIX_BASE_ADDR; return addr; } #define PTE_STRIDE (65536/PAGE_SIZE) #define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) #define ESPFIX_PMD_CLONES PTRS_PER_PMD #define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) #define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) static void init_espfix_random(void) { unsigned long rand = get_random_long(); slot_random = rand % ESPFIX_STACKS_PER_PAGE; page_random = (rand / ESPFIX_STACKS_PER_PAGE) & (ESPFIX_PAGE_SPACE - 1); } void __init init_espfix_bsp(void) { pgd_t *pgd; p4d_t *p4d; /* FRED systems always restore the full value of %rsp */ if (cpu_feature_enabled(X86_FEATURE_FRED)) return; /* Install the espfix pud into the kernel page directory */ pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)]; p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); p4d_populate(&init_mm, p4d, espfix_pud_page); /* Randomize the locations */ init_espfix_random(); /* The rest is the same as for any other processor */ init_espfix_ap(0); } void init_espfix_ap(int cpu) { unsigned int page; unsigned long addr; pud_t pud, *pud_p; pmd_t pmd, *pmd_p; pte_t pte, *pte_p; int n, node; void *stack_page; pteval_t ptemask; /* FRED systems always restore the full value of %rsp */ if (cpu_feature_enabled(X86_FEATURE_FRED)) return; /* We only have to do this once... */ if (likely(per_cpu(espfix_stack, cpu))) return; /* Already initialized */ addr = espfix_base_addr(cpu); page = cpu/ESPFIX_STACKS_PER_PAGE; /* Did another CPU already set this up? */ stack_page = READ_ONCE(espfix_pages[page]); if (likely(stack_page)) goto done; mutex_lock(&espfix_init_mutex); /* Did we race on the lock? */ stack_page = READ_ONCE(espfix_pages[page]); if (stack_page) goto unlock_done; node = cpu_to_node(cpu); ptemask = __supported_pte_mask; pud_p = &espfix_pud_page[pud_index(addr)]; pud = *pud_p; if (!pud_present(pud)) { struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); pmd_p = (pmd_t *)page_address(page); pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PUD_CLONES; n++) set_pud(&pud_p[n], pud); } pmd_p = pmd_offset(&pud, addr); pmd = *pmd_p; if (!pmd_present(pmd)) { struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); pte_p = (pte_t *)page_address(page); pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PMD_CLONES; n++) set_pmd(&pmd_p[n], pmd); } pte_p = pte_offset_kernel(&pmd, addr); stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); /* * __PAGE_KERNEL_* includes _PAGE_GLOBAL, which we want since * this is mapped to userspace. */ pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); /* Job is done for this CPU and any CPU which shares this page */ WRITE_ONCE(espfix_pages[page], stack_page); unlock_done: mutex_unlock(&espfix_init_mutex); done: per_cpu(espfix_stack, cpu) = addr; per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page + (addr & ~PAGE_MASK); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FPU_XCR_H #define _ASM_X86_FPU_XCR_H #define XCR_XFEATURE_ENABLED_MASK 0x00000000 #define XCR_XFEATURE_IN_USE_MASK 0x00000001 static __always_inline u64 xgetbv(u32 index) { u32 eax, edx; asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); return eax + ((u64)edx << 32); } static inline void xsetbv(u32 index, u64 value) { u32 eax = value; u32 edx = value >> 32; asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } /* * Return a mask of xfeatures which are currently being tracked * by the processor as being not in the initial configuration. * * Callers should check X86_FEATURE_XGETBV1. */ static __always_inline u64 xfeatures_in_use(void) { return xgetbv(XCR_XFEATURE_IN_USE_MASK); } #endif /* _ASM_X86_FPU_XCR_H */ |
| 50 16 21 15 86 86 94 30 25 13 133 4 629 68 25 25 25 25 13 13 13 1 2 2 1 1 7 7 6 6 1 1 7 2 1 2 25 68 90 90 69 23 32 31 37 37 1 1 1 1 1 1 1 1 1 109 16 49 32 15 94 4 4 4 1 1 4 63 3 15 4 41 31 1 30 13 68 68 68 56 1 12 12 13 13 68 68 56 13 68 56 56 56 12 12 12 5 16 5 5 4 4 5 11 11 14 13 12 12 12 23 23 23 23 22 12 16 5 16 2 3 3 2 1 1 14 2 2 2 2 2 15 2 7 6 6 3 3 46 31 13 88 85 86 86 60 60 6 3 9 8 6 35 35 34 26 9 4 80 4 16 6 80 20 95 60 35 78 38 2 4 36 26 2 14 32 3 11 14 16 13 124 123 4 120 118 2 20 7 3 70 28 38 65 100 26 88 11 35 75 19 9 3 8 75 15 61 4 80 81 57 15 7 2 42 42 32 39 8 8 8 2515 2518 12 8 8 638 11 571 210 628 12 12 12 12 12 12 12 12 12 19 19 19 19 7 12 19 18 7 12 150 4 4 4 4 4 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved. * Copyright (c) 1999-2019, Mellanox Technologies, Inc. All rights reserved. * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. */ #include <linux/completion.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rbtree.h> #include <linux/igmp.h> #include <linux/xarray.h> #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/module.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netevent.h> #include <net/tcp.h> #include <net/ipv6.h> #include <net/ip_fib.h> #include <net/ip6_route.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/rdma_netlink.h> #include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> #include <rdma/iw_cm.h> #include "core_priv.h" #include "cma_priv.h" #include "cma_trace.h" MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("Generic RDMA CM Agent"); MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_IBOE_PACKET_LIFETIME 16 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP static const char * const cma_events[] = { [RDMA_CM_EVENT_ADDR_RESOLVED] = "address resolved", [RDMA_CM_EVENT_ADDR_ERROR] = "address error", [RDMA_CM_EVENT_ROUTE_RESOLVED] = "route resolved ", [RDMA_CM_EVENT_ROUTE_ERROR] = "route error", [RDMA_CM_EVENT_CONNECT_REQUEST] = "connect request", [RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response", [RDMA_CM_EVENT_CONNECT_ERROR] = "connect error", [RDMA_CM_EVENT_UNREACHABLE] = "unreachable", [RDMA_CM_EVENT_REJECTED] = "rejected", [RDMA_CM_EVENT_ESTABLISHED] = "established", [RDMA_CM_EVENT_DISCONNECTED] = "disconnected", [RDMA_CM_EVENT_DEVICE_REMOVAL] = "device removal", [RDMA_CM_EVENT_MULTICAST_JOIN] = "multicast join", [RDMA_CM_EVENT_MULTICAST_ERROR] = "multicast error", [RDMA_CM_EVENT_ADDR_CHANGE] = "address change", [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type); static void cma_netevent_work_handler(struct work_struct *_work); const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { size_t index = event; return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ? cma_events[index] : "unrecognized event"; } EXPORT_SYMBOL(rdma_event_msg); const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return ibcm_reject_msg(reason); if (rdma_protocol_iwarp(id->device, id->port_num)) return iwcm_reject_msg(reason); WARN_ON_ONCE(1); return "unrecognized transport"; } EXPORT_SYMBOL(rdma_reject_msg); /** * rdma_is_consumer_reject - return true if the consumer rejected the connect * request. * @id: Communication identifier that received the REJECT event. * @reason: Value returned in the REJECT event status field. */ static bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return reason == IB_CM_REJ_CONSUMER_DEFINED; if (rdma_protocol_iwarp(id->device, id->port_num)) return reason == -ECONNREFUSED; WARN_ON_ONCE(1); return false; } const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len) { const void *p; if (rdma_is_consumer_reject(id, ev->status)) { *data_len = ev->param.conn.private_data_len; p = ev->param.conn.private_data; } else { *data_len = 0; p = NULL; } return p; } EXPORT_SYMBOL(rdma_consumer_reject_data); /** * rdma_iw_cm_id() - return the iw_cm_id pointer for this cm_id. * @id: Communication Identifier */ struct iw_cm_id *rdma_iw_cm_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); if (id->device->node_type == RDMA_NODE_RNIC) return id_priv->cm_id.iw; return NULL; } EXPORT_SYMBOL(rdma_iw_cm_id); static int cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device, void *client_data); static struct ib_client cma_client = { .name = "cma", .add = cma_add_one, .remove = cma_remove_one }; static struct ib_sa_client sa_client; static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct rb_root id_table = RB_ROOT; /* Serialize operations of id_table tree */ static DEFINE_SPINLOCK(id_table_lock); static struct workqueue_struct *cma_wq; static unsigned int cma_pernet_id; struct cma_pernet { struct xarray tcp_ps; struct xarray udp_ps; struct xarray ipoib_ps; struct xarray ib_ps; }; static struct cma_pernet *cma_pernet(struct net *net) { return net_generic(net, cma_pernet_id); } static struct xarray *cma_pernet_xa(struct net *net, enum rdma_ucm_port_space ps) { struct cma_pernet *pernet = cma_pernet(net); switch (ps) { case RDMA_PS_TCP: return &pernet->tcp_ps; case RDMA_PS_UDP: return &pernet->udp_ps; case RDMA_PS_IPOIB: return &pernet->ipoib_ps; case RDMA_PS_IB: return &pernet->ib_ps; default: return NULL; } } struct id_table_entry { struct list_head id_list; struct rb_node rb_node; }; struct cma_device { struct list_head list; struct ib_device *device; struct completion comp; refcount_t refcount; struct list_head id_list; enum ib_gid_type *default_gid_type; u8 *default_roce_tos; }; struct rdma_bind_list { enum rdma_ucm_port_space ps; struct hlist_head owners; unsigned short port; }; static int cma_ps_alloc(struct net *net, enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_insert(xa, snum, bind_list, GFP_KERNEL); } static struct rdma_bind_list *cma_ps_find(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_load(xa, snum); } static void cma_ps_remove(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); xa_erase(xa, snum); } enum { CMA_OPTION_AFONLY, }; void cma_dev_get(struct cma_device *cma_dev) { refcount_inc(&cma_dev->refcount); } void cma_dev_put(struct cma_device *cma_dev) { if (refcount_dec_and_test(&cma_dev->refcount)) complete(&cma_dev->comp); } struct cma_device *cma_enum_devices_by_ibdev(cma_device_filter filter, void *cookie) { struct cma_device *cma_dev; struct cma_device *found_cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) if (filter(cma_dev->device, cookie)) { found_cma_dev = cma_dev; break; } if (found_cma_dev) cma_dev_get(found_cma_dev); mutex_unlock(&lock); return found_cma_dev; } int cma_get_default_gid_type(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_gid_type(struct cma_device *cma_dev, u32 port, enum ib_gid_type default_gid_type) { unsigned long supported_gids; if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; if (default_gid_type == IB_GID_TYPE_IB && rdma_protocol_roce_eth_encap(cma_dev->device, port)) default_gid_type = IB_GID_TYPE_ROCE; supported_gids = roce_gid_type_mask_support(cma_dev->device, port); if (!(supported_gids & 1 << default_gid_type)) return -EINVAL; cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)] = default_gid_type; return 0; } int cma_get_default_roce_tos(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_roce_tos(struct cma_device *cma_dev, u32 port, u8 default_roce_tos) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)] = default_roce_tos; return 0; } struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev) { return cma_dev->device; } /* * Device removal can occur at anytime, so we need extra handling to * serialize notifying the user of device removal with other callbacks. * We do this by disabling removal notification while a callback is in process, * and reporting it after the callback completes. */ struct cma_multicast { struct rdma_id_private *id_priv; union { struct ib_sa_multicast *sa_mc; struct { struct work_struct work; struct rdma_cm_event event; } iboe_join; }; struct list_head list; void *context; struct sockaddr_storage addr; u8 join_state; }; struct cma_work { struct work_struct work; struct rdma_id_private *id; enum rdma_cm_state old_state; enum rdma_cm_state new_state; struct rdma_cm_event event; }; union cma_ip_addr { struct in6_addr ip6; struct { __be32 pad[3]; __be32 addr; } ip4; }; struct cma_hdr { u8 cma_version; u8 ip_version; /* IP version: 7:4 */ __be16 port; union cma_ip_addr src_addr; union cma_ip_addr dst_addr; }; #define CMA_VERSION 0x00 struct cma_req_info { struct sockaddr_storage listen_addr_storage; struct sockaddr_storage src_addr_storage; struct ib_device *device; union ib_gid local_gid; __be64 service_id; int port; bool has_gid; u16 pkey; }; static int cma_comp_exch(struct rdma_id_private *id_priv, enum rdma_cm_state comp, enum rdma_cm_state exch) { unsigned long flags; int ret; /* * The FSM uses a funny double locking where state is protected by both * the handler_mutex and the spinlock. State is not allowed to change * to/from a handler_mutex protected value without also holding * handler_mutex. */ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT) lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); if ((ret = (id_priv->state == comp))) id_priv->state = exch; spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } static inline u8 cma_get_ip_ver(const struct cma_hdr *hdr) { return hdr->ip_version >> 4; } static void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) { hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } static struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.src_addr; } static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.dst_addr; } static int cma_igmp_send(struct net_device *ndev, union ib_gid *mgid, bool join) { struct in_device *in_dev = NULL; if (ndev) { rtnl_lock(); in_dev = __in_dev_get_rtnl(ndev); if (in_dev) { if (join) ip_mc_inc_group(in_dev, *(__be32 *)(mgid->raw + 12)); else ip_mc_dec_group(in_dev, *(__be32 *)(mgid->raw + 12)); } rtnl_unlock(); } return (in_dev) ? 0 : -ENODEV; } static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa, struct id_table_entry *entry_b) { struct rdma_id_private *id_priv = list_first_entry( &entry_b->id_list, struct rdma_id_private, id_list_entry); int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if; struct sockaddr *sb = cma_dst_addr(id_priv); if (ifindex_a != ifindex_b) return (ifindex_a > ifindex_b) ? 1 : -1; if (sa->sa_family != sb->sa_family) return sa->sa_family - sb->sa_family; if (sa->sa_family == AF_INET && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in)) { return memcmp(&((struct sockaddr_in *)sa)->sin_addr, &((struct sockaddr_in *)sb)->sin_addr, sizeof(((struct sockaddr_in *)sa)->sin_addr)); } if (sa->sa_family == AF_INET6 && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in6)) { return ipv6_addr_cmp(&((struct sockaddr_in6 *)sa)->sin6_addr, &((struct sockaddr_in6 *)sb)->sin6_addr); } return -1; } static int cma_add_id_to_tree(struct rdma_id_private *node_id_priv) { struct rb_node **new, *parent = NULL; struct id_table_entry *this, *node; unsigned long flags; int result; node = kzalloc_obj(*node); if (!node) return -ENOMEM; spin_lock_irqsave(&id_table_lock, flags); new = &id_table.rb_node; while (*new) { this = container_of(*new, struct id_table_entry, rb_node); result = compare_netdev_and_ip( node_id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(node_id_priv), this); parent = *new; if (result < 0) new = &((*new)->rb_left); else if (result > 0) new = &((*new)->rb_right); else { list_add_tail(&node_id_priv->id_list_entry, &this->id_list); kfree(node); goto unlock; } } INIT_LIST_HEAD(&node->id_list); list_add_tail(&node_id_priv->id_list_entry, &node->id_list); rb_link_node(&node->rb_node, parent, new); rb_insert_color(&node->rb_node, &id_table); unlock: spin_unlock_irqrestore(&id_table_lock, flags); return 0; } static struct id_table_entry * node_from_ndev_ip(struct rb_root *root, int ifindex, struct sockaddr *sa) { struct rb_node *node = root->rb_node; struct id_table_entry *data; int result; while (node) { data = container_of(node, struct id_table_entry, rb_node); result = compare_netdev_and_ip(ifindex, sa, data); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return data; } return NULL; } static void cma_remove_id_from_tree(struct rdma_id_private *id_priv) { struct id_table_entry *data; unsigned long flags; spin_lock_irqsave(&id_table_lock, flags); if (list_empty(&id_priv->id_list_entry)) goto out; data = node_from_ndev_ip(&id_table, id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(id_priv)); if (!data) goto out; list_del_init(&id_priv->id_list_entry); if (list_empty(&data->id_list)) { rb_erase(&data->rb_node, &id_table); kfree(data); } out: spin_unlock_irqrestore(&id_table_lock, flags); } static void _cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { cma_dev_get(cma_dev); id_priv->cma_dev = cma_dev; id_priv->id.device = cma_dev->device; id_priv->id.route.addr.dev_addr.transport = rdma_node_get_transport(cma_dev->device->node_type); list_add_tail(&id_priv->device_item, &cma_dev->id_list); trace_cm_id_attach(id_priv, cma_dev->device); } static void cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { _cma_attach_to_dev(id_priv, cma_dev); id_priv->gid_type = cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(cma_dev->device)]; } static void cma_release_dev(struct rdma_id_private *id_priv) { mutex_lock(&lock); list_del_init(&id_priv->device_item); cma_dev_put(id_priv->cma_dev); id_priv->cma_dev = NULL; id_priv->id.device = NULL; if (id_priv->id.route.addr.dev_addr.sgid_attr) { rdma_put_gid_attr(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = NULL; } mutex_unlock(&lock); } static inline unsigned short cma_family(struct rdma_id_private *id_priv) { return id_priv->id.route.addr.src_addr.ss_family; } static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0; switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: id_priv->qkey = RDMA_UDP_QKEY; break; case RDMA_PS_IPOIB: ib_addr_get_mgid(&id_priv->id.route.addr.dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (!ret) id_priv->qkey = be32_to_cpu(rec.qkey); break; default: break; } return ret; } static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) { if (!qkey || (id_priv->qkey && (id_priv->qkey != qkey))) return -EINVAL; id_priv->qkey = qkey; return 0; } static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(dev_addr, (union ib_gid *) &sib->sib_addr); ib_addr_set_pkey(dev_addr, ntohs(sib->sib_pkey)); } static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) { int ret; if (addr->sa_family != AF_IB) { ret = rdma_translate_ip(addr, dev_addr); } else { cma_translate_ib((struct sockaddr_ib *) addr, dev_addr); ret = 0; } return ret; } static const struct ib_gid_attr * cma_validate_port(struct ib_device *device, u32 port, enum ib_gid_type gid_type, union ib_gid *gid, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr = ERR_PTR(-ENODEV); int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; struct net_device *pdev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port)) goto out; if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) goto out; /* * For drivers that do not associate more than one net device with * their gid tables, such as iWARP drivers, it is sufficient to * return the first table entry. * * Other driver classes might be included in the future. */ if (rdma_protocol_iwarp(device, port)) { sgid_attr = rdma_get_gid_attr(device, port, 0); if (IS_ERR(sgid_attr)) goto out; rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); if (ndev->ifindex != bound_if_index) { pdev = dev_get_by_index_rcu(dev_addr->net, bound_if_index); if (pdev) { if (is_vlan_dev(pdev)) { pdev = vlan_dev_real_dev(pdev); if (ndev->ifindex == pdev->ifindex) bound_if_index = pdev->ifindex; } if (is_vlan_dev(ndev)) { pdev = vlan_dev_real_dev(ndev); if (bound_if_index == pdev->ifindex) bound_if_index = ndev->ifindex; } } } if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); sgid_attr = ERR_PTR(-ENODEV); } rcu_read_unlock(); goto out; } /* * For a RXE device, it should work with TUN device and normal ethernet * devices. Use driver_id to check if a device is a RXE device or not. * ARPHDR_NONE means a TUN device. */ if (device->ops.driver_id == RDMA_DRIVER_RXE) { if ((dev_type == ARPHRD_NONE || dev_type == ARPHRD_ETHER) && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } } else { if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } else { gid_type = IB_GID_TYPE_IB; } } sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev); dev_put(ndev); out: return sgid_attr; } static void cma_bind_sgid_attr(struct rdma_id_private *id_priv, const struct ib_gid_attr *sgid_attr) { WARN_ON(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = sgid_attr; } /** * cma_acquire_dev_by_src_ip - Acquire cma device, port, gid attribute * based on source ip address. * @id_priv: cm_id which should be bound to cma device * * cma_acquire_dev_by_src_ip() binds cm id to cma device, port and GID attribute * based on source IP address. It returns 0 on success or error code otherwise. * It is applicable to active and passive side cm_id. */ static int cma_acquire_dev_by_src_ip(struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; union ib_gid gid, iboe_gid, *gidp; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &iboe_gid); memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) { if (id_priv->restricted_node_type != RDMA_NODE_UNSPECIFIED && id_priv->restricted_node_type != cma_dev->device->node_type) continue; rdma_for_each_port (cma_dev->device, port) { gidp = rdma_protocol_roce(cma_dev->device, port) ? &iboe_gid : &gid; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, gidp, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); cma_attach_to_dev(id_priv, cma_dev); ret = 0; goto out; } } } out: mutex_unlock(&lock); return ret; } /** * cma_ib_acquire_dev - Acquire cma device, port and SGID attribute * @id_priv: cm id to bind to cma device * @listen_id_priv: listener cm id to match against * @req: Pointer to req structure containaining incoming * request information * cma_ib_acquire_dev() acquires cma device, port and SGID attribute when * rdma device matches for listen_id and incoming request. It also verifies * that a GID table entry is present for the source address. * Returns 0 on success, or returns error code otherwise. */ static int cma_ib_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv, struct cma_req_info *req) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; enum ib_gid_type gid_type; union ib_gid gid; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; if (rdma_protocol_roce(req->device, req->port)) rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &gid); else memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); gid_type = listen_id_priv->cma_dev->default_gid_type[req->port - 1]; sgid_attr = cma_validate_port(req->device, req->port, gid_type, &gid, id_priv); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); id_priv->id.port_num = req->port; cma_bind_sgid_attr(id_priv, sgid_attr); /* Need to acquire lock to protect against reader * of cma_dev->id_list such as cma_netdev_callback() and * cma_process_remove(). */ mutex_lock(&lock); cma_attach_to_dev(id_priv, listen_id_priv->cma_dev); mutex_unlock(&lock); rdma_restrack_add(&id_priv->res); return 0; } static int cma_iw_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; union ib_gid gid; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); cma_dev = listen_id_priv->cma_dev; port = listen_id_priv->id.port_num; gid_type = listen_id_priv->gid_type; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { if (listen_id_priv->cma_dev == cma_dev && listen_id_priv->id.port_num == port) continue; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } } } out: if (!ret) { cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); } mutex_unlock(&lock); return ret; } /* * Select the source IB device and address to reach the destination IB address. */ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; struct sockaddr_ib *addr; union ib_gid gid, sgid, *dgid; unsigned int p; u16 pkey, index; enum ib_port_state port_state; int ret; int i; cma_dev = NULL; addr = (struct sockaddr_ib *) cma_dst_addr(id_priv); dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { rdma_for_each_port (cur_dev->device, p) { if (!rdma_cap_af_ib(cur_dev->device, p)) continue; if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) continue; if (ib_get_cached_port_state(cur_dev->device, p, &port_state)) continue; for (i = 0; i < cur_dev->device->port_data[p].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(cur_dev->device, p, i, &gid); if (ret) continue; if (!memcmp(&gid, dgid, sizeof(gid))) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } if (!cma_dev && (gid.global.subnet_prefix == dgid->global.subnet_prefix) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } } } } mutex_unlock(&lock); return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); mutex_unlock(&lock); addr = (struct sockaddr_ib *)cma_src_addr(id_priv); memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } static void cma_id_get(struct rdma_id_private *id_priv) { refcount_inc(&id_priv->refcount); } static void cma_id_put(struct rdma_id_private *id_priv) { if (refcount_dec_and_test(&id_priv->refcount)) complete(&id_priv->comp); } static struct rdma_id_private * __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const struct rdma_id_private *parent) { struct rdma_id_private *id_priv; id_priv = kzalloc_obj(*id_priv); if (!id_priv) return ERR_PTR(-ENOMEM); id_priv->state = RDMA_CM_IDLE; id_priv->restricted_node_type = RDMA_NODE_UNSPECIFIED; id_priv->id.context = context; id_priv->id.event_handler = event_handler; id_priv->id.ps = ps; id_priv->id.qp_type = qp_type; id_priv->tos_set = false; id_priv->timeout_set = false; id_priv->min_rnr_timer_set = false; id_priv->gid_type = IB_GID_TYPE_IB; spin_lock_init(&id_priv->lock); mutex_init(&id_priv->qp_mutex); init_completion(&id_priv->comp); refcount_set(&id_priv->refcount, 1); mutex_init(&id_priv->handler_mutex); INIT_LIST_HEAD(&id_priv->device_item); INIT_LIST_HEAD(&id_priv->id_list_entry); INIT_LIST_HEAD(&id_priv->listen_list); INIT_LIST_HEAD(&id_priv->mc_list); get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num); id_priv->id.route.addr.dev_addr.net = get_net(net); id_priv->seq_num &= 0x00ffffff; INIT_WORK(&id_priv->id.net_work, cma_netevent_work_handler); rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID); if (parent) rdma_restrack_parent_name(&id_priv->res, &parent->res); return id_priv; } struct rdma_cm_id * __rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const char *caller) { struct rdma_id_private *ret; ret = __rdma_create_id(net, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, caller); return &ret->id; } EXPORT_SYMBOL(__rdma_create_kernel_id); struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type) { struct rdma_id_private *ret; ret = __rdma_create_id(current->nsproxy->net_ns, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, NULL); return &ret->id; } EXPORT_SYMBOL(rdma_create_user_id); static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTR; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTS; qp_attr.sq_psn = 0; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE | IB_QP_SQ_PSN); return ret; } static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; return ib_modify_qp(qp, &qp_attr, qp_attr_mask); } int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr) { struct rdma_id_private *id_priv; struct ib_qp *qp; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (id->device != pd->device) { ret = -EINVAL; goto out_err; } qp_init_attr->port_num = id->port_num; qp = ib_create_qp(pd, qp_init_attr); if (IS_ERR(qp)) { ret = PTR_ERR(qp); goto out_err; } if (id->qp_type == IB_QPT_UD) ret = cma_init_ud_qp(id_priv, qp); else ret = cma_init_conn_qp(id_priv, qp); if (ret) goto out_destroy; id->qp = qp; id_priv->qp_num = qp->qp_num; id_priv->srq = (qp->srq != NULL); trace_cm_qp_create(id_priv, pd, qp_init_attr, 0); return 0; out_destroy: ib_destroy_qp(qp); out_err: trace_cm_qp_create(id_priv, pd, qp_init_attr, ret); return ret; } EXPORT_SYMBOL(rdma_create_qp); void rdma_destroy_qp(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); trace_cm_qp_destroy(id_priv); mutex_lock(&id_priv->qp_mutex); ib_destroy_qp(id_priv->id.qp); id_priv->id.qp = NULL; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_destroy_qp); static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } /* Need to update QP attributes from default values. */ qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); if (ret) goto out; qp_attr.qp_state = IB_QPS_RTR; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; BUG_ON(id_priv->cma_dev->device != id_priv->id.device); if (conn_param) qp_attr.max_dest_rd_atomic = conn_param->responder_resources; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_rts(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_RTS; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; if (conn_param) qp_attr.max_rd_atomic = conn_param->initiator_depth; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_err(struct rdma_id_private *id_priv) { struct ib_qp_attr qp_attr; int ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_ERR; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, IB_QP_STATE); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int ret; u16 pkey; if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num)) pkey = 0xffff; else pkey = ib_addr_get_pkey(dev_addr); ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, pkey, &qp_attr->pkey_index); if (ret) return ret; qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; qp_attr->qkey = id_priv->qkey; *qp_attr_mask |= IB_QP_QKEY; } else { qp_attr->qp_access_flags = 0; *qp_attr_mask |= IB_QP_ACCESS_FLAGS; } return 0; } int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_id_private *id_priv; int ret = 0; id_priv = container_of(id, struct rdma_id_private, id); if (rdma_cap_ib_cm(id->device, id->port_num)) { if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD)) ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask); else ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr, qp_attr_mask); if (qp_attr->qp_state == IB_QPS_RTR) qp_attr->rq_psn = id_priv->seq_num; } else if (rdma_cap_iw_cm(id->device, id->port_num)) { if (!id_priv->cm_id.iw) { qp_attr->qp_access_flags = 0; *qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS; } else ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr, qp_attr_mask); qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask |= IB_QP_PORT; } else { ret = -ENOSYS; } if ((*qp_attr_mask & IB_QP_TIMEOUT) && id_priv->timeout_set) qp_attr->timeout = id_priv->timeout; if ((*qp_attr_mask & IB_QP_MIN_RNR_TIMER) && id_priv->min_rnr_timer_set) qp_attr->min_rnr_timer = id_priv->min_rnr_timer; return ret; } EXPORT_SYMBOL(rdma_init_qp_attr); static inline bool cma_zero_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_any(&((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_any(&((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_loopback_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_loopback( ((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_loopback( &((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_loopback( &((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_any_addr(const struct sockaddr *addr) { return cma_zero_addr(addr) || cma_loopback_addr(addr); } static int cma_addr_cmp(const struct sockaddr *src, const struct sockaddr *dst) { if (src->sa_family != dst->sa_family) return -1; switch (src->sa_family) { case AF_INET: return ((struct sockaddr_in *)src)->sin_addr.s_addr != ((struct sockaddr_in *)dst)->sin_addr.s_addr; case AF_INET6: { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)src; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst; bool link_local; if (ipv6_addr_cmp(&src_addr6->sin6_addr, &dst_addr6->sin6_addr)) return 1; link_local = ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL; /* Link local must match their scope_ids */ return link_local ? (src_addr6->sin6_scope_id != dst_addr6->sin6_scope_id) : 0; } default: return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, &((struct sockaddr_ib *) dst)->sib_addr); } } static __be16 cma_port(const struct sockaddr *addr) { struct sockaddr_ib *sib; switch (addr->sa_family) { case AF_INET: return ((struct sockaddr_in *) addr)->sin_port; case AF_INET6: return ((struct sockaddr_in6 *) addr)->sin6_port; case AF_IB: sib = (struct sockaddr_ib *) addr; return htons((u16) (be64_to_cpu(sib->sib_sid) & be64_to_cpu(sib->sib_sid_mask))); default: return 0; } } static inline int cma_any_port(const struct sockaddr *addr) { return !cma_port(addr); } static void cma_save_ib_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct sa_path_rec *path) { struct sockaddr_ib *listen_ib, *ib; listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr; if (src_addr) { ib = (struct sockaddr_ib *)src_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->sgid, 16); ib->sib_sid = path->service_id; ib->sib_scope_id = 0; } else { ib->sib_pkey = listen_ib->sib_pkey; ib->sib_flowinfo = listen_ib->sib_flowinfo; ib->sib_addr = listen_ib->sib_addr; ib->sib_sid = listen_ib->sib_sid; ib->sib_scope_id = listen_ib->sib_scope_id; } ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL); } if (dst_addr) { ib = (struct sockaddr_ib *)dst_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->dgid, 16); } } } static void cma_save_ip4_info(struct sockaddr_in *src_addr, struct sockaddr_in *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->dst_addr.ip4.addr, .sin_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->src_addr.ip4.addr, .sin_port = hdr->port, }; } } static void cma_save_ip6_info(struct sockaddr_in6 *src_addr, struct sockaddr_in6 *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->dst_addr.ip6, .sin6_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->src_addr.ip6, .sin6_port = hdr->port, }; } } static u16 cma_port_from_service_id(__be64 service_id) { return (u16)be64_to_cpu(service_id); } static int cma_save_ip_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct ib_cm_event *ib_event, __be64 service_id) { struct cma_hdr *hdr; __be16 port; hdr = ib_event->private_data; if (hdr->cma_version != CMA_VERSION) return -EINVAL; port = htons(cma_port_from_service_id(service_id)); switch (cma_get_ip_ver(hdr)) { case 4: cma_save_ip4_info((struct sockaddr_in *)src_addr, (struct sockaddr_in *)dst_addr, hdr, port); break; case 6: cma_save_ip6_info((struct sockaddr_in6 *)src_addr, (struct sockaddr_in6 *)dst_addr, hdr, port); break; default: return -EAFNOSUPPORT; } return 0; } static int cma_save_net_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, sa_family_t sa_family, __be64 service_id) { if (sa_family == AF_IB) { if (ib_event->event == IB_CM_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, ib_event->param.req_rcvd.primary_path); else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, NULL); return 0; } return cma_save_ip_info(src_addr, dst_addr, ib_event, service_id); } static int cma_save_req_info(const struct ib_cm_event *ib_event, struct cma_req_info *req) { const struct ib_cm_req_event_param *req_param = &ib_event->param.req_rcvd; const struct ib_cm_sidr_req_event_param *sidr_param = &ib_event->param.sidr_req_rcvd; switch (ib_event->event) { case IB_CM_REQ_RECEIVED: req->device = req_param->listen_id->device; req->port = req_param->port; memcpy(&req->local_gid, &req_param->primary_path->sgid, sizeof(req->local_gid)); req->has_gid = true; req->service_id = req_param->primary_path->service_id; req->pkey = be16_to_cpu(req_param->primary_path->pkey); if (req->pkey != req_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and primary path P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", req_param->bth_pkey, req->pkey); break; case IB_CM_SIDR_REQ_RECEIVED: req->device = sidr_param->listen_id->device; req->port = sidr_param->port; req->has_gid = false; req->service_id = sidr_param->service_id; req->pkey = sidr_param->pkey; if (req->pkey != sidr_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and SIDR request payload P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", sidr_param->bth_pkey, req->pkey); break; default: return -EINVAL; } return 0; } static bool validate_ipv4_net_dev(struct net_device *net_dev, const struct sockaddr_in *dst_addr, const struct sockaddr_in *src_addr) { __be32 daddr = dst_addr->sin_addr.s_addr, saddr = src_addr->sin_addr.s_addr; struct fib_result res; struct flowi4 fl4; int err; bool ret; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || ipv4_is_lbcast(daddr) || ipv4_is_zeronet(saddr) || ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr) || ipv4_is_loopback(saddr)) return false; memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; rcu_read_lock(); err = fib_lookup(dev_net(net_dev), &fl4, &res, 0); ret = err == 0 && FIB_RES_DEV(res) == net_dev; rcu_read_unlock(); return ret; } static bool validate_ipv6_net_dev(struct net_device *net_dev, const struct sockaddr_in6 *dst_addr, const struct sockaddr_in6 *src_addr) { #if IS_ENABLED(CONFIG_IPV6) const int strict = ipv6_addr_type(&dst_addr->sin6_addr) & IPV6_ADDR_LINKLOCAL; struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr, &src_addr->sin6_addr, net_dev->ifindex, NULL, strict); bool ret; if (!rt) return false; ret = rt->rt6i_idev->dev == net_dev; ip6_rt_put(rt); return ret; #else return false; #endif } static bool validate_net_dev(struct net_device *net_dev, const struct sockaddr *daddr, const struct sockaddr *saddr) { const struct sockaddr_in *daddr4 = (const struct sockaddr_in *)daddr; const struct sockaddr_in *saddr4 = (const struct sockaddr_in *)saddr; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; const struct sockaddr_in6 *saddr6 = (const struct sockaddr_in6 *)saddr; switch (daddr->sa_family) { case AF_INET: return saddr->sa_family == AF_INET && validate_ipv4_net_dev(net_dev, daddr4, saddr4); case AF_INET6: return saddr->sa_family == AF_INET6 && validate_ipv6_net_dev(net_dev, daddr6, saddr6); default: return false; } } static struct net_device * roce_get_net_dev_by_cm_event(const struct ib_cm_event *ib_event) { const struct ib_gid_attr *sgid_attr = NULL; struct net_device *ndev; if (ib_event->event == IB_CM_REQ_RECEIVED) sgid_attr = ib_event->param.req_rcvd.ppath_sgid_attr; else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) sgid_attr = ib_event->param.sidr_req_rcvd.sgid_attr; if (!sgid_attr) return NULL; rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(sgid_attr); if (IS_ERR(ndev)) ndev = NULL; else dev_hold(ndev); rcu_read_unlock(); return ndev; } static struct net_device *cma_get_net_dev(const struct ib_cm_event *ib_event, struct cma_req_info *req) { struct sockaddr *listen_addr = (struct sockaddr *)&req->listen_addr_storage; struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage; struct net_device *net_dev; const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL; int err; err = cma_save_ip_info(listen_addr, src_addr, ib_event, req->service_id); if (err) return ERR_PTR(err); if (rdma_protocol_roce(req->device, req->port)) net_dev = roce_get_net_dev_by_cm_event(ib_event); else net_dev = ib_get_net_dev_by_params(req->device, req->port, req->pkey, gid, listen_addr); if (!net_dev) return ERR_PTR(-ENODEV); return net_dev; } static enum rdma_ucm_port_space rdma_ps_from_service_id(__be64 service_id) { return (be64_to_cpu(service_id) >> 16) & 0xffff; } static bool cma_match_private_data(struct rdma_id_private *id_priv, const struct cma_hdr *hdr) { struct sockaddr *addr = cma_src_addr(id_priv); __be32 ip4_addr; struct in6_addr ip6_addr; if (cma_any_addr(addr) && !id_priv->afonly) return true; switch (addr->sa_family) { case AF_INET: ip4_addr = ((struct sockaddr_in *)addr)->sin_addr.s_addr; if (cma_get_ip_ver(hdr) != 4) return false; if (!cma_any_addr(addr) && hdr->dst_addr.ip4.addr != ip4_addr) return false; break; case AF_INET6: ip6_addr = ((struct sockaddr_in6 *)addr)->sin6_addr; if (cma_get_ip_ver(hdr) != 6) return false; if (!cma_any_addr(addr) && memcmp(&hdr->dst_addr.ip6, &ip6_addr, sizeof(ip6_addr))) return false; break; case AF_IB: return true; default: return false; } return true; } static bool cma_protocol_roce(const struct rdma_cm_id *id) { struct ib_device *device = id->device; const u32 port_num = id->port_num ?: rdma_start_port(device); return rdma_protocol_roce(device, port_num); } static bool cma_is_req_ipv6_ll(const struct cma_req_info *req) { const struct sockaddr *daddr = (const struct sockaddr *)&req->listen_addr_storage; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; /* Returns true if the req is for IPv6 link local */ return (daddr->sa_family == AF_INET6 && (ipv6_addr_type(&daddr6->sin6_addr) & IPV6_ADDR_LINKLOCAL)); } static bool cma_match_net_dev(const struct rdma_cm_id *id, const struct net_device *net_dev, const struct cma_req_info *req) { const struct rdma_addr *addr = &id->route.addr; if (!net_dev) /* This request is an AF_IB request */ return (!id->port_num || id->port_num == req->port) && (addr->src_addr.ss_family == AF_IB); /* * If the request is not for IPv6 link local, allow matching * request to any netdevice of the one or multiport rdma device. */ if (!cma_is_req_ipv6_ll(req)) return true; /* * Net namespaces must match, and if the listner is listening * on a specific netdevice than netdevice must match as well. */ if (net_eq(dev_net(net_dev), addr->dev_addr.net) && (!!addr->dev_addr.bound_dev_if == (addr->dev_addr.bound_dev_if == net_dev->ifindex))) return true; else return false; } static struct rdma_id_private *cma_find_listener( const struct rdma_bind_list *bind_list, const struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, const struct cma_req_info *req, const struct net_device *net_dev) { struct rdma_id_private *id_priv, *id_priv_dev; lockdep_assert_held(&lock); if (!bind_list) return ERR_PTR(-EINVAL); hlist_for_each_entry(id_priv, &bind_list->owners, node) { if (cma_match_private_data(id_priv, ib_event->private_data)) { if (id_priv->id.device == cm_id->device && cma_match_net_dev(&id_priv->id, net_dev, req)) return id_priv; list_for_each_entry(id_priv_dev, &id_priv->listen_list, listen_item) { if (id_priv_dev->id.device == cm_id->device && cma_match_net_dev(&id_priv_dev->id, net_dev, req)) return id_priv_dev; } } } return ERR_PTR(-EINVAL); } static struct rdma_id_private * cma_ib_id_from_event(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, struct cma_req_info *req, struct net_device **net_dev) { struct rdma_bind_list *bind_list; struct rdma_id_private *id_priv; int err; err = cma_save_req_info(ib_event, req); if (err) return ERR_PTR(err); *net_dev = cma_get_net_dev(ib_event, req); if (IS_ERR(*net_dev)) { if (PTR_ERR(*net_dev) == -EAFNOSUPPORT) { /* Assuming the protocol is AF_IB */ *net_dev = NULL; } else { return ERR_CAST(*net_dev); } } mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice * validation, cm_id lookup under rcu lock. * RCU lock along with netdevice state check, synchronizes with * netdevice migrating to different net namespace and also avoids * case where net namespace doesn't get deleted while lookup is in * progress. * If the device state is not IFF_UP, its properties such as ifindex * and nd_net cannot be trusted to remain valid without rcu lock. * net/core/dev.c change_net_namespace() ensures to synchronize with * ongoing operations on net device after device is closed using * synchronize_net(). */ rcu_read_lock(); if (*net_dev) { /* * If netdevice is down, it is likely that it is administratively * down or it might be migrating to different namespace. * In that case avoid further processing, as the net namespace * or ifindex may change. */ if (((*net_dev)->flags & IFF_UP) == 0) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } if (!validate_net_dev(*net_dev, (struct sockaddr *)&req->src_addr_storage, (struct sockaddr *)&req->listen_addr_storage)) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } } bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net, rdma_ps_from_service_id(req->service_id), cma_port_from_service_id(req->service_id)); id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; } return id_priv; } static inline u8 cma_user_data_offset(struct rdma_id_private *id_priv) { return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } static void cma_cancel_route(struct rdma_id_private *id_priv) { if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) { if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); } } static void _cma_cancel_listens(struct rdma_id_private *id_priv) { struct rdma_id_private *dev_id_priv; lockdep_assert_held(&lock); /* * Remove from listen_any_list to prevent added devices from spawning * additional listen requests. */ list_del_init(&id_priv->listen_any_item); while (!list_empty(&id_priv->listen_list)) { dev_id_priv = list_first_entry(&id_priv->listen_list, struct rdma_id_private, listen_item); /* sync with device removal to avoid duplicate destruction */ list_del_init(&dev_id_priv->device_item); list_del_init(&dev_id_priv->listen_item); mutex_unlock(&lock); rdma_destroy_id(&dev_id_priv->id); mutex_lock(&lock); } } static void cma_cancel_listens(struct rdma_id_private *id_priv) { mutex_lock(&lock); _cma_cancel_listens(id_priv); mutex_unlock(&lock); } static void cma_cancel_operation(struct rdma_id_private *id_priv, enum rdma_cm_state state) { switch (state) { case RDMA_CM_ADDR_QUERY: /* * We can avoid doing the rdma_addr_cancel() based on state, * only RDMA_CM_ADDR_QUERY has a work that could still execute. * Notice that the addr_handler work could still be exiting * outside this state, however due to the interaction with the * handler_mutex the work is guaranteed not to touch id_priv * during exit. */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: cma_cancel_route(id_priv); break; case RDMA_CM_LISTEN: if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) cma_cancel_listens(id_priv); break; default: break; } } static void cma_release_port(struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list = id_priv->bind_list; struct net *net = id_priv->id.route.addr.dev_addr.net; if (!bind_list) return; mutex_lock(&lock); hlist_del(&id_priv->node); if (hlist_empty(&bind_list->owners)) { cma_ps_remove(net, bind_list->ps, bind_list->port); kfree(bind_list); } mutex_unlock(&lock); } static void destroy_mc(struct rdma_id_private *id_priv, struct cma_multicast *mc) { bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) ib_sa_free_multicast(mc->sa_mc); if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct net_device *ndev = NULL; if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (ndev && !send_only) { enum ib_gid_type gid_type; union ib_gid mgid; gid_type = id_priv->cma_dev->default_gid_type [id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; cma_iboe_set_mgid((struct sockaddr *)&mc->addr, &mgid, gid_type); cma_igmp_send(ndev, &mgid, false); } dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&event->param.ud.ah_attr); } kfree(mc); } static void cma_leave_mc_groups(struct rdma_id_private *id_priv) { struct cma_multicast *mc; while (!list_empty(&id_priv->mc_list)) { mc = list_first_entry(&id_priv->mc_list, struct cma_multicast, list); list_del(&mc->list); destroy_mc(id_priv, mc); } } static void _destroy_id(struct rdma_id_private *id_priv, enum rdma_cm_state state) { cma_cancel_operation(id_priv, state); rdma_restrack_del(&id_priv->res); cma_remove_id_from_tree(id_priv); if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.ib) ib_destroy_cm_id(id_priv->cm_id.ib); } else if (rdma_cap_iw_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.iw) iw_destroy_cm_id(id_priv->cm_id.iw); } cma_leave_mc_groups(id_priv); cma_release_dev(id_priv); } cma_release_port(id_priv); cma_id_put(id_priv); wait_for_completion(&id_priv->comp); if (id_priv->internal_id) cma_id_put(id_priv->id.context); kfree(id_priv->id.route.path_rec); kfree(id_priv->id.route.path_rec_inbound); kfree(id_priv->id.route.path_rec_outbound); kfree(id_priv->id.route.service_recs); put_net(id_priv->id.route.addr.dev_addr.net); kfree(id_priv); } /* * destroy an ID from within the handler_mutex. This ensures that no other * handlers can start running concurrently. */ static void destroy_id_handler_unlock(struct rdma_id_private *id_priv) __releases(&idprv->handler_mutex) { enum rdma_cm_state state; unsigned long flags; trace_cm_id_destroy(id_priv); /* * Setting the state to destroyed under the handler mutex provides a * fence against calling handler callbacks. If this is invoked due to * the failure of a handler callback then it guarentees that no future * handlers will be called. */ lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; id_priv->state = RDMA_CM_DESTROYING; spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); _destroy_id(id_priv, state); } void rdma_destroy_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); destroy_id_handler_unlock(id_priv); } EXPORT_SYMBOL(rdma_destroy_id); static int cma_rep_recv(struct rdma_id_private *id_priv) { int ret; ret = cma_modify_qp_rtr(id_priv, NULL); if (ret) goto reject; ret = cma_modify_qp_rts(id_priv, NULL); if (ret) goto reject; trace_cm_send_rtu(id_priv); ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0); if (ret) goto reject; return 0; reject: pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret); cma_modify_qp_err(id_priv); trace_cm_send_rej(id_priv); ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, NULL, 0); return ret; } static void cma_set_rep_event_data(struct rdma_cm_event *event, const struct ib_cm_rep_event_param *rep_data, void *private_data) { event->param.conn.private_data = private_data; event->param.conn.private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE; event->param.conn.responder_resources = rep_data->responder_resources; event->param.conn.initiator_depth = rep_data->initiator_depth; event->param.conn.flow_control = rep_data->flow_control; event->param.conn.rnr_retry_count = rep_data->rnr_retry_count; event->param.conn.srq = rep_data->srq; event->param.conn.qp_num = rep_data->remote_qpn; event->ece.vendor_id = rep_data->ece.vendor_id; event->ece.attr_mod = rep_data->ece.attr_mod; } static int cma_cm_event_handler(struct rdma_id_private *id_priv, struct rdma_cm_event *event) { int ret; lockdep_assert_held(&id_priv->handler_mutex); trace_cm_event_handler(id_priv, event); ret = id_priv->id.event_handler(&id_priv->id, event); trace_cm_event_done(id_priv, event, ret); return ret; } static int cma_ib_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; enum rdma_cm_state state; int ret; mutex_lock(&id_priv->handler_mutex); state = READ_ONCE(id_priv->state); if ((ib_event->event != IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_CONNECT) || (ib_event->event == IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_DISCONNECT)) goto out; switch (ib_event->event) { case IB_CM_REQ_ERROR: case IB_CM_REP_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_REP_RECEIVED: if (state == RDMA_CM_CONNECT && (id_priv->id.qp_type != IB_QPT_UD)) { trace_cm_prepare_mra(id_priv); ib_prepare_cm_mra(cm_id); } if (id_priv->id.qp) { event.status = cma_rep_recv(id_priv); event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR : RDMA_CM_EVENT_ESTABLISHED; } else { event.event = RDMA_CM_EVENT_CONNECT_RESPONSE; } cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd, ib_event->private_data); break; case IB_CM_RTU_RECEIVED: case IB_CM_USER_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IB_CM_DREQ_ERROR: event.status = -ETIMEDOUT; fallthrough; case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_DISCONNECT)) goto out; event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IB_CM_TIMEWAIT_EXIT: event.event = RDMA_CM_EVENT_TIMEWAIT_EXIT; break; case IB_CM_MRA_RECEIVED: /* ignore event */ goto out; case IB_CM_REJ_RECEIVED: pr_debug_ratelimited("RDMA CM: REJECTED: %s\n", rdma_reject_msg(&id_priv->id, ib_event->param.rej_rcvd.reason)); cma_modify_qp_err(id_priv); event.status = ib_event->param.rej_rcvd.reason; event.event = RDMA_CM_EVENT_REJECTED; event.param.conn.private_data = ib_event->private_data; event.param.conn.private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static struct rdma_id_private * cma_ib_new_conn_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; struct rdma_route *rt; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct sa_path_rec *path = ib_event->param.req_rcvd.primary_path; const __be64 service_id = ib_event->param.req_rcvd.primary_path->service_id; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(listen_id->route.addr.dev_addr.net, listen_id->event_handler, listen_id->context, listen_id->ps, ib_event->param.req_rcvd.qp_type, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, service_id)) goto err; rt = &id->route; rt->num_pri_alt_paths = ib_event->param.req_rcvd.alternate_path ? 2 : 1; rt->path_rec = kmalloc_objs(*rt->path_rec, rt->num_pri_alt_paths); if (!rt->path_rec) goto err; rt->path_rec[0] = *path; if (rt->num_pri_alt_paths == 2) rt->path_rec[1] = *ib_event->param.req_rcvd.alternate_path; if (net_dev) { rdma_copy_src_l2_addr(&rt->addr.dev_addr, net_dev); } else { if (!cma_protocol_roce(listen_id) && cma_any_addr(cma_src_addr(id_priv))) { rt->addr.dev_addr.dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(&rt->addr.dev_addr, &rt->path_rec[0].sgid); ib_addr_set_pkey(&rt->addr.dev_addr, be16_to_cpu(rt->path_rec[0].pkey)); } else if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &rt->addr.dev_addr); if (ret) goto err; } } rdma_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid); id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static struct rdma_id_private * cma_ib_new_udp_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { const struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct net *net = listen_id->route.addr.dev_addr.net; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(net, listen_id->event_handler, listen_id->context, listen_id->ps, IB_QPT_UD, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, ib_event->param.sidr_req_rcvd.service_id)) goto err; if (net_dev) { rdma_copy_src_l2_addr(&id->route.addr.dev_addr, net_dev); } else { if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &id->route.addr.dev_addr); if (ret) goto err; } } id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static void cma_set_req_event_data(struct rdma_cm_event *event, const struct ib_cm_req_event_param *req_data, void *private_data, int offset) { event->param.conn.private_data = private_data + offset; event->param.conn.private_data_len = IB_CM_REQ_PRIVATE_DATA_SIZE - offset; event->param.conn.responder_resources = req_data->responder_resources; event->param.conn.initiator_depth = req_data->initiator_depth; event->param.conn.flow_control = req_data->flow_control; event->param.conn.retry_count = req_data->retry_count; event->param.conn.rnr_retry_count = req_data->rnr_retry_count; event->param.conn.srq = req_data->srq; event->param.conn.qp_num = req_data->remote_qpn; event->ece.vendor_id = req_data->ece.vendor_id; event->ece.attr_mod = req_data->ece.attr_mod; } static int cma_ib_check_req_qp_type(const struct rdma_cm_id *id, const struct ib_cm_event *ib_event) { return (((ib_event->event == IB_CM_REQ_RECEIVED) && (ib_event->param.req_rcvd.qp_type == id->qp_type)) || ((ib_event->event == IB_CM_SIDR_REQ_RECEIVED) && (id->qp_type == IB_QPT_UD)) || (!id->qp_type)); } static int cma_ib_req_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *listen_id, *conn_id = NULL; struct rdma_cm_event event = {}; struct cma_req_info req = {}; struct net_device *net_dev; u8 offset; int ret; listen_id = cma_ib_id_from_event(cm_id, ib_event, &req, &net_dev); if (IS_ERR(listen_id)) return PTR_ERR(listen_id); trace_cm_req_handler(listen_id, ib_event->event); if (!cma_ib_check_req_qp_type(&listen_id->id, ib_event)) { ret = -EINVAL; goto net_dev_put; } mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) { ret = -ECONNABORTED; goto err_unlock; } offset = cma_user_data_offset(listen_id); event.event = RDMA_CM_EVENT_CONNECT_REQUEST; if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) { conn_id = cma_ib_new_udp_id(&listen_id->id, ib_event, net_dev); event.param.ud.private_data = ib_event->private_data + offset; event.param.ud.private_data_len = IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset; } else { conn_id = cma_ib_new_conn_id(&listen_id->id, ib_event, net_dev); cma_set_req_event_data(&event, &ib_event->param.req_rcvd, ib_event->private_data, offset); } if (!conn_id) { ret = -ENOMEM; goto err_unlock; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); ret = cma_ib_acquire_dev(conn_id, listen_id, &req); if (ret) { destroy_id_handler_unlock(conn_id); goto err_unlock; } conn_id->cm_id.ib = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_ib_handler; ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ conn_id->cm_id.ib = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); goto net_dev_put; } if (READ_ONCE(conn_id->state) == RDMA_CM_CONNECT && conn_id->id.qp_type != IB_QPT_UD) { trace_cm_prepare_mra(cm_id->context); ib_prepare_cm_mra(cm_id); } mutex_unlock(&conn_id->handler_mutex); err_unlock: mutex_unlock(&listen_id->handler_mutex); net_dev_put: dev_put(net_dev); return ret; } __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr) { if (addr->sa_family == AF_IB) return ((struct sockaddr_ib *) addr)->sib_sid; return cpu_to_be64(((u64)id->ps << 16) + be16_to_cpu(cma_port(addr))); } EXPORT_SYMBOL(rdma_get_service_id); void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, union ib_gid *dgid) { struct rdma_addr *addr = &cm_id->route.addr; if (!cm_id->device) { if (sgid) memset(sgid, 0, sizeof(*sgid)); if (dgid) memset(dgid, 0, sizeof(*dgid)); return; } if (rdma_protocol_roce(cm_id->device, cm_id->port_num)) { if (sgid) rdma_ip2gid((struct sockaddr *)&addr->src_addr, sgid); if (dgid) rdma_ip2gid((struct sockaddr *)&addr->dst_addr, dgid); } else { if (sgid) rdma_addr_get_sgid(&addr->dev_addr, sgid); if (dgid) rdma_addr_get_dgid(&addr->dev_addr, dgid); } } EXPORT_SYMBOL(rdma_read_gids); static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; struct rdma_cm_event event = {}; int ret = 0; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (iw_event->event) { case IW_CM_EVENT_CLOSE: event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IW_CM_EVENT_CONNECT_REPLY: memcpy(cma_src_addr(id_priv), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(id_priv), raddr, rdma_addr_size(raddr)); switch (iw_event->status) { case 0: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; case -ECONNRESET: case -ECONNREFUSED: event.event = RDMA_CM_EVENT_REJECTED; break; case -ETIMEDOUT: event.event = RDMA_CM_EVENT_UNREACHABLE; break; default: event.event = RDMA_CM_EVENT_CONNECT_ERROR; break; } break; case IW_CM_EVENT_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; default: goto out; } event.status = iw_event->status; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.iw = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return ret; } static int iw_conn_req_handler(struct iw_cm_id *cm_id, struct iw_cm_event *iw_event) { struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event = {}; int ret = -ECONNABORTED; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; event.event = RDMA_CM_EVENT_CONNECT_REQUEST; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; listen_id = cm_id->context; mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) goto out; /* Create a new RDMA id for the new IW CM ID */ conn_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net, listen_id->id.event_handler, listen_id->id.context, RDMA_PS_TCP, IB_QPT_RC, listen_id); if (IS_ERR(conn_id)) { ret = -ENOMEM; goto out; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); conn_id->state = RDMA_CM_CONNECT; ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } ret = cma_iw_acquire_dev(conn_id, listen_id); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } conn_id->cm_id.iw = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; memcpy(cma_src_addr(conn_id), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(conn_id), raddr, rdma_addr_size(raddr)); ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* User wants to destroy the CM ID */ conn_id->cm_id.iw = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } mutex_unlock(&conn_id->handler_mutex); out: mutex_unlock(&listen_id->handler_mutex); return ret; } static int cma_ib_listen(struct rdma_id_private *id_priv) { struct sockaddr *addr; struct ib_cm_id *id; __be64 svc_id; addr = cma_src_addr(id_priv); svc_id = rdma_get_service_id(&id_priv->id, addr); id = ib_cm_insert_listen(id_priv->id.device, cma_ib_req_handler, svc_id); if (IS_ERR(id)) return PTR_ERR(id); id_priv->cm_id.ib = id; return 0; } static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog) { int ret; struct iw_cm_id *id; id = iw_create_cm_id(id_priv->id.device, iw_conn_req_handler, id_priv); if (IS_ERR(id)) return PTR_ERR(id); mutex_lock(&id_priv->qp_mutex); id->tos = id_priv->tos; id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id->afonly = id_priv->afonly; id_priv->cm_id.iw = id; memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); ret = iw_cm_listen(id_priv->cm_id.iw, backlog); if (ret) { iw_destroy_cm_id(id_priv->cm_id.iw); id_priv->cm_id.iw = NULL; } return ret; } static int cma_listen_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct rdma_id_private *id_priv = id->context; /* Listening IDs are always destroyed on removal */ if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) return -1; id->context = id_priv->id.context; id->event_handler = id_priv->id.event_handler; trace_cm_event_handler(id_priv, event); return id_priv->id.event_handler(id, event); } static int cma_listen_on_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev, struct rdma_id_private **to_destroy) { struct rdma_id_private *dev_id_priv; struct net *net = id_priv->id.route.addr.dev_addr.net; int ret; lockdep_assert_held(&lock); *to_destroy = NULL; if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return 0; if (id_priv->restricted_node_type != RDMA_NODE_UNSPECIFIED && id_priv->restricted_node_type != cma_dev->device->node_type) return 0; dev_id_priv = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps, id_priv->id.qp_type, id_priv); if (IS_ERR(dev_id_priv)) return PTR_ERR(dev_id_priv); dev_id_priv->restricted_node_type = id_priv->restricted_node_type; dev_id_priv->state = RDMA_CM_ADDR_BOUND; memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); _cma_attach_to_dev(dev_id_priv, cma_dev); rdma_restrack_add(&dev_id_priv->res); cma_id_get(id_priv); dev_id_priv->internal_id = 1; dev_id_priv->afonly = id_priv->afonly; mutex_lock(&id_priv->qp_mutex); dev_id_priv->tos_set = id_priv->tos_set; dev_id_priv->tos = id_priv->tos; mutex_unlock(&id_priv->qp_mutex); ret = rdma_listen(&dev_id_priv->id, id_priv->backlog); if (ret) goto err_listen; list_add_tail(&dev_id_priv->listen_item, &id_priv->listen_list); return 0; err_listen: /* Caller must destroy this after releasing lock */ *to_destroy = dev_id_priv; dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret); return ret; } static int cma_listen_on_all(struct rdma_id_private *id_priv) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; int ret; mutex_lock(&lock); list_add_tail(&id_priv->listen_any_item, &listen_any_list); list_for_each_entry(cma_dev, &dev_list, list) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) { /* Prevent racing with cma_process_remove() */ if (to_destroy) list_del_init(&to_destroy->device_item); goto err_listen; } } mutex_unlock(&lock); return 0; err_listen: _cma_cancel_listens(id_priv); mutex_unlock(&lock); if (to_destroy) rdma_destroy_id(&to_destroy->id); return ret; } void rdma_set_service_type(struct rdma_cm_id *id, int tos) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->tos = (u8) tos; id_priv->tos_set = true; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_set_service_type); /** * rdma_set_ack_timeout() - Set the ack timeout of QP associated * with a connection identifier. * @id: Communication identifier to associated with service type. * @timeout: Ack timeout to set a QP, expressed as 4.096 * 2^(timeout) usec. * * This function should be called before rdma_connect() on active side, * and on passive side before rdma_accept(). It is applicable to primary * path only. The timeout will affect the local side of the QP, it is not * negotiated with remote side and zero disables the timer. In case it is * set before rdma_resolve_route, the value will also be used to determine * PacketLifeTime for RoCE. * * Return: 0 for success */ int rdma_set_ack_timeout(struct rdma_cm_id *id, u8 timeout) { struct rdma_id_private *id_priv; if (id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_INI) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->timeout = timeout; id_priv->timeout_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_ack_timeout); /** * rdma_set_min_rnr_timer() - Set the minimum RNR Retry timer of the * QP associated with a connection identifier. * @id: Communication identifier to associated with service type. * @min_rnr_timer: 5-bit value encoded as Table 45: "Encoding for RNR NAK * Timer Field" in the IBTA specification. * * This function should be called before rdma_connect() on active * side, and on passive side before rdma_accept(). The timer value * will be associated with the local QP. When it receives a send it is * not read to handle, typically if the receive queue is empty, an RNR * Retry NAK is returned to the requester with the min_rnr_timer * encoded. The requester will then wait at least the time specified * in the NAK before retrying. The default is zero, which translates * to a minimum RNR Timer value of 655 ms. * * Return: 0 for success */ int rdma_set_min_rnr_timer(struct rdma_cm_id *id, u8 min_rnr_timer) { struct rdma_id_private *id_priv; /* It is a five-bit value */ if (min_rnr_timer & 0xe0) return -EINVAL; if (WARN_ON(id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_TGT)) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->min_rnr_timer = min_rnr_timer; id_priv->min_rnr_timer_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_min_rnr_timer); static int route_set_path_rec_inbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_inbound) { route->path_rec_inbound = kzalloc_obj(*route->path_rec_inbound); if (!route->path_rec_inbound) return -ENOMEM; } *route->path_rec_inbound = *path_rec; return 0; } static int route_set_path_rec_outbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_outbound) { route->path_rec_outbound = kzalloc_obj(*route->path_rec_outbound); if (!route->path_rec_outbound) return -ENOMEM; } *route->path_rec_outbound = *path_rec; return 0; } static void cma_query_handler(int status, struct sa_path_rec *path_rec, unsigned int num_prs, void *context) { struct cma_work *work = context; struct rdma_route *route; int i; route = &work->id->id.route; if (status) goto fail; for (i = 0; i < num_prs; i++) { if (!path_rec[i].flags || (path_rec[i].flags & IB_PATH_GMP)) *route->path_rec = path_rec[i]; else if (path_rec[i].flags & IB_PATH_INBOUND) status = route_set_path_rec_inbound(work, &path_rec[i]); else if (path_rec[i].flags & IB_PATH_OUTBOUND) status = route_set_path_rec_outbound(work, &path_rec[i]); else status = -EINVAL; if (status) goto fail; } route->num_pri_alt_paths = 1; queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_ERROR; work->event.status = status; pr_debug_ratelimited("RDMA CM: ROUTE_ERROR: failed to query path. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_query_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms, struct cma_work *work) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sa_path_rec path_rec; ib_sa_comp_mask comp_mask; struct sockaddr_in6 *sin6; struct sockaddr_ib *sib; memset(&path_rec, 0, sizeof path_rec); if (rdma_cap_opa_ah(id_priv->id.device, id_priv->id.port_num)) path_rec.rec_type = SA_PATH_REC_TYPE_OPA; else path_rec.rec_type = SA_PATH_REC_TYPE_IB; rdma_addr_get_sgid(dev_addr, &path_rec.sgid); rdma_addr_get_dgid(dev_addr, &path_rec.dgid); path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); path_rec.numb_path = 1; path_rec.reversible = 1; path_rec.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID; switch (cma_family(id_priv)) { case AF_INET: path_rec.qos_class = cpu_to_be16((u16) id_priv->tos); comp_mask |= IB_SA_PATH_REC_QOS_CLASS; break; case AF_INET6: sin6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; case AF_IB: sib = (struct sockaddr_ib *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sib->sib_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; } id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &path_rec, comp_mask, timeout_ms, GFP_KERNEL, cma_query_handler, work, &id_priv->query); return (id_priv->query_id < 0) ? id_priv->query_id : 0; } static void cma_iboe_join_work_handler(struct work_struct *work) { struct cma_multicast *mc = container_of(work, struct cma_multicast, iboe_join.work); struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_id_private *id_priv = mc->id_priv; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; ret = cma_cm_event_handler(id_priv, event); WARN_ON(ret); out_unlock: mutex_unlock(&id_priv->handler_mutex); if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&event->param.ud.ah_attr); } static void cma_work_handler(struct work_struct *_work) { struct cma_work *work = container_of(_work, struct cma_work, work); struct rdma_id_private *id_priv = work->id; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; if (work->old_state != 0 || work->new_state != 0) { if (!cma_comp_exch(id_priv, work->old_state, work->new_state)) goto out_unlock; } if (cma_cm_event_handler(id_priv, &work->event)) { cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); goto out_free; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); out_free: if (work->event.event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&work->event.param.ud.ah_attr); kfree(work); } static void cma_init_resolve_route_work(struct cma_work *work, struct rdma_id_private *id_priv) { work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ROUTE_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; } static void enqueue_resolve_addr_work(struct cma_work *work, struct rdma_id_private *id_priv) { /* Balances with cma_id_put() in cma_work_handler */ cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDR_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; queue_work(cma_wq, &work->work); } static int cma_resolve_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms) { struct rdma_route *route = &id_priv->id.route; struct cma_work *work; int ret; work = kzalloc_obj(*work); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); if (!route->path_rec) route->path_rec = kmalloc_obj(*route->path_rec); if (!route->path_rec) { ret = -ENOMEM; goto err1; } ret = cma_query_ib_route(id_priv, timeout_ms, work); if (ret) goto err2; return 0; err2: kfree(route->path_rec); route->path_rec = NULL; err1: kfree(work); return ret; } static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, unsigned long supported_gids, enum ib_gid_type default_gid) { if ((network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) && test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) return IB_GID_TYPE_ROCE_UDP_ENCAP; return default_gid; } /* * cma_iboe_set_path_rec_l2_fields() is helper function which sets * path record type based on GID type. * It also sets up other L2 fields which includes destination mac address * netdev ifindex, of the path record. * It returns the netdev of the bound interface for this path record entry. */ static struct net_device * cma_iboe_set_path_rec_l2_fields(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; enum ib_gid_type gid_type = IB_GID_TYPE_ROCE; struct rdma_addr *addr = &route->addr; unsigned long supported_gids; struct net_device *ndev; if (!addr->dev_addr.bound_dev_if) return NULL; ndev = dev_get_by_index(addr->dev_addr.net, addr->dev_addr.bound_dev_if); if (!ndev) return NULL; supported_gids = roce_gid_type_mask_support(id_priv->id.device, id_priv->id.port_num); gid_type = cma_route_gid_type(addr->dev_addr.network, supported_gids, id_priv->gid_type); /* Use the hint from IP Stack to select GID Type */ if (gid_type < ib_network_to_gid_type(addr->dev_addr.network)) gid_type = ib_network_to_gid_type(addr->dev_addr.network); route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type); route->path_rec->roce.route_resolved = true; sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr); return ndev; } int rdma_set_ib_path(struct rdma_cm_id *id, struct sa_path_rec *path_rec) { struct rdma_id_private *id_priv; struct net_device *ndev; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_RESOLVED)) return -EINVAL; id->route.path_rec = kmemdup(path_rec, sizeof(*path_rec), GFP_KERNEL); if (!id->route.path_rec) { ret = -ENOMEM; goto err; } if (rdma_protocol_roce(id->device, id->port_num)) { ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err_free; } dev_put(ndev); } id->route.num_pri_alt_paths = 1; return 0; err_free: kfree(id->route.path_rec); id->route.path_rec = NULL; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_set_ib_path); static int cma_resolve_iw_route(struct rdma_id_private *id_priv) { struct cma_work *work; work = kzalloc_obj(*work); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; } static int get_vlan_ndev_tc(struct net_device *vlan_ndev, int prio) { struct net_device *dev; dev = vlan_dev_real_dev(vlan_ndev); if (dev->num_tc) return netdev_get_prio_tc_map(dev, prio); return (vlan_dev_get_egress_qos_mask(vlan_ndev, prio) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } struct iboe_prio_tc_map { int input_prio; int output_tc; bool found; }; static int get_lower_vlan_dev_tc(struct net_device *dev, struct netdev_nested_priv *priv) { struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data; if (is_vlan_dev(dev)) map->output_tc = get_vlan_ndev_tc(dev, map->input_prio); else if (dev->num_tc) map->output_tc = netdev_get_prio_tc_map(dev, map->input_prio); else map->output_tc = 0; /* We are interested only in first level VLAN device, so always * return 1 to stop iterating over next level devices. */ map->found = true; return 1; } static int iboe_tos_to_sl(struct net_device *ndev, int tos) { struct iboe_prio_tc_map prio_tc_map = {}; int prio = rt_tos2priority(tos); struct netdev_nested_priv priv; /* If VLAN device, get it directly from the VLAN netdev */ if (is_vlan_dev(ndev)) return get_vlan_ndev_tc(ndev, prio); prio_tc_map.input_prio = prio; priv.data = (void *)&prio_tc_map; rcu_read_lock(); netdev_walk_all_lower_dev_rcu(ndev, get_lower_vlan_dev_tc, &priv); rcu_read_unlock(); /* If map is found from lower device, use it; Otherwise * continue with the current netdevice to get priority to tc map. */ if (prio_tc_map.found) return prio_tc_map.output_tc; else if (ndev->num_tc) return netdev_get_prio_tc_map(ndev, prio); else return 0; } static __be32 cma_get_roce_udp_flow_label(struct rdma_id_private *id_priv) { struct sockaddr_in6 *addr6; u16 dport, sport; u32 hash, fl; addr6 = (struct sockaddr_in6 *)cma_src_addr(id_priv); fl = be32_to_cpu(addr6->sin6_flowinfo) & IB_GRH_FLOWLABEL_MASK; if ((cma_family(id_priv) != AF_INET6) || !fl) { dport = be16_to_cpu(cma_port(cma_dst_addr(id_priv))); sport = be16_to_cpu(cma_port(cma_src_addr(id_priv))); hash = (u32)sport * 31 + dport; fl = hash & IB_GRH_FLOWLABEL_MASK; } return cpu_to_be32(fl); } static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; struct rdma_addr *addr = &route->addr; struct cma_work *work; int ret; struct net_device *ndev; u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; u8 tos; mutex_lock(&id_priv->qp_mutex); tos = id_priv->tos_set ? id_priv->tos : default_roce_tos; mutex_unlock(&id_priv->qp_mutex); work = kzalloc_obj(*work); if (!work) return -ENOMEM; route->path_rec = kzalloc_obj(*route->path_rec); if (!route->path_rec) { ret = -ENOMEM; goto err1; } route->num_pri_alt_paths = 1; ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err2; } rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &route->path_rec->sgid); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr, &route->path_rec->dgid); if (((struct sockaddr *)&id_priv->id.route.addr.dst_addr)->sa_family != AF_IB) /* TODO: get the hoplimit from the inet/inet6 device */ route->path_rec->hop_limit = addr->dev_addr.hoplimit; else route->path_rec->hop_limit = 1; route->path_rec->reversible = 1; route->path_rec->pkey = cpu_to_be16(0xffff); route->path_rec->mtu_selector = IB_SA_EQ; route->path_rec->sl = iboe_tos_to_sl(ndev, tos); route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate * PacketLifeTime. As per IBTA 12.7.34, * local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). * Assuming a negligible local ACK delay, we can use * PacketLifeTime = local ACK timeout/2 * as a reasonable approximation for RoCE networks. */ mutex_lock(&id_priv->qp_mutex); if (id_priv->timeout_set && id_priv->timeout) route->path_rec->packet_life_time = id_priv->timeout - 1; else route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; mutex_unlock(&id_priv->qp_mutex); if (!route->path_rec->mtu) { ret = -EINVAL; goto err2; } if (rdma_protocol_roce_udp_encap(id_priv->id.device, id_priv->id.port_num)) route->path_rec->flow_label = cma_get_roce_udp_flow_label(id_priv); cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; err2: kfree(route->path_rec); route->path_rec = NULL; route->num_pri_alt_paths = 0; err1: kfree(work); return ret; } int rdma_resolve_route(struct rdma_cm_id *id, unsigned long timeout_ms) { struct rdma_id_private *id_priv; enum rdma_cm_state state; int ret; if (!timeout_ms) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); state = id_priv->state; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_QUERY) && !cma_comp_exch(id_priv, RDMA_CM_ADDRINFO_RESOLVED, RDMA_CM_ROUTE_QUERY)) return -EINVAL; cma_id_get(id_priv); if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_route(id_priv, timeout_ms); else if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_resolve_iboe_route(id_priv); if (!ret) cma_add_id_to_tree(id_priv); } else if (rdma_protocol_iwarp(id->device, id->port_num)) ret = cma_resolve_iw_route(id_priv); else ret = -ENOSYS; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_QUERY, state); cma_id_put(id_priv); return ret; } EXPORT_SYMBOL(rdma_resolve_route); static void cma_set_loopback(struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_addr.s_addr = htonl(INADDR_LOOPBACK); break; case AF_INET6: ipv6_addr_set(&((struct sockaddr_in6 *) addr)->sin6_addr, 0, 0, 0, htonl(1)); break; default: ib_addr_set(&((struct sockaddr_ib *) addr)->sib_addr, 0, 0, 0, htonl(1)); break; } } static int cma_bind_loopback(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; union ib_gid gid; enum ib_port_state port_state; unsigned int p; u16 pkey; int ret; cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cur_dev->device, 1)) continue; if (!cma_dev) cma_dev = cur_dev; rdma_for_each_port (cur_dev->device, p) { if (!ib_get_cached_port_state(cur_dev->device, p, &port_state) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; goto port_found; } } } if (!cma_dev) { ret = -ENODEV; goto out; } p = 1; port_found: ret = rdma_query_gid(cma_dev->device, p, 0, &gid); if (ret) goto out; ret = ib_get_cached_pkey(cma_dev->device, p, 0, &pkey); if (ret) goto out; id_priv->id.route.addr.dev_addr.dev_type = (rdma_protocol_ib(cma_dev->device, p)) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey); id_priv->id.port_num = p; cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); cma_set_loopback(cma_src_addr(id_priv)); out: mutex_unlock(&lock); return ret; } static void addr_handler(int status, struct sockaddr *src_addr, struct rdma_dev_addr *dev_addr, void *context) { struct rdma_id_private *id_priv = context; struct rdma_cm_event event = {}; struct sockaddr *addr; struct sockaddr_storage old_addr; mutex_lock(&id_priv->handler_mutex); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_RESOLVED)) goto out; /* * Store the previous src address, so that if we fail to acquire * matching rdma device, old address can be restored back, which helps * to cancel the cma listen operation correctly. */ addr = cma_src_addr(id_priv); memcpy(&old_addr, addr, rdma_addr_size(addr)); memcpy(addr, src_addr, rdma_addr_size(src_addr)); if (!status && !id_priv->cma_dev) { status = cma_acquire_dev_by_src_ip(id_priv); if (status) pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n", status); rdma_restrack_add(&id_priv->res); } else if (status) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status); } if (status) { memcpy(addr, &old_addr, rdma_addr_size((struct sockaddr *)&old_addr)); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ADDR_BOUND)) goto out; event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = status; } else event.event = RDMA_CM_EVENT_ADDR_RESOLVED; if (cma_cm_event_handler(id_priv, &event)) { destroy_id_handler_unlock(id_priv); return; } out: mutex_unlock(&id_priv->handler_mutex); } static int cma_resolve_loopback(struct rdma_id_private *id_priv) { struct cma_work *work; union ib_gid gid; int ret; work = kzalloc_obj(*work); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_bind_loopback(id_priv); if (ret) goto err; } rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid); rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) { struct cma_work *work; int ret; work = kzalloc_obj(*work); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_resolve_ib_dev(id_priv); if (ret) goto err; } rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *) &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr)); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if ((reuse && id_priv->state != RDMA_CM_LISTEN) || id_priv->state == RDMA_CM_IDLE) { id_priv->reuseaddr = reuse; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_reuseaddr); int rdma_set_afonly(struct rdma_cm_id *id, int afonly) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if (id_priv->state == RDMA_CM_IDLE || id_priv->state == RDMA_CM_ADDR_BOUND) { id_priv->options |= (1 << CMA_OPTION_AFONLY); id_priv->afonly = afonly; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_afonly); static void cma_bind_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct sockaddr *addr; struct sockaddr_ib *sib; u64 sid, mask; __be16 port; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); port = htons(bind_list->port); switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_port = port; break; case AF_INET6: ((struct sockaddr_in6 *) addr)->sin6_port = port; break; case AF_IB: sib = (struct sockaddr_ib *) addr; sid = be64_to_cpu(sib->sib_sid); mask = be64_to_cpu(sib->sib_sid_mask); sib->sib_sid = cpu_to_be64((sid & mask) | (u64) ntohs(port)); sib->sib_sid_mask = cpu_to_be64(~0ULL); break; } id_priv->bind_list = bind_list; hlist_add_head(&id_priv->node, &bind_list->owners); } static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv, unsigned short snum) { struct rdma_bind_list *bind_list; int ret; lockdep_assert_held(&lock); bind_list = kzalloc_obj(*bind_list); if (!bind_list) return -ENOMEM; ret = cma_ps_alloc(id_priv->id.route.addr.dev_addr.net, ps, bind_list, snum); if (ret < 0) goto err; bind_list->ps = ps; bind_list->port = snum; cma_bind_port(bind_list, id_priv); return 0; err: kfree(bind_list); return ret == -ENOSPC ? -EADDRNOTAVAIL : ret; } static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct rdma_id_private *cur_id; struct sockaddr *daddr = cma_dst_addr(id_priv); struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr); lockdep_assert_held(&lock); hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); __be16 cur_dport = cma_port(cur_daddr); if (id_priv == cur_id) continue; /* different dest port -> unique */ if (!cma_any_port(daddr) && !cma_any_port(cur_daddr) && (dport != cur_dport)) continue; /* different src address -> unique */ if (!cma_any_addr(saddr) && !cma_any_addr(cur_saddr) && cma_addr_cmp(saddr, cur_saddr)) continue; /* different dst address -> unique */ if (!cma_any_addr(daddr) && !cma_any_addr(cur_daddr) && cma_addr_cmp(daddr, cur_daddr)) continue; return -EADDRNOTAVAIL; } return 0; } static int cma_alloc_any_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { static unsigned int last_used_port; int low, high, remaining; unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net; lockdep_assert_held(&lock); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_inclusive(low, remaining + low - 1); retry: if (last_used_port != rover) { struct rdma_bind_list *bind_list; int ret; bind_list = cma_ps_find(net, ps, (unsigned short)rover); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, rover); } else { ret = cma_port_is_unique(bind_list, id_priv); if (!ret) cma_bind_port(bind_list, id_priv); } /* * Remember previously used port number in order to avoid * re-using same port immediately after it is closed. */ if (!ret) last_used_port = rover; if (ret != -EADDRNOTAVAIL) return ret; } if (--remaining) { rover++; if ((rover < low) || (rover > high)) rover = low; goto retry; } return -EADDRNOTAVAIL; } /* * Check that the requested port is available. This is called when trying to * bind to a specific port, or when trying to listen on a bound port. In * the latter case, the provided id_priv may already be on the bind_list, but * we still need to check that it's okay to start listening. */ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv, uint8_t reuseaddr) { struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) continue; if (reuseaddr && cur_id->reuseaddr) continue; cur_addr = cma_src_addr(cur_id); if (id_priv->afonly && cur_id->afonly && (addr->sa_family != cur_addr->sa_family)) continue; if (cma_any_addr(addr) || cma_any_addr(cur_addr)) return -EADDRNOTAVAIL; if (!cma_addr_cmp(addr, cur_addr)) return -EADDRINUSE; } return 0; } static int cma_use_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list; unsigned short snum; int ret; lockdep_assert_held(&lock); snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; bind_list = cma_ps_find(id_priv->id.route.addr.dev_addr.net, ps, snum); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, snum); } else { ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr); if (!ret) cma_bind_port(bind_list, id_priv); } return ret; } static enum rdma_ucm_port_space cma_select_inet_ps(struct rdma_id_private *id_priv) { switch (id_priv->id.ps) { case RDMA_PS_TCP: case RDMA_PS_UDP: case RDMA_PS_IPOIB: case RDMA_PS_IB: return id_priv->id.ps; default: return 0; } } static enum rdma_ucm_port_space cma_select_ib_ps(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps = 0; struct sockaddr_ib *sib; u64 sid_ps, mask, sid; sib = (struct sockaddr_ib *) cma_src_addr(id_priv); mask = be64_to_cpu(sib->sib_sid_mask) & RDMA_IB_IP_PS_MASK; sid = be64_to_cpu(sib->sib_sid) & mask; if ((id_priv->id.ps == RDMA_PS_IB) && (sid == (RDMA_IB_IP_PS_IB & mask))) { sid_ps = RDMA_IB_IP_PS_IB; ps = RDMA_PS_IB; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_TCP)) && (sid == (RDMA_IB_IP_PS_TCP & mask))) { sid_ps = RDMA_IB_IP_PS_TCP; ps = RDMA_PS_TCP; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_UDP)) && (sid == (RDMA_IB_IP_PS_UDP & mask))) { sid_ps = RDMA_IB_IP_PS_UDP; ps = RDMA_PS_UDP; } if (ps) { sib->sib_sid = cpu_to_be64(sid_ps | ntohs(cma_port((struct sockaddr *) sib))); sib->sib_sid_mask = cpu_to_be64(RDMA_IB_IP_PS_MASK | be64_to_cpu(sib->sib_sid_mask)); } return ps; } static int cma_get_port(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps; int ret; if (cma_family(id_priv) != AF_IB) ps = cma_select_inet_ps(id_priv); else ps = cma_select_ib_ps(id_priv); if (!ps) return -EPROTONOSUPPORT; mutex_lock(&lock); if (cma_any_port(cma_src_addr(id_priv))) ret = cma_alloc_any_port(ps, id_priv); else ret = cma_use_port(ps, id_priv); mutex_unlock(&lock); return ret; } static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, struct sockaddr *addr) { #if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 *sin6; if (addr->sa_family != AF_INET6) return 0; sin6 = (struct sockaddr_in6 *) addr; if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) return 0; if (!sin6->sin6_scope_id) return -EINVAL; dev_addr->bound_dev_if = sin6->sin6_scope_id; #endif return 0; } int rdma_listen(struct rdma_cm_id *id, int backlog) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) { struct sockaddr_in any_in = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), }; /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN))) return -EINVAL; } /* * Once the ID reaches RDMA_CM_LISTEN it is not allowed to be reusable * any more, and has to be unique in the bind list. */ if (id_priv->reuseaddr) { mutex_lock(&lock); ret = cma_check_port(id_priv->bind_list, id_priv, 0); if (!ret) id_priv->reuseaddr = 0; mutex_unlock(&lock); if (ret) goto err; } id_priv->backlog = backlog; if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id->device, 1)) { ret = cma_ib_listen(id_priv); if (ret) goto err; } else if (rdma_cap_iw_cm(id->device, 1)) { ret = cma_iw_listen(id_priv, backlog); if (ret) goto err; } else { ret = -ENOSYS; goto err; } } else { ret = cma_listen_on_all(id_priv); if (ret) goto err; } return 0; err: id_priv->backlog = 0; /* * All the failure paths that lead here will not allow the req_handler's * to have run. */ cma_comp_exch(id_priv, RDMA_CM_LISTEN, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_listen); static int rdma_bind_addr_dst(struct rdma_id_private *id_priv, struct sockaddr *addr, const struct sockaddr *daddr) { struct sockaddr *id_daddr; int ret; if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && addr->sa_family != AF_IB) return -EAFNOSUPPORT; if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL; ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr); if (ret) goto err1; memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr); if (ret) goto err1; ret = cma_acquire_dev_by_src_ip(id_priv); if (ret) goto err1; } if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) { if (addr->sa_family == AF_INET) id_priv->afonly = 1; #if IS_ENABLED(CONFIG_IPV6) else if (addr->sa_family == AF_INET6) { struct net *net = id_priv->id.route.addr.dev_addr.net; id_priv->afonly = net->ipv6.sysctl.bindv6only; } #endif } id_daddr = cma_dst_addr(id_priv); if (daddr != id_daddr) memcpy(id_daddr, daddr, rdma_addr_size(addr)); id_daddr->sa_family = addr->sa_family; ret = cma_get_port(id_priv); if (ret) goto err2; if (!cma_any_addr(addr)) rdma_restrack_add(&id_priv->res); return 0; err2: if (id_priv->cma_dev) cma_release_dev(id_priv); err1: cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct sockaddr_storage zero_sock = {}; if (src_addr && src_addr->sa_family) return rdma_bind_addr_dst(id_priv, src_addr, dst_addr); /* * When the src_addr is not specified, automatically supply an any addr */ zero_sock.ss_family = dst_addr->sa_family; if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)&zero_sock; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst_addr; src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) id->route.addr.dev_addr.bound_dev_if = dst_addr6->sin6_scope_id; } else if (dst_addr->sa_family == AF_IB) { ((struct sockaddr_ib *)&zero_sock)->sib_pkey = ((struct sockaddr_ib *)dst_addr)->sib_pkey; } return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr); } /* * If required, resolve the source address for bind and leave the id_priv in * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior * calls made by ULP, a previously bound ID will not be re-bound and src_addr is * ignored. */ static int resolve_prepare_src(struct rdma_id_private *id_priv, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))) return -EINVAL; } else { memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); } if (cma_family(id_priv) != dst_addr->sa_family) { ret = -EINVAL; goto err_state; } return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr, unsigned long timeout_ms) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; ret = resolve_prepare_src(id_priv, src_addr, dst_addr); if (ret) return ret; if (cma_any_addr(dst_addr)) { ret = cma_resolve_loopback(id_priv); } else { if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { /* * The FSM can return back to RDMA_CM_ADDR_BOUND after * rdma_resolve_ip() is called, eg through the error * path in addr_handler(). If this happens the existing * request must be canceled before issuing a new one. * Since canceling a request is a bit slow and this * oddball path is rare, keep track once a request has * been issued. The track turns out to be a permanent * state since this is the only cancel as it is * immediately before rdma_resolve_ip(). */ if (id_priv->used_resolve_ip) rdma_addr_cancel(&id->route.addr.dev_addr); else id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, false, id_priv); } } if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_addr); int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret = 0; switch (node_type) { case RDMA_NODE_UNSPECIFIED: case RDMA_NODE_IB_CA: case RDMA_NODE_RNIC: break; default: return -EINVAL; } mutex_lock(&lock); if (READ_ONCE(id_priv->state) != RDMA_CM_IDLE) ret = -EALREADY; else id_priv->restricted_node_type = node_type; mutex_unlock(&lock); return ret; } EXPORT_SYMBOL(rdma_restrict_node_type); int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv)); } EXPORT_SYMBOL(rdma_bind_addr); static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) { struct cma_hdr *cma_hdr; cma_hdr = hdr; cma_hdr->cma_version = CMA_VERSION; if (cma_family(id_priv) == AF_INET) { struct sockaddr_in *src4, *dst4; src4 = (struct sockaddr_in *) cma_src_addr(id_priv); dst4 = (struct sockaddr_in *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 4); cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; cma_hdr->port = src4->sin_port; } else if (cma_family(id_priv) == AF_INET6) { struct sockaddr_in6 *src6, *dst6; src6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); dst6 = (struct sockaddr_in6 *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 6); cma_hdr->src_addr.ip6 = src6->sin6_addr; cma_hdr->dst_addr.ip6 = dst6->sin6_addr; cma_hdr->port = src6->sin6_port; } return 0; } static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; const struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (ib_event->event) { case IB_CM_SIDR_REQ_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_SIDR_REP_RECEIVED: event.param.ud.private_data = ib_event->private_data; event.param.ud.private_data_len = IB_CM_SIDR_REP_PRIVATE_DATA_SIZE; if (rep->status != IB_SIDR_SUCCESS) { event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = ib_event->param.sidr_rep_rcvd.status; pr_debug_ratelimited("RDMA CM: UNREACHABLE: bad SIDR reply. status %d\n", event.status); break; } ret = cma_set_qkey(id_priv, rep->qkey); if (ret) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to set qkey. status %d\n", ret); event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = ret; break; } ib_init_ah_attr_from_path(id_priv->id.device, id_priv->id.port_num, id_priv->id.route.path_rec, &event.param.ud.ah_attr, rep->sgid_attr); event.param.ud.qp_num = rep->qpn; event.param.ud.qkey = rep->qkey; event.event = RDMA_CM_EVENT_ESTABLISHED; event.status = 0; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); rdma_destroy_ah_attr(&event.param.ud.ah_attr); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_sidr_req_param req; struct ib_cm_id *id; void *private_data; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; req.path = id_priv->id.route.path_rec; req.sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8); req.max_cm_retries = CMA_MAX_CM_RETRIES; trace_cm_send_sidr_req(id_priv); ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req); if (ret) { ib_destroy_cm_id(id_priv->cm_id.ib); id_priv->cm_id.ib = NULL; } out: kfree(private_data); return ret; } static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_req_param req; struct rdma_route *route; void *private_data; struct ib_cm_id *id; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; route = &id_priv->id.route; if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } req.primary_path = &route->path_rec[0]; req.primary_path_inbound = route->path_rec_inbound; req.primary_path_outbound = route->path_rec_outbound; if (route->num_pri_alt_paths == 2) req.alternate_path = &route->path_rec[1]; req.ppath_sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; /* Alternate path SGID attribute currently unsupported */ req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.qp_num = id_priv->qp_num; req.qp_type = id_priv->id.qp_type; req.starting_psn = id_priv->seq_num; req.responder_resources = conn_param->responder_resources; req.initiator_depth = conn_param->initiator_depth; req.flow_control = conn_param->flow_control; req.retry_count = min_t(u8, 7, conn_param->retry_count); req.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.max_cm_retries = CMA_MAX_CM_RETRIES; req.srq = id_priv->srq ? 1 : 0; req.ece.vendor_id = id_priv->ece.vendor_id; req.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_req(id_priv); ret = ib_send_cm_req(id_priv->cm_id.ib, &req); out: if (ret && !IS_ERR(id)) { ib_destroy_cm_id(id); id_priv->cm_id.ib = NULL; } kfree(private_data); return ret; } static int cma_connect_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_id *cm_id; int ret; struct iw_cm_conn_param iw_param; cm_id = iw_create_cm_id(id_priv->id.device, cma_iw_handler, id_priv); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); mutex_lock(&id_priv->qp_mutex); cm_id->tos = id_priv->tos; cm_id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id_priv->cm_id.iw = cm_id; memcpy(&cm_id->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); memcpy(&cm_id->remote_addr, cma_dst_addr(id_priv), rdma_addr_size(cma_dst_addr(id_priv))); ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; if (conn_param) { iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; iw_param.qpn = id_priv->id.qp ? id_priv->qp_num : conn_param->qp_num; } else { memset(&iw_param, 0, sizeof iw_param); iw_param.qpn = id_priv->qp_num; } ret = iw_cm_connect(cm_id, &iw_param); out: if (ret) { iw_destroy_cm_id(cm_id); id_priv->cm_id.iw = NULL; } return ret; } /** * rdma_connect_locked - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Same as rdma_connect() but can only be called from the * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback. */ int rdma_connect_locked(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; lockdep_assert_held(&id_priv->handler_mutex); if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) return -EINVAL; if (!id->qp) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) ret = cma_resolve_ib_udp(id_priv, conn_param); else ret = cma_connect_ib(id_priv, conn_param); } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_connect_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto err_state; return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_connect_locked); /** * rdma_connect - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Users must have resolved a route for the rdma_cm_id to connect with by having * called rdma_resolve_route before calling this routine. * * This call will either connect to a remote QP or obtain remote QP information * for unconnected rdma_cm_id's. The actual operation is based on the * rdma_cm_id's port space. */ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; mutex_lock(&id_priv->handler_mutex); ret = rdma_connect_locked(id, conn_param); mutex_unlock(&id_priv->handler_mutex); return ret; } EXPORT_SYMBOL(rdma_connect); /** * rdma_connect_ece - Initiate an active connection request with ECE data. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * @ece: ECE parameters * * See rdma_connect() explanation. */ int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_connect(id, conn_param); } EXPORT_SYMBOL(rdma_connect_ece); static int cma_accept_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_rep_param rep; int ret; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; ret = cma_modify_qp_rts(id_priv, conn_param); if (ret) goto out; memset(&rep, 0, sizeof rep); rep.qp_num = id_priv->qp_num; rep.starting_psn = id_priv->seq_num; rep.private_data = conn_param->private_data; rep.private_data_len = conn_param->private_data_len; rep.responder_resources = conn_param->responder_resources; rep.initiator_depth = conn_param->initiator_depth; rep.failover_accepted = 0; rep.flow_control = conn_param->flow_control; rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); rep.srq = id_priv->srq ? 1 : 0; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_rep(id_priv); ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep); out: return ret; } static int cma_accept_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_conn_param iw_param; int ret; if (!conn_param) return -EINVAL; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) return ret; iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; if (id_priv->id.qp) iw_param.qpn = id_priv->qp_num; else iw_param.qpn = conn_param->qp_num; return iw_cm_accept(id_priv->cm_id.iw, &iw_param); } static int cma_send_sidr_rep(struct rdma_id_private *id_priv, enum ib_cm_sidr_status status, u32 qkey, const void *private_data, int private_data_len) { struct ib_cm_sidr_rep_param rep; int ret; memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { if (qkey) ret = cma_set_qkey(id_priv, qkey); else ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; rep.qkey = id_priv->qkey; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; } rep.private_data = private_data; rep.private_data_len = private_data_len; trace_cm_send_sidr_rep(id_priv); return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep); } /** * rdma_accept - Called to accept a connection request or response. * @id: Connection identifier associated with the request. * @conn_param: Information needed to establish the connection. This must be * provided if accepting a connection request. If accepting a connection * response, this parameter must be NULL. * * Typically, this routine is only called by the listener to accept a connection * request. It must also be called on the active side of a connection if the * user is performing their own QP transitions. * * In the case of error, a reject message is sent to the remote side and the * state of the qp associated with the id is modified to error, such that any * previously posted receive buffers would be flushed. * * This function is for use by kernel ULPs and must be called from under the * handler callback. */ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; lockdep_assert_held(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) return -EINVAL; if (!id->qp && conn_param) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { if (conn_param) ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, conn_param->qkey, conn_param->private_data, conn_param->private_data_len); else ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, 0, NULL, 0); } else { if (conn_param) ret = cma_accept_ib(id_priv, conn_param); else ret = cma_rep_recv(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_accept_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto reject; return 0; reject: cma_modify_qp_err(id_priv); rdma_reject(id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED); return ret; } EXPORT_SYMBOL(rdma_accept); int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_accept(id, conn_param); } EXPORT_SYMBOL(rdma_accept_ece); void rdma_lock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_lock_handler); void rdma_unlock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_unlock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_unlock_handler); int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; switch (id->device->node_type) { case RDMA_NODE_IB_CA: ret = ib_cm_notify(id_priv->cm_id.ib, event); break; default: ret = 0; break; } return ret; } EXPORT_SYMBOL(rdma_notify); int rdma_reject(struct rdma_cm_id *id, const void *private_data, u8 private_data_len, u8 reason) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0, private_data, private_data_len); } else { trace_cm_send_rej(id_priv); ret = ib_send_cm_rej(id_priv->cm_id.ib, reason, NULL, 0, private_data, private_data_len); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_reject(id_priv->cm_id.iw, private_data, private_data_len); } else { ret = -ENOSYS; } return ret; } EXPORT_SYMBOL(rdma_reject); int rdma_disconnect(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { ret = cma_modify_qp_err(id_priv); if (ret) goto out; /* Initiate or respond to a disconnect. */ trace_cm_disconnect(id_priv); if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) { if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0)) trace_cm_sent_drep(id_priv); } else { trace_cm_sent_dreq(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_disconnect(id_priv->cm_id.iw, 0); } else ret = -EINVAL; out: return ret; } EXPORT_SYMBOL(rdma_disconnect); static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, struct ib_sa_multicast *multicast, struct rdma_cm_event *event, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr; enum ib_gid_type gid_type; struct net_device *ndev; if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); event->status = status; event->param.ud.private_data = mc->context; if (status) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; return; } dev_addr = &id_priv->id.route.addr.dev_addr; ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); gid_type = id_priv->cma_dev ->default_gid_type[id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; event->event = RDMA_CM_EVENT_MULTICAST_JOIN; if (ib_init_ah_from_mcmember(id_priv->id.device, id_priv->id.port_num, &multicast->rec, ndev, gid_type, &event->param.ud.ah_attr)) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; goto out; } event->param.ud.qp_num = 0xFFFFFF; event->param.ud.qkey = id_priv->qkey; out: dev_put(ndev); } static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) { struct cma_multicast *mc = multicast->context; struct rdma_id_private *id_priv = mc->id_priv; struct rdma_cm_event event = {}; int ret = 0; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL || READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out; ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); if (!ret) { cma_make_mc_event(status, id_priv, multicast, &event, mc); ret = cma_cm_event_handler(id_priv, &event); } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret); out: mutex_unlock(&id_priv->handler_mutex); return 0; } static void cma_set_mgid(struct rdma_id_private *id_priv, struct sockaddr *addr, union ib_gid *mgid) { unsigned char mc_map[MAX_ADDR_LEN]; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sockaddr_in *sin = (struct sockaddr_in *) addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if ((addr->sa_family == AF_INET6) && ((be32_to_cpu(sin6->sin6_addr.s6_addr32[0]) & 0xFFF0FFFF) == 0xFF10A01B)) { /* IPv6 address is an SA assigned MGID. */ memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else if (addr->sa_family == AF_IB) { memcpy(mgid, &((struct sockaddr_ib *) addr)->sib_addr, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { ipv6_ib_mc_map(&sin6->sin6_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } else { ip_ib_mc_map(sin->sin_addr.s_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } } static int cma_join_ib_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct ib_sa_mcmember_rec rec; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; ib_sa_comp_mask comp_mask; int ret; ib_addr_get_mgid(dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (ret) return ret; if (!id_priv->qkey) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; } cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); rdma_addr_get_sgid(dev_addr, &rec.port_gid); rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); rec.join_state = mc->join_state; comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE | IB_SA_MCMEMBER_REC_QKEY | IB_SA_MCMEMBER_REC_SL | IB_SA_MCMEMBER_REC_FLOW_LABEL | IB_SA_MCMEMBER_REC_TRAFFIC_CLASS; if (id_priv->id.ps == RDMA_PS_IPOIB) comp_mask |= IB_SA_MCMEMBER_REC_RATE | IB_SA_MCMEMBER_REC_RATE_SELECTOR | IB_SA_MCMEMBER_REC_MTU_SELECTOR | IB_SA_MCMEMBER_REC_MTU | IB_SA_MCMEMBER_REC_HOP_LIMIT; mc->sa_mc = ib_sa_join_multicast(&sa_client, id_priv->id.device, id_priv->id.port_num, &rec, comp_mask, GFP_KERNEL, cma_ib_mc_handler, mc); return PTR_ERR_OR_ZERO(mc->sa_mc); } static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type) { struct sockaddr_in *sin = (struct sockaddr_in *)addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else { mgid->raw[0] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0xff; mgid->raw[1] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0x0e; mgid->raw[2] = 0; mgid->raw[3] = 0; mgid->raw[4] = 0; mgid->raw[5] = 0; mgid->raw[6] = 0; mgid->raw[7] = 0; mgid->raw[8] = 0; mgid->raw[9] = 0; mgid->raw[10] = 0xff; mgid->raw[11] = 0xff; *(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr; } } static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; struct ib_sa_multicast ib = {}; enum ib_gid_type gid_type; bool send_only; send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (cma_zero_addr(addr)) return -EINVAL; gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); ib.rec.pkey = cpu_to_be16(0xffff); if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) return -ENODEV; ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; if (!send_only) { err = cma_igmp_send(ndev, &ib.rec.mgid, true); } } } else { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) err = -ENOTSUPP; } dev_put(ndev); if (err || !ib.rec.mtu) return err ?: -EINVAL; if (!id_priv->qkey) cma_set_default_qkey(id_priv); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); cma_make_mc_event(0, id_priv, &ib, &mc->iboe_join.event, mc); queue_work(cma_wq, &mc->iboe_join.work); return 0; } int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, u8 join_state, void *context) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct cma_multicast *mc; int ret; /* Not supported for kernel QPs */ if (WARN_ON(id->qp)) return -EINVAL; /* ULP is calling this wrong. */ if (!id->device || (READ_ONCE(id_priv->state) != RDMA_CM_ADDR_BOUND && READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL; if (id_priv->id.qp_type != IB_QPT_UD) return -EINVAL; mc = kzalloc_obj(*mc); if (!mc) return -ENOMEM; memcpy(&mc->addr, addr, rdma_addr_size(addr)); mc->context = context; mc->id_priv = id_priv; mc->join_state = join_state; if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_iboe_join_multicast(id_priv, mc); if (ret) goto out_err; } else if (rdma_cap_ib_mcast(id->device, id->port_num)) { ret = cma_join_ib_multicast(id_priv, mc); if (ret) goto out_err; } else { ret = -ENOSYS; goto out_err; } spin_lock(&id_priv->lock); list_add(&mc->list, &id_priv->mc_list); spin_unlock(&id_priv->lock); return 0; out_err: kfree(mc); return ret; } EXPORT_SYMBOL(rdma_join_multicast); void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; struct cma_multicast *mc; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irq(&id_priv->lock); list_for_each_entry(mc, &id_priv->mc_list, list) { if (memcmp(&mc->addr, addr, rdma_addr_size(addr)) != 0) continue; list_del(&mc->list); spin_unlock_irq(&id_priv->lock); WARN_ON(id_priv->cma_dev->device != id->device); destroy_mc(id_priv, mc); return; } spin_unlock_irq(&id_priv->lock); } EXPORT_SYMBOL(rdma_leave_multicast); static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr; struct cma_work *work; dev_addr = &id_priv->id.route.addr.dev_addr; if ((dev_addr->bound_dev_if == ndev->ifindex) && (net_eq(dev_net(ndev), dev_addr->net)) && memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) { pr_info("RDMA CM addr change for ndev %s used by id %p\n", ndev->name, &id_priv->id); work = kzalloc_obj(*work); if (!work) return -ENOMEM; INIT_WORK(&work->work, cma_work_handler); work->id = id_priv; work->event.event = RDMA_CM_EVENT_ADDR_CHANGE; cma_id_get(id_priv); queue_work(cma_wq, &work->work); } return 0; } static int cma_netdev_callback(struct notifier_block *self, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct cma_device *cma_dev; struct rdma_id_private *id_priv; int ret = NOTIFY_DONE; if (event != NETDEV_BONDING_FAILOVER) return NOTIFY_DONE; if (!netif_is_bond_master(ndev)) return NOTIFY_DONE; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) list_for_each_entry(id_priv, &cma_dev->id_list, device_item) { ret = cma_netdev_change(ndev, id_priv); if (ret) goto out; } out: mutex_unlock(&lock); return ret; } static void cma_netevent_work_handler(struct work_struct *_work) { struct rdma_id_private *id_priv = container_of(_work, struct rdma_id_private, id.net_work); struct rdma_cm_event event = {}; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; if (cma_cm_event_handler(id_priv, &event)) { __acquire(&id_priv->handler_mutex); id_priv->cm_id.ib = NULL; cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); return; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); } static int cma_netevent_callback(struct notifier_block *self, unsigned long event, void *ctx) { struct id_table_entry *ips_node = NULL; struct rdma_id_private *current_id; struct neighbour *neigh = ctx; unsigned long flags; if (event != NETEVENT_NEIGH_UPDATE) return NOTIFY_DONE; spin_lock_irqsave(&id_table_lock, flags); if (neigh->tbl->family == AF_INET6) { struct sockaddr_in6 neigh_sock_6; neigh_sock_6.sin6_family = AF_INET6; neigh_sock_6.sin6_addr = *(struct in6_addr *)neigh->primary_key; ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_6); } else if (neigh->tbl->family == AF_INET) { struct sockaddr_in neigh_sock_4; neigh_sock_4.sin_family = AF_INET; neigh_sock_4.sin_addr.s_addr = *(__be32 *)(neigh->primary_key); ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_4); } else goto out; if (!ips_node) goto out; list_for_each_entry(current_id, &ips_node->id_list, id_list_entry) { if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr, neigh->ha, neigh->dev->addr_len)) continue; cma_id_get(current_id); if (!queue_work(cma_wq, ¤t_id->id.net_work)) cma_id_put(current_id); } out: spin_unlock_irqrestore(&id_table_lock, flags); return NOTIFY_DONE; } static struct notifier_block cma_nb = { .notifier_call = cma_netdev_callback }; static struct notifier_block cma_netevent_cb = { .notifier_call = cma_netevent_callback }; static void cma_send_device_removal_put(struct rdma_id_private *id_priv) { struct rdma_cm_event event = { .event = RDMA_CM_EVENT_DEVICE_REMOVAL }; enum rdma_cm_state state; unsigned long flags; mutex_lock(&id_priv->handler_mutex); /* Record that we want to remove the device */ spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; if (state == RDMA_CM_DESTROYING || state == RDMA_CM_DEVICE_REMOVAL) { spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); return; } id_priv->state = RDMA_CM_DEVICE_REMOVAL; spin_unlock_irqrestore(&id_priv->lock, flags); if (cma_cm_event_handler(id_priv, &event)) { /* * At this point the ULP promises it won't call * rdma_destroy_id() concurrently */ cma_id_put(id_priv); mutex_unlock(&id_priv->handler_mutex); trace_cm_id_destroy(id_priv); _destroy_id(id_priv, state); return; } mutex_unlock(&id_priv->handler_mutex); /* * If this races with destroy then the thread that first assigns state * to a destroying does the cancel. */ cma_cancel_operation(id_priv, state); cma_id_put(id_priv); } static void cma_process_remove(struct cma_device *cma_dev) { mutex_lock(&lock); while (!list_empty(&cma_dev->id_list)) { struct rdma_id_private *id_priv = list_first_entry( &cma_dev->id_list, struct rdma_id_private, device_item); list_del_init(&id_priv->listen_item); list_del_init(&id_priv->device_item); cma_id_get(id_priv); mutex_unlock(&lock); cma_send_device_removal_put(id_priv); mutex_lock(&lock); } mutex_unlock(&lock); cma_dev_put(cma_dev); wait_for_completion(&cma_dev->comp); } static bool cma_supported(struct ib_device *device) { u32 i; rdma_for_each_port(device, i) { if (rdma_cap_ib_cm(device, i) || rdma_cap_iw_cm(device, i)) return true; } return false; } static int cma_add_one(struct ib_device *device) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; struct rdma_id_private *id_priv; unsigned long supported_gids = 0; int ret; u32 i; if (!cma_supported(device)) return -EOPNOTSUPP; cma_dev = kmalloc_obj(*cma_dev); if (!cma_dev) return -ENOMEM; cma_dev->device = device; cma_dev->default_gid_type = kzalloc_objs(*cma_dev->default_gid_type, device->phys_port_cnt); if (!cma_dev->default_gid_type) { ret = -ENOMEM; goto free_cma_dev; } cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_roce_tos), GFP_KERNEL); if (!cma_dev->default_roce_tos) { ret = -ENOMEM; goto free_gid_type; } rdma_for_each_port (device, i) { supported_gids = roce_gid_type_mask_support(device, i); WARN_ON(!supported_gids); if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE)) cma_dev->default_gid_type[i - rdma_start_port(device)] = CMA_PREFERRED_ROCE_GID_TYPE; else cma_dev->default_gid_type[i - rdma_start_port(device)] = find_first_bit(&supported_gids, BITS_PER_LONG); cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0; } init_completion(&cma_dev->comp); refcount_set(&cma_dev->refcount, 1); INIT_LIST_HEAD(&cma_dev->id_list); ib_set_client_data(device, &cma_client, cma_dev); mutex_lock(&lock); list_add_tail(&cma_dev->list, &dev_list); list_for_each_entry(id_priv, &listen_any_list, listen_any_item) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) goto free_listen; } mutex_unlock(&lock); trace_cm_add_one(device); return 0; free_listen: list_del(&cma_dev->list); mutex_unlock(&lock); /* cma_process_remove() will delete to_destroy */ cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); free_gid_type: kfree(cma_dev->default_gid_type); free_cma_dev: kfree(cma_dev); return ret; } static void cma_remove_one(struct ib_device *device, void *client_data) { struct cma_device *cma_dev = client_data; trace_cm_remove_one(device); mutex_lock(&lock); list_del(&cma_dev->list); mutex_unlock(&lock); cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); kfree(cma_dev->default_gid_type); kfree(cma_dev); } static int cma_init_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); xa_init(&pernet->tcp_ps); xa_init(&pernet->udp_ps); xa_init(&pernet->ipoib_ps); xa_init(&pernet->ib_ps); return 0; } static void cma_exit_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); WARN_ON(!xa_empty(&pernet->tcp_ps)); WARN_ON(!xa_empty(&pernet->udp_ps)); WARN_ON(!xa_empty(&pernet->ipoib_ps)); WARN_ON(!xa_empty(&pernet->ib_ps)); } static struct pernet_operations cma_pernet_operations = { .init = cma_init_net, .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), }; static int __init cma_init(void) { int ret; /* * There is a rare lock ordering dependency in cma_netdev_callback() * that only happens when bonding is enabled. Teach lockdep that rtnl * must never be nested under lock so it can find these without having * to test with bonding. */ if (IS_ENABLED(CONFIG_LOCKDEP)) { rtnl_lock(); mutex_lock(&lock); mutex_unlock(&lock); rtnl_unlock(); } cma_wq = alloc_ordered_workqueue("rdma_cm", WQ_MEM_RECLAIM); if (!cma_wq) return -ENOMEM; ret = register_pernet_subsys(&cma_pernet_operations); if (ret) goto err_wq; ib_sa_register_client(&sa_client); register_netdevice_notifier(&cma_nb); register_netevent_notifier(&cma_netevent_cb); ret = ib_register_client(&cma_client); if (ret) goto err; ret = cma_configfs_init(); if (ret) goto err_ib; return 0; err_ib: ib_unregister_client(&cma_client); err: unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); err_wq: destroy_workqueue(cma_wq); return ret; } static void __exit cma_cleanup(void) { cma_configfs_exit(); ib_unregister_client(&cma_client); unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); destroy_workqueue(cma_wq); } module_init(cma_init); module_exit(cma_cleanup); static void cma_query_ib_service_handler(int status, struct sa_service_rec *recs, unsigned int num_recs, void *context) { struct cma_work *work = context; struct rdma_id_private *id_priv = work->id; struct sockaddr_ib *addr; if (status) goto fail; if (!num_recs) { status = -ENOENT; goto fail; } if (id_priv->id.route.service_recs) { status = -EALREADY; goto fail; } id_priv->id.route.service_recs = kmalloc_objs(*recs, num_recs); if (!id_priv->id.route.service_recs) { status = -ENOMEM; goto fail; } id_priv->id.route.num_service_recs = num_recs; memcpy(id_priv->id.route.service_recs, recs, sizeof(*recs) * num_recs); addr = (struct sockaddr_ib *)&id_priv->id.route.addr.dst_addr; addr->sib_family = AF_IB; addr->sib_addr = *(struct ib_addr *)&recs->gid; addr->sib_pkey = recs->pkey; addr->sib_sid = recs->id; rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)&addr->sib_addr); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, ntohs(addr->sib_pkey)); queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ADDRINFO_QUERY; work->new_state = RDMA_CM_ADDR_BOUND; work->event.event = RDMA_CM_EVENT_ADDRINFO_ERROR; work->event.status = status; pr_debug_ratelimited( "RDMA CM: SERVICE_ERROR: failed to query service record. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_resolve_ib_service(struct rdma_id_private *id_priv, struct rdma_ucm_ib_service *ibs) { struct sa_service_rec sr = {}; ib_sa_comp_mask mask = 0; struct cma_work *work; work = kzalloc_obj(*work); if (!work) return -ENOMEM; cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDRINFO_QUERY; work->new_state = RDMA_CM_ADDRINFO_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDRINFO_RESOLVED; if (ibs->flags & RDMA_USER_CM_IB_SERVICE_FLAG_ID) { sr.id = cpu_to_be64(ibs->service_id); mask |= IB_SA_SERVICE_REC_SERVICE_ID; } if (ibs->flags & RDMA_USER_CM_IB_SERVICE_FLAG_NAME) { strscpy(sr.name, ibs->service_name, sizeof(sr.name)); mask |= IB_SA_SERVICE_REC_SERVICE_NAME; } id_priv->query_id = ib_sa_service_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &sr, mask, 2000, GFP_KERNEL, cma_query_ib_service_handler, work, &id_priv->query); if (id_priv->query_id < 0) { cma_id_put(id_priv); kfree(work); return id_priv->query_id; } return 0; } int rdma_resolve_ib_service(struct rdma_cm_id *id, struct rdma_ucm_ib_service *ibs) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cma_dev || !cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDRINFO_QUERY)) return -EINVAL; if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_service(id_priv, ibs); else ret = -EOPNOTSUPP; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDRINFO_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_ib_service); |
| 271 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the ICMP protocol. * * Version: @(#)icmp.h 1.0.3 04/28/93 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_ICMP_H #define _LINUX_ICMP_H #include <linux/skbuff.h> #include <uapi/linux/icmp.h> #include <uapi/linux/errqueue.h> static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb) { return (struct icmphdr *)skb_transport_header(skb); } static inline bool icmp_is_err(int type) { switch (type) { case ICMP_DEST_UNREACH: case ICMP_SOURCE_QUENCH: case ICMP_REDIRECT: case ICMP_TIME_EXCEEDED: case ICMP_PARAMETERPROB: return true; } return false; } void ip_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out, int thlen, int off); /* RFC 4884 */ #define ICMP_EXT_ORIG_DGRAM_MIN_LEN 128 #define ICMP_EXT_VERSION_2 2 /* ICMP Extension Object Classes */ #define ICMP_EXT_OBJ_CLASS_IIO 2 /* RFC 5837 */ /* Interface Information Object - RFC 5837 */ enum { ICMP_EXT_CTYPE_IIO_ROLE_IIF, }; #define ICMP_EXT_CTYPE_IIO_ROLE(ROLE) ((ROLE) << 6) #define ICMP_EXT_CTYPE_IIO_MTU BIT(0) #define ICMP_EXT_CTYPE_IIO_NAME BIT(1) #define ICMP_EXT_CTYPE_IIO_IPADDR BIT(2) #define ICMP_EXT_CTYPE_IIO_IFINDEX BIT(3) struct icmp_ext_iio_name_subobj { u8 len; char name[IFNAMSIZ]; }; enum { /* RFC 5837 - Incoming IP Interface Role */ ICMP_ERR_EXT_IIO_IIF, /* Add new constants above. Used by "icmp_errors_extension_mask" * sysctl. */ ICMP_ERR_EXT_COUNT, }; #endif /* _LINUX_ICMP_H */ |
| 1051 1054 1052 17 1053 1052 1053 1051 1051 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 | // 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_obj(*site_mod); 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_obj(*site_mod); 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 */ |
| 56 55 40 90 90 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 | // 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 |
| 25 2 2 1 2 10 10 5 4 3 3 3 7 3 1 3 3 1517 120 1 1 612 58 2 2 1 1 20 2 5 1 5 5 5 6 11 13 7 8 11 7 8 7 5 1 5 5 5 4 1 1 22 5 14 7 6 6 3 4 5 23 23 5 4 1 1 2 2 1 2 1 1 3 745 150 3 2518 2522 612 1517 745 541 150 150 3 3 1121 282 1120 35 35 24 24 2 2 24 8 8 8 1 2 24 24 24 24 24 24 24 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Generic netlink support functions to configure an SMC-R PNET table * * Copyright IBM Corp. 2016 * * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> */ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> #include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> #include <uapi/linux/if.h> #include <uapi/linux/smc.h> #include <rdma/ib_verbs.h> #include <net/netns/generic.h> #include "smc_netns.h" #include "smc_pnet.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_core.h" static struct net_device *__pnet_find_base_ndev(struct net_device *ndev); static struct net_device *pnet_find_base_ndev(struct net_device *ndev); static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [SMC_PNETID_IBNAME] = { .type = NLA_NUL_STRING, .len = IB_DEVICE_NAME_MAX - 1 }, [SMC_PNETID_IBPORT] = { .type = NLA_U8 } }; static struct genl_family smc_pnet_nl_family; enum smc_pnet_nametype { SMC_PNET_ETH = 1, SMC_PNET_IB = 2, }; /* pnet entry stored in pnet table */ struct smc_pnetentry { struct list_head list; char pnet_name[SMC_MAX_PNETID_LEN + 1]; enum smc_pnet_nametype type; union { struct { char eth_name[IFNAMSIZ + 1]; struct net_device *ndev; netdevice_tracker dev_tracker; }; struct { char ib_name[IB_DEVICE_NAME_MAX + 1]; u8 ib_port; }; }; }; /* Check if the pnetid is set */ bool smc_pnet_is_pnetid_set(u8 *pnetid) { if (pnetid[0] == 0 || pnetid[0] == _S) return false; return true; } /* Check if two given pnetids match */ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2) { int i; for (i = 0; i < SMC_MAX_PNETID_LEN; i++) { if ((pnetid1[i] == 0 || pnetid1[i] == _S) && (pnetid2[i] == 0 || pnetid2[i] == _S)) break; if (pnetid1[i] != pnetid2[i]) return false; } return true; } /* Remove a pnetid from the pnet table. */ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct smc_ib_device *ibdev; struct smcd_dev *smcd; struct smc_net *sn; int rc = -ENOENT; int ibport; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* remove table entry */ mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || smc_pnet_match(pnetelem->pnet_name, pnet_name)) { list_del(&pnetelem->list); if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pr_warn_ratelimited("smc: net device %s " "erased user defined " "pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); } kfree(pnetelem); rc = 0; } } mutex_unlock(&pnettable->lock); /* if this is not the initial namespace, stop here */ if (net != &init_net) return rc; /* remove ib devices */ mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && (!pnet_name || smc_pnet_match(pnet_name, ibdev->pnetid[ibport]))) { pr_warn_ratelimited("smc: ib device %s ibport " "%d erased user defined " "pnetid %.16s\n", ibdev->ibdev->name, ibport + 1, ibdev->pnetid[ibport]); memset(ibdev->pnetid[ibport], 0, SMC_MAX_PNETID_LEN); ibdev->pnetid_by_user[ibport] = false; rc = 0; } } } mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->pnetid_by_user && (!pnet_name || smc_pnet_match(pnet_name, smcd->pnetid))) { pr_warn_ratelimited("smc: smcd device %s " "erased user defined pnetid " "%.16s\n", dev_name(&smcd->dibs->dev), smcd->pnetid); memset(smcd->pnetid, 0, SMC_MAX_PNETID_LEN); smcd->pnetid_by_user = false; rc = 0; } } mutex_unlock(&smcd_dev_list.mutex); return rc; } /* Add the reference to a given network device to the pnet table. */ static int smc_pnet_add_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { netdev_hold(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); pnetelem->ndev = ndev; rc = 0; pr_warn_ratelimited("smc: adding net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Remove the reference to a given network device from the pnet table. */ static int smc_pnet_remove_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pnetelem->ndev = NULL; rc = 0; pr_warn_ratelimited("smc: removing net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Apply pnetid to ib device when no pnetid is set. */ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, char *pnet_name) { bool applied = false; mutex_lock(&smc_ib_devices.mutex); if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } mutex_unlock(&smc_ib_devices.mutex); return applied; } /* Apply pnetid to smcd device when no pnetid is set. */ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) { bool applied = false; mutex_lock(&smcd_dev_list.mutex); if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } mutex_unlock(&smcd_dev_list.mutex); return applied; } /* The limit for pnetid is 16 characters. * Valid characters should be (single-byte character set) a-z, A-Z, 0-9. * Lower case letters are converted to upper case. * Interior blanks should not be used. */ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) { char *bf = skip_spaces(pnet_name); size_t len = strlen(bf); char *end = bf + len; if (!len) return false; while (--end >= bf && isspace(*end)) ; if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) return false; *pnetid++ = islower(*bf) ? toupper(*bf) : *bf; bf++; } *pnetid = '\0'; return true; } /* Find an infiniband device by a given name. The device might not exist. */ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || (ibdev->ibdev->dev.parent && !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, IB_DEVICE_NAME_MAX - 1))) { goto out; } } ibdev = NULL; out: mutex_unlock(&smc_ib_devices.mutex); return ibdev; } /* Find an smcd device by a given name. The device might not exist. */ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(&smcd_dev->dibs->dev), smcd_name, IB_DEVICE_NAME_MAX - 1) || (smcd_dev->dibs->dev.parent && !strncmp(dev_name(smcd_dev->dibs->dev.parent), smcd_name, IB_DEVICE_NAME_MAX - 1))) goto out; } smcd_dev = NULL; out: mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, char *eth_name, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct net_device *ndev, *base_ndev; u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; bool new_netdev; int rc; /* check if (base) netdev already has a pnetid. If there is one, we do * not want to add a pnet table entry */ rc = -EEXIST; ndev = dev_get_by_name(net, eth_name); /* dev_hold() */ if (ndev) { base_ndev = pnet_find_base_ndev(ndev); if (!smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid)) goto out_put; } /* add a new netdev entry to the pnet table if there isn't one */ rc = -ENOMEM; new_pe = kzalloc_obj(*new_pe); if (!new_pe) goto out_put; new_pe->type = SMC_PNET_ETH; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strscpy(new_pe->eth_name, eth_name); rc = -EEXIST; new_netdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { new_netdev = false; break; } } if (new_netdev) { if (ndev) { new_pe->ndev = ndev; netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_ATOMIC); } list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } if (ndev) pr_warn_ratelimited("smc: net device %s " "applied user defined pnetid %.16s\n", new_pe->eth_name, new_pe->pnet_name); return 0; out_put: dev_put(ndev); return rc; } static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, u8 ib_port, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct smc_ib_device *ib_dev; bool smcddev_applied = true; bool ibdev_applied = true; struct smcd_dev *smcd; bool new_ibdev; /* try to apply the pnetid to active devices */ ib_dev = smc_pnet_find_ib(ib_name); if (ib_dev) { ibdev_applied = smc_pnet_apply_ib(ib_dev, ib_port, pnet_name); if (ibdev_applied) pr_warn_ratelimited("smc: ib device %s ibport %d " "applied user defined pnetid " "%.16s\n", ib_dev->ibdev->name, ib_port, ib_dev->pnetid[ib_port - 1]); } smcd = smc_pnet_find_smcd(ib_name); if (smcd) { smcddev_applied = smc_pnet_apply_smcd(smcd, pnet_name); if (smcddev_applied) { pr_warn_ratelimited("smc: smcd device %s applied user defined pnetid %.16s\n", dev_name(&smcd->dibs->dev), smcd->pnetid); } } /* Apply fails when a device has a hardware-defined pnetid set, do not * add a pnet table entry in that case. */ if (!ibdev_applied || !smcddev_applied) return -EEXIST; /* add a new ib entry to the pnet table if there isn't one */ new_pe = kzalloc_obj(*new_pe); if (!new_pe) return -ENOMEM; new_pe->type = SMC_PNET_IB; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strscpy(new_pe->ib_name, ib_name); new_pe->ib_port = ib_port; new_ibdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { new_ibdev = false; break; } } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; } /* Append a pnetid to the end of the pnet table if not already on this list. */ static int smc_pnet_enter(struct net *net, struct nlattr *tb[]) { char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct smc_pnettable *pnettable; bool new_netdev = false; bool new_ibdev = false; struct smc_net *sn; u8 ibport = 1; char *string; int rc; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; rc = -EINVAL; if (!tb[SMC_PNETID_NAME]) goto error; string = (char *)nla_data(tb[SMC_PNETID_NAME]); if (!smc_pnetid_valid(string, pnet_name)) goto error; if (tb[SMC_PNETID_ETHNAME]) { string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); rc = smc_pnet_add_eth(pnettable, net, string, pnet_name); if (!rc) new_netdev = true; else if (rc != -EEXIST) goto error; } /* if this is not the initial namespace, stop here */ if (net != &init_net) return new_netdev ? 0 : -EEXIST; rc = -EINVAL; if (tb[SMC_PNETID_IBNAME]) { string = (char *)nla_data(tb[SMC_PNETID_IBNAME]); string = strim(string); if (tb[SMC_PNETID_IBPORT]) { ibport = nla_get_u8(tb[SMC_PNETID_IBPORT]); if (ibport < 1 || ibport > SMC_MAX_PORTS) goto error; } rc = smc_pnet_add_ib(pnettable, string, ibport, pnet_name); if (!rc) new_ibdev = true; else if (rc != -EEXIST) goto error; } return (new_netdev || new_ibdev) ? 0 : -EEXIST; error: return rc; } /* Convert an smc_pnetentry to a netlink attribute sequence */ static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem) { if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name)) return -1; if (pnetelem->type == SMC_PNET_ETH) { if (nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->eth_name)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a")) return -1; } if (pnetelem->type == SMC_PNET_IB) { if (nla_put_string(msg, SMC_PNETID_IBNAME, pnetelem->ib_name) || nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") || nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff)) return -1; } return 0; } static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); return smc_pnet_enter(net, info->attrs); } static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; return smc_pnet_remove_by_pnetid(net, (char *)nla_data(info->attrs[SMC_PNETID_NAME])); } static int smc_pnet_dump_start(struct netlink_callback *cb) { cb->args[0] = 0; return 0; } static int smc_pnet_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, u32 flags, struct smc_pnetentry *pnetelem) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family, flags, SMC_PNETID_GET); if (!hdr) return -ENOMEM; if (smc_pnet_set_nla(skb, pnetelem) < 0) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; } genlmsg_end(skb, hdr); return 0; } static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid, int start_idx) { struct smc_pnettable *pnettable; struct smc_pnetentry *pnetelem; struct smc_net *sn; int idx = 0; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* dump pnettable entries */ mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; if (idx++ < start_idx) continue; /* if this is not the initial namespace, dump only netdev */ if (net != &init_net && pnetelem->type != SMC_PNET_ETH) continue; if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI, pnetelem)) { --idx; break; } } mutex_unlock(&pnettable->lock); return idx; } static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx; idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NULL, cb->args[0]); cb->args[0] = idx; return skb->len; } /* Retrieve one PNETID entry */ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct sk_buff *msg; void *hdr; if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; _smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq, nla_data(info->attrs[SMC_PNETID_NAME]), 0); /* finish multi part message and send it */ hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, NLM_F_MULTI); if (!hdr) { nlmsg_free(msg); return -EMSGSIZE; } return genlmsg_reply(msg, info); } /* Remove and delete all pnetids from pnet table. */ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); smc_pnet_remove_by_pnetid(net, NULL); return 0; } /* SMC_PNETID generic netlink operation definition */ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start }, { .cmd = SMC_PNETID_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_flush } }; /* SMC_PNETID family definition */ static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, .policy = smc_pnet_policy, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, .n_ops = ARRAY_SIZE(smc_pnet_ops), .resv_start_op = SMC_PNETID_FLUSH + 1, }; bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe; bool rc = false; read_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pe, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { rc = true; goto unlock; } } unlock: read_unlock(&sn->pnetids_ndev.lock); return rc; } static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pi; pe = kzalloc_obj(*pe); if (!pe) return -ENOMEM; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pi->pnetid)) { refcount_inc(&pi->refcnt); kfree(pe); goto unlock; } } refcount_set(&pe->refcnt, 1); memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN); list_add_tail(&pe->list, &sn->pnetids_ndev.list); unlock: write_unlock(&sn->pnetids_ndev.lock); return 0; } static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pe2; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { if (refcount_dec_and_test(&pe->refcnt)) { list_del(&pe->list); kfree(pe); } break; } } write_unlock(&sn->pnetids_ndev.lock); } static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev, u8 *ndev_pnetid) { struct net_device *base_dev; base_dev = __pnet_find_base_ndev(dev); if (base_dev->flags & IFF_UP && !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port, ndev_pnetid)) { /* add to PNETIDs list */ smc_pnet_add_pnetid(net, ndev_pnetid); } } /* create initial list of netdevice pnetids */ static void smc_pnet_create_pnetids_list(struct net *net) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; /* Newly created netns do not have devices. * Do not even acquire rtnl. */ if (list_empty(&net->dev_base_head)) return; /* Note: This might not be needed, because smc_pnet_netdev_event() * is also calling smc_pnet_add_base_pnetid() when handling * NETDEV_UP event. */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); rtnl_unlock(); } /* clean up list of netdevice pnetids */ static void smc_pnet_destroy_pnetids_list(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *temp_pe; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) { list_del(&pe->list); kfree(pe); } write_unlock(&sn->pnetids_ndev.lock); } static int smc_pnet_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(event_dev); u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; switch (event) { case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_REGISTER: smc_pnet_add_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_UP: smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid); return NOTIFY_OK; case NETDEV_DOWN: event_dev = __pnet_find_base_ndev(event_dev); if (!smc_pnetid_by_dev_port(event_dev->dev.parent, event_dev->dev_port, ndev_pnetid)) { /* remove from PNETIDs list */ smc_pnet_remove_pnetid(net, ndev_pnetid); } return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block smc_netdev_notifier = { .notifier_call = smc_pnet_netdev_event }; /* init network namespace */ int smc_pnet_net_init(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnettable *pnettable = &sn->pnettable; struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock); smc_pnet_create_pnetids_list(net); return 0; } int __init smc_pnet_init(void) { int rc; rc = genl_register_family(&smc_pnet_nl_family); if (rc) return rc; rc = register_netdevice_notifier(&smc_netdev_notifier); if (rc) genl_unregister_family(&smc_pnet_nl_family); return rc; } /* exit network namespace */ void smc_pnet_net_exit(struct net *net) { /* flush pnet table */ smc_pnet_remove_by_pnetid(net, NULL); smc_pnet_destroy_pnetids_list(net); } void smc_pnet_exit(void) { unregister_netdevice_notifier(&smc_netdev_notifier); genl_unregister_family(&smc_pnet_nl_family); } static struct net_device *__pnet_find_base_ndev(struct net_device *ndev) { int i, nest_lvl; ASSERT_RTNL(); nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; if (list_empty(lower)) break; lower = lower->next; ndev = netdev_lower_get_next(ndev, &lower); } return ndev; } /* Determine one base device for stacked net devices. * If the lower device level contains more than one devices * (for instance with bonding slaves), just the first device * is used to reach a base device. */ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { rtnl_lock(); ndev = __pnet_find_base_ndev(ndev); rtnl_unlock(); return ndev; } static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, u8 *pnetid) { struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_pnetentry *pnetelem; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, struct smc_init_info *ini) { if (!ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, NULL)) { ini->ib_dev = ibdev; ini->ib_port = i; return 0; } if (ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, NULL, &ini->smcrv2)) { ini->smcrv2.ib_dev_v2 = ibdev; ini->smcrv2.ib_port_v2 = i; return 0; } return -ENODEV; } /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, struct smc_ib_device *known_dev, struct net *net) { struct smc_ib_device *ibdev; int i; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev || !rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) goto out; } } } out: mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id, vlan_id and net namespace */ void smc_pnet_find_alt_roce(struct smc_link_group *lgr, struct smc_init_info *ini, struct smc_ib_device *known_dev) { struct net *net = lgr->net; _smc_pnet_find_roce_by_pnetid(lgr->pnet_id, ini, known_dev, net); } /* if handshake network device belongs to a roce device, return its * IB device and port */ static void smc_pnet_find_rdma_dev(struct net_device *netdev, struct smc_init_info *ini) { struct net *net = dev_net(netdev); struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; /* check rdma net namespace */ if (!rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; ndev = ib_device_get_netdev(ibdev->ibdev, i); if (!ndev) continue; dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) break; } } } mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. * Searching stops at the first matching active IB device port with vlan_id * configured. * If nothing found, check pnetid table. * If nothing found, try to use handshake device */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *base_ndev; struct net *net; base_ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); if (smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(base_ndev, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { smc_pnet_find_rdma_dev(base_ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); } static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct smcd_dev *ismdev; ndev = pnet_find_base_ndev(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away && (!ini->ism_peer_gid[0].gid || !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id, ismdev))) { ini->ism_dev[0] = ismdev; break; } } mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: * determine ib_device and port belonging to used internal TCP socket * ethernet interface. */ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct net_device *dev; struct dst_entry *dst; rcu_read_lock(); dst = __sk_dst_get(sk); dev = dst ? dst_dev_rcu(dst) : NULL; dev_hold(dev); rcu_read_unlock(); if (dev) { smc_pnet_find_roce_by_pnetid(dev, ini); dev_put(dev); } } void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini) { struct net_device *dev; struct dst_entry *dst; ini->ism_dev[0] = NULL; rcu_read_lock(); dst = __sk_dst_get(sk); dev = dst ? dst_dev_rcu(dst) : NULL; dev_hold(dev); rcu_read_unlock(); if (dev) { smc_pnet_find_ism_by_pnetid(dev, ini); dev_put(dev); } } /* Lookup and apply a pnet table entry to the given ib device. */ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) { char *ib_name = smcibdev->ibdev->name; struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && tmp_pe->ib_port == ib_port) { smc_pnet_apply_ib(smcibdev, ib_port, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } /* Lookup and apply a pnet table entry to the given smcd device. */ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) { struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && (!strncmp(tmp_pe->ib_name, dev_name(&smcddev->dibs->dev), sizeof(tmp_pe->ib_name)) || (smcddev->dibs->dev.parent && !strncmp(tmp_pe->ib_name, dev_name(smcddev->dibs->dev.parent), sizeof(tmp_pe->ib_name))))) { smc_pnet_apply_smcd(smcddev, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } |
| 31 53 24 40 40 40 3 21 22 9 8 3019 3008 48 9 7 10 9 10 31 30 8 2 37 7 2 4 9 24 31 31 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fsnotify_backend.h> static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL static const struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static void __init dnotify_sysctl_init(void) { register_sysctl_init("fs", dnotify_sysctls); } #else #define dnotify_sysctl_init() do { } while (0) #endif static struct kmem_cache *dnotify_struct_cache __ro_after_init; static struct kmem_cache *dnotify_mark_cache __ro_after_init; static struct fsnotify_group *dnotify_group __ro_after_init; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = file_f_owner(dn->dn_filp); send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned int arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f = NULL; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } error = file_f_owner_allocate(filp); if (error) goto out_err; /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } f = fget_raw(fd); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); if (f) fput(f); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); dnotify_sysctl_init(); return 0; } module_init(dnotify_init) |
| 16 1 2 2 2 2 2 2 5 5 5 16 16 5 4 4 1 1 3 1 1 1 2 2 2 2 2 2 2 2 1 1 3 2 1 5 4 2 15 15 15 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" struct devlink_region { struct devlink *devlink; struct devlink_port *port; struct list_head list; union { const struct devlink_region_ops *ops; const struct devlink_port_region_ops *port_ops; }; struct mutex snapshot_lock; /* protects snapshot_list, * max_snapshots and cur_snapshots * consistency. */ struct list_head snapshot_list; u32 max_snapshots; u32 cur_snapshots; u64 size; }; struct devlink_snapshot { struct list_head list; struct devlink_region *region; u8 *data; u32 id; }; static struct devlink_region * devlink_region_get_by_name(struct devlink *devlink, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) if (!strcmp(region->ops->name, region_name)) return region; return NULL; } static struct devlink_region * devlink_port_region_get_by_name(struct devlink_port *port, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &port->region_list, list) if (!strcmp(region->port_ops->name, region_name)) return region; return NULL; } static struct devlink_snapshot * devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) { struct devlink_snapshot *snapshot; list_for_each_entry(snapshot, ®ion->snapshot_list, list) if (snapshot->id == id) return snapshot; return NULL; } static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) { struct nlattr *snap_attr; int err; snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT); if (!snap_attr) return -EMSGSIZE; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto nla_put_failure; nla_nest_end(msg, snap_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snap_attr); return err; } static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_region *region) { struct devlink_snapshot *snapshot; struct nlattr *snapshots_attr; int err; snapshots_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOTS); if (!snapshots_attr) return -EMSGSIZE; list_for_each_entry(snapshot, ®ion->snapshot_list, list) { err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot); if (err) goto nla_put_failure; } nla_nest_end(msg, snapshots_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snapshots_attr); return err; } static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct devlink_region *region) { void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; err = devlink_nl_put_handle(msg, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto nla_put_failure; err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_SIZE, region->size); if (err) goto nla_put_failure; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, region->max_snapshots); if (err) goto nla_put_failure; err = devlink_nl_region_snapshots_id_put(msg, devlink, region); if (err) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return err; } static struct sk_buff * devlink_nl_region_notify_build(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd, u32 portid, u32 seq) { struct devlink *devlink = region->devlink; struct sk_buff *msg; void *hdr; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return ERR_PTR(-ENOMEM); hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd); if (!hdr) { err = -EMSGSIZE; goto out_free_msg; } err = devlink_nl_put_handle(msg, devlink); if (err) goto out_cancel_msg; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto out_cancel_msg; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto out_cancel_msg; if (snapshot) { err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto out_cancel_msg; } else { err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_SIZE, region->size); if (err) goto out_cancel_msg; } genlmsg_end(msg, hdr); return msg; out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); return ERR_PTR(err); } static void devlink_nl_region_notify(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd) { struct devlink *devlink = region->devlink; struct sk_buff *msg; WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); if (IS_ERR(msg)) return; devlink_nl_notify_send(devlink, msg); } void devlink_regions_notify_register(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); } void devlink_regions_notify_unregister(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry_reverse(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); } /** * __devlink_snapshot_id_increment - Increment number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a new snapshot begins using an id. Load the count for the * given id from the snapshot xarray, increment it, and store it back. * * Called when a new snapshot is created with the given id. * * The id *must* have been previously allocated by * devlink_region_snapshot_id_get(). * * Returns 0 on success, or an error on failure. */ static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id) { unsigned long count; void *p; int err; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) { err = -EINVAL; goto unlock; } if (WARN_ON(!xa_is_value(p))) { err = -EINVAL; goto unlock; } count = xa_to_value(p); count++; err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC)); unlock: xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a snapshot is deleted and stops using an id. Load the count * for the given id from the snapshot xarray, decrement it, and store it * back. * * If the count reaches zero, erase this id from the xarray, freeing it * up for future re-use by devlink_region_snapshot_id_get(). * * Called when a snapshot using the given id is deleted, and when the * initial allocator of the id is finished using it. */ static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id) { unsigned long count; void *p; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) goto unlock; if (WARN_ON(!xa_is_value(p))) goto unlock; count = xa_to_value(p); if (count > 1) { count--; __xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC); } else { /* If this was the last user, we can erase this id */ __xa_erase(&devlink->snapshot_ids, id); } unlock: xa_unlock(&devlink->snapshot_ids); } /** * __devlink_snapshot_id_insert - Insert a specific snapshot ID * @devlink: devlink instance * @id: the snapshot id * * Mark the given snapshot id as used by inserting a zero value into the * snapshot xarray. * * This must be called while holding the devlink instance lock. Unlike * devlink_snapshot_id_get, the initial reference count is zero, not one. * It is expected that the id will immediately be used before * releasing the devlink instance lock. * * Returns zero on success, or an error code if the snapshot id could not * be inserted. */ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) { int err; xa_lock(&devlink->snapshot_ids); if (xa_load(&devlink->snapshot_ids, id)) { xa_unlock(&devlink->snapshot_ids); return -EEXIST; } err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), GFP_ATOMIC)); xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_region_snapshot_id_get - get snapshot ID * @devlink: devlink instance * @id: storage to return snapshot id * * Allocates a new snapshot id. Returns zero on success, or a negative * error on failure. Must be called while holding the devlink instance * lock. * * Snapshot IDs are tracked using an xarray which stores the number of * users of the snapshot id. * * Note that the caller of this function counts as a 'user', in order to * avoid race conditions. The caller must release its hold on the * snapshot by using devlink_region_snapshot_id_put. */ static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1), xa_limit_32b, GFP_KERNEL); } /** * __devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * Must be called only while holding the region snapshot lock. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ static int __devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot; int err; lockdep_assert_held(®ion->snapshot_lock); /* check if region can hold one more snapshot */ if (region->cur_snapshots == region->max_snapshots) return -ENOSPC; if (devlink_region_snapshot_get_by_id(region, snapshot_id)) return -EEXIST; snapshot = kzalloc_obj(*snapshot); if (!snapshot) return -ENOMEM; err = __devlink_snapshot_id_increment(devlink, snapshot_id); if (err) goto err_snapshot_id_increment; snapshot->id = snapshot_id; snapshot->region = region; snapshot->data = data; list_add_tail(&snapshot->list, ®ion->snapshot_list); region->cur_snapshots++; devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW); return 0; err_snapshot_id_increment: kfree(snapshot); return err; } static void devlink_region_snapshot_del(struct devlink_region *region, struct devlink_snapshot *snapshot) { struct devlink *devlink = region->devlink; lockdep_assert_held(®ion->snapshot_lock); devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); region->cur_snapshots--; list_del(&snapshot->list); region->ops->destructor(snapshot->data); __devlink_snapshot_id_decrement(devlink, snapshot->id); kfree(snapshot); } int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; struct sk_buff *msg; unsigned int index; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) return -EINVAL; if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, info->snd_portid, info->snd_seq, 0, region); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, struct netlink_callback *cb, struct devlink_port *port, int *idx, int start, int flags) { struct devlink_region *region; int err = 0; list_for_each_entry(region, &port->region_list, list) { if (*idx < start) { (*idx)++; continue; } err = devlink_nl_region_fill(msg, port->devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) goto out; (*idx)++; } out: return err; } static int devlink_nl_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_region *region; struct devlink_port *port; unsigned long port_index; int idx = 0; int err; list_for_each_entry(region, &devlink->region_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) { state->idx = idx; return err; } idx++; } xa_for_each(&devlink->ports, port_index, port) { err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx, state->idx, flags); if (err) { state->idx = idx; return err; } } return 0; } int devlink_nl_region_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one); } int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) || GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID)) return -EINVAL; region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; mutex_lock(®ion->snapshot_lock); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { mutex_unlock(®ion->snapshot_lock); return -EINVAL; } devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); return 0; } int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct nlattr *snapshot_id_attr; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; u8 *data; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) { NL_SET_ERR_MSG(info->extack, "No region name provided"); return -EINVAL; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG(info->extack, "The requested region does not exist"); return -EINVAL; } if (!region->ops->snapshot) { NL_SET_ERR_MSG(info->extack, "The requested region does not support taking an immediate snapshot"); return -EOPNOTSUPP; } mutex_lock(®ion->snapshot_lock); if (region->cur_snapshots == region->max_snapshots) { NL_SET_ERR_MSG(info->extack, "The region has reached the maximum number of stored snapshots"); err = -ENOSPC; goto unlock; } snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (snapshot_id_attr) { snapshot_id = nla_get_u32(snapshot_id_attr); if (devlink_region_snapshot_get_by_id(region, snapshot_id)) { NL_SET_ERR_MSG(info->extack, "The requested snapshot id is already in use"); err = -EEXIST; goto unlock; } err = __devlink_snapshot_id_insert(devlink, snapshot_id); if (err) goto unlock; } else { err = __devlink_region_snapshot_id_get(devlink, &snapshot_id); if (err) { NL_SET_ERR_MSG(info->extack, "Failed to allocate a new snapshot id"); goto unlock; } } if (port) err = region->port_ops->snapshot(port, region->port_ops, info->extack, &data); else err = region->ops->snapshot(devlink, region->ops, info->extack, &data); if (err) goto err_snapshot_capture; err = __devlink_region_snapshot_create(region, data, snapshot_id); if (err) goto err_snapshot_create; if (!snapshot_id_attr) { struct sk_buff *msg; snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (WARN_ON(!snapshot)) { err = -EINVAL; goto unlock; } msg = devlink_nl_region_notify_build(region, snapshot, DEVLINK_CMD_REGION_NEW, info->snd_portid, info->snd_seq); err = PTR_ERR_OR_ZERO(msg); if (err) goto err_notify; err = genlmsg_reply(msg, info); if (err) goto err_notify; } mutex_unlock(®ion->snapshot_lock); return 0; err_snapshot_create: region->ops->destructor(data); err_snapshot_capture: __devlink_snapshot_id_decrement(devlink, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; err_notify: devlink_region_snapshot_del(region, snapshot); unlock: mutex_unlock(®ion->snapshot_lock); return err; } static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, u8 *chunk, u32 chunk_size, u64 addr) { struct nlattr *chunk_attr; int err; chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK); if (!chunk_attr) return -EINVAL; err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk); if (err) goto nla_put_failure; err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr); if (err) goto nla_put_failure; nla_nest_end(msg, chunk_attr); return 0; nla_put_failure: nla_nest_cancel(msg, chunk_attr); return err; } #define DEVLINK_REGION_READ_CHUNK_SIZE 256 typedef int devlink_chunk_fill_t(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack); static int devlink_nl_region_read_fill(struct sk_buff *skb, devlink_chunk_fill_t *cb, void *cb_priv, u64 start_offset, u64 end_offset, u64 *new_offset, struct netlink_ext_ack *extack) { u64 curr_offset = start_offset; int err = 0; u8 *data; /* Allocate and re-use a single buffer */ data = kmalloc(DEVLINK_REGION_READ_CHUNK_SIZE, GFP_KERNEL); if (!data) return -ENOMEM; *new_offset = start_offset; while (curr_offset < end_offset) { u32 data_size; data_size = min_t(u32, end_offset - curr_offset, DEVLINK_REGION_READ_CHUNK_SIZE); err = cb(cb_priv, data, data_size, curr_offset, extack); if (err) break; err = devlink_nl_cmd_region_read_chunk_fill(skb, data, data_size, curr_offset); if (err) break; curr_offset += data_size; } *new_offset = curr_offset; kfree(data); return err; } static int devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack __always_unused *extack) { struct devlink_snapshot *snapshot = cb_priv; memcpy(chunk, &snapshot->data[curr_offset], chunk_size); return 0; } static int devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->port_ops->read(region->port, region->port_ops, extack, curr_offset, chunk_size, chunk); } static int devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->ops->read(region->devlink, region->ops, extack, curr_offset, chunk_size, chunk); } int devlink_nl_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct nlattr *chunks_attr, *region_attr, *snapshot_attr; u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->info.attrs; struct devlink_port *port = NULL; devlink_chunk_fill_t *region_cb; struct devlink_region *region; const char *region_name; struct devlink *devlink; unsigned int index; void *region_cb_priv; void *hdr; int err; start_offset = state->start_offset; devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs, false); if (IS_ERR(devlink)) return PTR_ERR(devlink); if (!attrs[DEVLINK_ATTR_REGION_NAME]) { NL_SET_ERR_MSG(cb->extack, "No region name provided"); err = -EINVAL; goto out_unlock; } if (attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) { err = -ENODEV; goto out_unlock; } } region_attr = attrs[DEVLINK_ATTR_REGION_NAME]; region_name = nla_data(region_attr); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG_ATTR(cb->extack, region_attr, "Requested region does not exist"); err = -EINVAL; goto out_unlock; } snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (!snapshot_attr) { if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); err = -EINVAL; goto out_unlock; } if (!region->ops->read) { NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read"); err = -EOPNOTSUPP; goto out_unlock; } if (port) region_cb = &devlink_region_port_direct_fill; else region_cb = &devlink_region_direct_fill; region_cb_priv = region; } else { struct devlink_snapshot *snapshot; u32 snapshot_id; if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot"); err = -EINVAL; goto out_unlock; } snapshot_id = nla_get_u32(snapshot_attr); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); err = -EINVAL; goto out_unlock; } region_cb = &devlink_region_snapshot_fill; region_cb_priv = snapshot; } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { if (!start_offset) start_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); } if (end_offset > region->size) end_offset = region->size; /* return 0 if there is no further data to read */ if (start_offset == end_offset) { err = 0; goto out_unlock; } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); if (!hdr) { err = -EMSGSIZE; goto out_unlock; } err = devlink_nl_put_handle(skb, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); if (err) goto nla_put_failure; chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS); if (!chunks_attr) { err = -EMSGSIZE; goto nla_put_failure; } err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv, start_offset, end_offset, &ret_offset, cb->extack); if (err && err != -EMSGSIZE) goto nla_put_failure; /* Check if there was any progress done to prevent infinite loop */ if (ret_offset == start_offset) { err = -EINVAL; goto nla_put_failure; } state->start_offset = ret_offset; nla_nest_end(skb, chunks_attr); genlmsg_end(skb, hdr); devl_unlock(devlink); devlink_put(devlink); return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); out_unlock: devl_unlock(devlink); devlink_put(devlink); return err; } /** * devl_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region */ struct devlink_region *devl_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_assert_locked(devlink); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); if (devlink_region_get_by_name(devlink, ops->name)) return ERR_PTR(-EEXIST); region = kzalloc_obj(*region); if (!region) return ERR_PTR(-ENOMEM); region->devlink = devlink; region->max_snapshots = region_max_snapshots; region->ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &devlink->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); return region; } EXPORT_SYMBOL_GPL(devl_region_create); /** * devlink_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_lock(devlink); region = devl_region_create(devlink, ops, region_max_snapshots, region_size); devl_unlock(devlink); return region; } EXPORT_SYMBOL_GPL(devlink_region_create); /** * devlink_port_region_create - create a new address region for a port * * @port: devlink port * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_port_region_create(struct devlink_port *port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink *devlink = port->devlink; struct devlink_region *region; int err = 0; ASSERT_DEVLINK_PORT_INITIALIZED(port); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); devl_lock(devlink); if (devlink_port_region_get_by_name(port, ops->name)) { err = -EEXIST; goto unlock; } region = kzalloc_obj(*region); if (!region) { err = -ENOMEM; goto unlock; } region->devlink = devlink; region->port = port; region->max_snapshots = region_max_snapshots; region->port_ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &port->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); devl_unlock(devlink); return region; unlock: devl_unlock(devlink); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(devlink_port_region_create); /** * devl_region_destroy - destroy address region * * @region: devlink region to destroy */ void devl_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot, *ts; devl_assert_locked(devlink); /* Free all snapshots of region */ mutex_lock(®ion->snapshot_lock); list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); list_del(®ion->list); mutex_destroy(®ion->snapshot_lock); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); kfree(region); } EXPORT_SYMBOL_GPL(devl_region_destroy); /** * devlink_region_destroy - destroy address region * * @region: devlink region to destroy * * Context: Takes and release devlink->lock <mutex>. */ void devlink_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; devl_lock(devlink); devl_region_destroy(region); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_region_destroy); /** * devlink_region_snapshot_id_get - get snapshot ID * * This callback should be called when adding a new snapshot, * Driver should use the same id for multiple snapshots taken * on multiple regions at the same time/by the same trigger. * * The caller of this function must use devlink_region_snapshot_id_put * when finished creating regions using this id. * * Returns zero on success, or a negative error code on failure. * * @devlink: devlink * @id: storage to return id */ int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return __devlink_region_snapshot_id_get(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); /** * devlink_region_snapshot_id_put - put snapshot ID reference * * This should be called by a driver after finishing creating snapshots * with an id. Doing so ensures that the ID can later be released in the * event that all snapshots using it have been destroyed. * * @devlink: devlink * @id: id to release reference on */ void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id) { __devlink_snapshot_id_decrement(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put); /** * devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { int err; mutex_lock(®ion->snapshot_lock); err = __devlink_region_snapshot_create(region, data, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); |
| 6 165 106 10 353 355 190 5 190 190 190 188 356 5 190 356 190 354 355 168 166 2 356 356 356 353 355 2569 2382 207 2385 201 203 1 10 9 1 10 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * blk-mq scheduling framework * * Copyright (C) 2016 Jens Axboe */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/list_sort.h> #include <trace/events/block.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-sched.h" #include "blk-wbt.h" /* * Mark a hardware queue as needing a restart. */ void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) { if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) return; set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } EXPORT_SYMBOL_GPL(blk_mq_sched_mark_restart_hctx); void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) { clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); /* * Order clearing SCHED_RESTART and list_empty_careful(&hctx->dispatch) * in blk_mq_run_hw_queue(). Its pair is the barrier in * blk_mq_dispatch_rq_list(). So dispatch code won't see SCHED_RESTART, * meantime new request added to hctx->dispatch is missed to check in * blk_mq_run_hw_queue(). */ smp_mb(); blk_mq_run_hw_queue(hctx, true); } static int sched_rq_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); return rqa->mq_hctx > rqb->mq_hctx; } static bool blk_mq_dispatch_hctx_list(struct list_head *rq_list) { struct blk_mq_hw_ctx *hctx = list_first_entry(rq_list, struct request, queuelist)->mq_hctx; struct request *rq; LIST_HEAD(hctx_list); list_for_each_entry(rq, rq_list, queuelist) { if (rq->mq_hctx != hctx) { list_cut_before(&hctx_list, rq_list, &rq->queuelist); goto dispatch; } } list_splice_tail_init(rq_list, &hctx_list); dispatch: return blk_mq_dispatch_rq_list(hctx, &hctx_list, false); } #define BLK_MQ_BUDGET_DELAY 3 /* ms units */ /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to * restart queue if .get_budget() fails to get the budget. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. */ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; bool multi_hctxs = false, run_queue = false; bool dispatched = false, busy = false; unsigned int max_dispatch; LIST_HEAD(rq_list); int count = 0; if (hctx->dispatch_busy) max_dispatch = 1; else max_dispatch = hctx->queue->nr_requests; do { struct request *rq; int budget_token; if (e->type->ops.has_work && !e->type->ops.has_work(hctx)) break; if (!list_empty_careful(&hctx->dispatch)) { busy = true; break; } budget_token = blk_mq_get_dispatch_budget(q); if (budget_token < 0) break; rq = e->type->ops.dispatch_request(hctx); if (!rq) { blk_mq_put_dispatch_budget(q, budget_token); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the * same queue and if we didn't dispatch then there's * no guarantee anyone will kick the queue. Kick it * ourselves. */ run_queue = true; break; } blk_mq_set_rq_budget_token(rq, budget_token); /* * Now this rq owns the budget which has to be released * if this rq won't be queued to driver via .queue_rq() * in blk_mq_dispatch_rq_list(). */ list_add_tail(&rq->queuelist, &rq_list); count++; if (rq->mq_hctx != hctx) multi_hctxs = true; /* * If we cannot get tag for the request, stop dequeueing * requests from the IO scheduler. We are unlikely to be able * to submit them anyway and it creates false impression for * scheduling heuristics that the device can take more IO. */ if (!blk_mq_get_driver_tag(rq)) break; } while (count < max_dispatch); if (!count) { if (run_queue) blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); } else if (multi_hctxs) { /* * Requests from different hctx may be dequeued from some * schedulers, such as bfq and deadline. * * Sort the requests in the list according to their hctx, * dispatch batching requests from same hctx at a time. */ list_sort(NULL, &rq_list, sched_rq_cmp); do { dispatched |= blk_mq_dispatch_hctx_list(&rq_list); } while (!list_empty(&rq_list)); } else { dispatched = blk_mq_dispatch_rq_list(hctx, &rq_list, false); } if (busy) return -EAGAIN; return !!dispatched; } static int blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) { unsigned long end = jiffies + HZ; int ret; do { ret = __blk_mq_do_dispatch_sched(hctx); if (ret != 1) break; if (need_resched() || time_is_before_jiffies(end)) { blk_mq_delay_run_hw_queue(hctx, 0); break; } } while (1); return ret; } static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { unsigned short idx = ctx->index_hw[hctx->type]; if (++idx == hctx->nr_ctx) idx = 0; return hctx->ctxs[idx]; } /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to * restart queue if .get_budget() fails to get the budget. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. */ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; LIST_HEAD(rq_list); struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from); int ret = 0; struct request *rq; do { int budget_token; if (!list_empty_careful(&hctx->dispatch)) { ret = -EAGAIN; break; } if (!sbitmap_any_bit_set(&hctx->ctx_map)) break; budget_token = blk_mq_get_dispatch_budget(q); if (budget_token < 0) break; rq = blk_mq_dequeue_from_ctx(hctx, ctx); if (!rq) { blk_mq_put_dispatch_budget(q, budget_token); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the * same queue and if we didn't dispatch then there's * no guarantee anyone will kick the queue. Kick it * ourselves. */ blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); break; } blk_mq_set_rq_budget_token(rq, budget_token); /* * Now this rq owns the budget which has to be released * if this rq won't be queued to driver via .queue_rq() * in blk_mq_dispatch_rq_list(). */ list_add(&rq->queuelist, &rq_list); /* round robin for fair dispatch */ ctx = blk_mq_next_ctx(hctx, rq->mq_ctx); } while (blk_mq_dispatch_rq_list(rq->mq_hctx, &rq_list, false)); WRITE_ONCE(hctx->dispatch_from, ctx); return ret; } static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { bool need_dispatch = false; LIST_HEAD(rq_list); /* * If we have previous entries on our dispatch list, grab them first for * more fair dispatch. */ if (!list_empty_careful(&hctx->dispatch)) { spin_lock(&hctx->lock); if (!list_empty(&hctx->dispatch)) list_splice_init(&hctx->dispatch, &rq_list); spin_unlock(&hctx->lock); } /* * Only ask the scheduler for requests, if we didn't have residual * requests from the dispatch list. This is to avoid the case where * we only ever dispatch a fraction of the requests available because * of low device queue depth. Once we pull requests out of the IO * scheduler, we can no longer merge or sort them. So it's best to * leave them there for as long as we can. Mark the hw queue as * needing a restart in that case. * * We want to dispatch from the scheduler if there was nothing * on the dispatch list or we were able to dispatch from the * dispatch list. */ if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); if (!blk_mq_dispatch_rq_list(hctx, &rq_list, true)) return 0; need_dispatch = true; } else { need_dispatch = hctx->dispatch_busy; } if (hctx->queue->elevator) return blk_mq_do_dispatch_sched(hctx); /* dequeue request one by one from sw queue if queue is busy */ if (need_dispatch) return blk_mq_do_dispatch_ctx(hctx); blk_mq_flush_busy_ctxs(hctx, &rq_list); blk_mq_dispatch_rq_list(hctx, &rq_list, true); return 0; } void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; /* RCU or SRCU read lock is needed before checking quiesced flag */ if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) return; /* * A return of -EAGAIN is an indication that hctx->dispatch is not * empty and we must run again in order to avoid starving flushes. */ if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN) { if (__blk_mq_sched_dispatch_requests(hctx) == -EAGAIN) blk_mq_run_hw_queue(hctx, true); } } bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; bool ret = false; enum hctx_type type; if (e && e->type->ops.bio_merge) { ret = e->type->ops.bio_merge(q, bio, nr_segs); goto out_put; } ctx = blk_mq_get_ctx(q); hctx = blk_mq_map_queue(bio->bi_opf, ctx); type = hctx->type; if (list_empty_careful(&ctx->rq_lists[type])) goto out_put; /* default per sw-queue merge */ spin_lock(&ctx->lock); /* * Reverse check our software queue for entries that we could * potentially merge with. Currently includes a hand-wavy stop * count of 8, to not spend too much time checking for merges. */ if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) ret = true; spin_unlock(&ctx->lock); out_put: return ret; } bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq, struct list_head *free) { return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq, free); } EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge); /* called in queue's release handler, tagset has gone away */ static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int flags) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) hctx->sched_tags = NULL; if (blk_mq_is_shared_tags(flags)) q->sched_shared_tags = NULL; } void blk_mq_sched_reg_debugfs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int memflags; unsigned long i; memflags = blk_debugfs_lock(q); blk_mq_debugfs_register_sched(q); queue_for_each_hw_ctx(q, hctx, i) blk_mq_debugfs_register_sched_hctx(q, hctx); blk_debugfs_unlock(q, memflags); } void blk_mq_sched_unreg_debugfs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; blk_debugfs_lock_nomemsave(q); queue_for_each_hw_ctx(q, hctx, i) blk_mq_debugfs_unregister_sched_hctx(hctx); blk_mq_debugfs_unregister_sched(q); blk_debugfs_unlock_nomemrestore(q); } void blk_mq_free_sched_tags(struct elevator_tags *et, struct blk_mq_tag_set *set) { unsigned long i; /* Shared tags are stored at index 0 in @tags. */ if (blk_mq_is_shared_tags(set->flags)) blk_mq_free_map_and_rqs(set, et->tags[0], BLK_MQ_NO_HCTX_IDX); else { for (i = 0; i < et->nr_hw_queues; i++) blk_mq_free_map_and_rqs(set, et->tags[i], i); } kfree(et); } void blk_mq_free_sched_res(struct elevator_resources *res, struct elevator_type *type, struct blk_mq_tag_set *set) { if (res->et) { blk_mq_free_sched_tags(res->et, set); res->et = NULL; } if (res->data) { blk_mq_free_sched_data(type, res->data); res->data = NULL; } } void blk_mq_free_sched_res_batch(struct xarray *elv_tbl, struct blk_mq_tag_set *set) { struct request_queue *q; struct elv_change_ctx *ctx; lockdep_assert_held_write(&set->update_nr_hwq_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { /* * Accessing q->elevator without holding q->elevator_lock is * safe because we're holding here set->update_nr_hwq_lock in * the writer context. So, scheduler update/switch code (which * acquires the same lock but in the reader context) can't run * concurrently. */ if (q->elevator) { ctx = xa_load(elv_tbl, q->id); if (!ctx) { WARN_ON_ONCE(1); continue; } blk_mq_free_sched_res(&ctx->res, ctx->type, set); } } } void blk_mq_free_sched_ctx_batch(struct xarray *elv_tbl) { unsigned long i; struct elv_change_ctx *ctx; xa_for_each(elv_tbl, i, ctx) { xa_erase(elv_tbl, i); kfree(ctx); } } int blk_mq_alloc_sched_ctx_batch(struct xarray *elv_tbl, struct blk_mq_tag_set *set) { struct request_queue *q; struct elv_change_ctx *ctx; lockdep_assert_held_write(&set->update_nr_hwq_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { ctx = kzalloc_obj(struct elv_change_ctx); if (!ctx) return -ENOMEM; if (xa_insert(elv_tbl, q->id, ctx, GFP_KERNEL)) { kfree(ctx); return -ENOMEM; } } return 0; } struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, unsigned int nr_hw_queues, unsigned int nr_requests) { unsigned int nr_tags; int i; struct elevator_tags *et; gfp_t gfp = GFP_NOIO | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; if (blk_mq_is_shared_tags(set->flags)) nr_tags = 1; else nr_tags = nr_hw_queues; et = kmalloc_flex(*et, tags, nr_tags, gfp); if (!et) return NULL; et->nr_requests = nr_requests; et->nr_hw_queues = nr_hw_queues; if (blk_mq_is_shared_tags(set->flags)) { /* Shared tags are stored at index 0 in @tags. */ et->tags[0] = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX, MAX_SCHED_RQ); if (!et->tags[0]) goto out; } else { for (i = 0; i < et->nr_hw_queues; i++) { et->tags[i] = blk_mq_alloc_map_and_rqs(set, i, et->nr_requests); if (!et->tags[i]) goto out_unwind; } } return et; out_unwind: while (--i >= 0) blk_mq_free_map_and_rqs(set, et->tags[i], i); out: kfree(et); return NULL; } int blk_mq_alloc_sched_res(struct request_queue *q, struct elevator_type *type, struct elevator_resources *res, unsigned int nr_hw_queues) { struct blk_mq_tag_set *set = q->tag_set; res->et = blk_mq_alloc_sched_tags(set, nr_hw_queues, blk_mq_default_nr_requests(set)); if (!res->et) return -ENOMEM; res->data = blk_mq_alloc_sched_data(q, type); if (IS_ERR(res->data)) { blk_mq_free_sched_tags(res->et, set); return -ENOMEM; } return 0; } int blk_mq_alloc_sched_res_batch(struct xarray *elv_tbl, struct blk_mq_tag_set *set, unsigned int nr_hw_queues) { struct elv_change_ctx *ctx; struct request_queue *q; int ret = -ENOMEM; lockdep_assert_held_write(&set->update_nr_hwq_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { /* * Accessing q->elevator without holding q->elevator_lock is * safe because we're holding here set->update_nr_hwq_lock in * the writer context. So, scheduler update/switch code (which * acquires the same lock but in the reader context) can't run * concurrently. */ if (q->elevator) { ctx = xa_load(elv_tbl, q->id); if (WARN_ON_ONCE(!ctx)) { ret = -ENOENT; goto out_unwind; } ret = blk_mq_alloc_sched_res(q, q->elevator->type, &ctx->res, nr_hw_queues); if (ret) goto out_unwind; } } return 0; out_unwind: list_for_each_entry_continue_reverse(q, &set->tag_list, tag_set_list) { if (q->elevator) { ctx = xa_load(elv_tbl, q->id); if (ctx) blk_mq_free_sched_res(&ctx->res, ctx->type, set); } } return ret; } /* caller must have a reference to @e, will grab another one if successful */ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e, struct elevator_resources *res) { unsigned int flags = q->tag_set->flags; struct elevator_tags *et = res->et; struct blk_mq_hw_ctx *hctx; struct elevator_queue *eq; unsigned long i; int ret; eq = elevator_alloc(q, e, res); if (!eq) return -ENOMEM; q->nr_requests = et->nr_requests; if (blk_mq_is_shared_tags(flags)) { /* Shared tags are stored at index 0 in @et->tags. */ q->sched_shared_tags = et->tags[0]; blk_mq_tag_update_sched_shared_tags(q, et->nr_requests); } queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_is_shared_tags(flags)) hctx->sched_tags = q->sched_shared_tags; else hctx->sched_tags = et->tags[i]; } ret = e->ops.init_sched(q, eq); if (ret) goto out; queue_for_each_hw_ctx(q, hctx, i) { if (e->ops.init_hctx) { ret = e->ops.init_hctx(hctx, i); if (ret) { blk_mq_exit_sched(q, eq); kobject_put(&eq->kobj); return ret; } } } return 0; out: blk_mq_sched_tags_teardown(q, flags); kobject_put(&eq->kobj); q->elevator = NULL; return ret; } /* * called in either blk_queue_cleanup or elevator_switch, tagset * is required for freeing requests */ void blk_mq_sched_free_rqs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; if (blk_mq_is_shared_tags(q->tag_set->flags)) { blk_mq_free_rqs(q->tag_set, q->sched_shared_tags, BLK_MQ_NO_HCTX_IDX); } else { queue_for_each_hw_ctx(q, hctx, i) { if (hctx->sched_tags) blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i); } } } void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) { struct blk_mq_hw_ctx *hctx; unsigned long i; unsigned int flags = 0; queue_for_each_hw_ctx(q, hctx, i) { if (e->type->ops.exit_hctx && hctx->sched_data) { e->type->ops.exit_hctx(hctx, i); hctx->sched_data = NULL; } flags = hctx->flags; } if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); blk_mq_sched_tags_teardown(q, flags); set_bit(ELEVATOR_FLAG_DYING, &q->elevator->flags); q->elevator = NULL; } |
| 1 3 2 22 92 93 93 83 24 24 22 4 4 92 92 1 94 93 83 93 83 4 21 22 4 1 2 1 1 11 12 91 3 83 1 12 1 11 4 3 15 13 2 12 1 1 11 3 2 2 5 2 3 2 6 2 2 8 4 4 21 8 15 14 7 8 10 1 9 42 26 29 46 46 44 2 2 1 1 13 4 5 2 25 9 21 18 29 12 26 23 26 14 48 6 17 16 9 9 9 3 9 18 9 28 9 17 17 17 28 28 28 18 3 3 2 3 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 | // SPDX-License-Identifier: GPL-2.0-only /* * common code for virtio vsock * * Copyright (C) 2013-2015 Red Hat, Inc. * Author: Asias He <asias@redhat.com> * Stefan Hajnoczi <stefanha@redhat.com> */ #include <linux/spinlock.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/virtio_vsock.h> #include <uapi/linux/vsockmon.h> #include <net/sock.h> #include <net/af_vsock.h> #define CREATE_TRACE_POINTS #include <trace/events/vsock_virtio_transport_common.h> /* How long to wait for graceful shutdown of a connection */ #define VSOCK_CLOSE_TIMEOUT (8 * HZ) /* Threshold for detecting small packets to copy */ #define GOOD_COPY_LEN 128 /* Max payload that can be collapsed into a single linear skb, using the same * allocation threshold as virtio_vsock_alloc_skb() to avoid adding pressure * on the page allocator. */ #define MAX_COLLAPSE_LEN \ SKB_MAX_ORDER(VIRTIO_VSOCK_SKB_HEADROOM, PAGE_ALLOC_COSTLY_ORDER) static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, bool cancel_timeout); static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs); static const struct virtio_transport * virtio_transport_get_ops(struct vsock_sock *vsk) { const struct vsock_transport *t = vsock_core_get_transport(vsk); if (WARN_ON(!t)) return NULL; return container_of(t, struct virtio_transport, transport); } static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops, struct virtio_vsock_pkt_info *info, size_t pkt_len) { struct iov_iter *iov_iter; if (!info->msg) return false; iov_iter = &info->msg->msg_iter; if (iov_iter->iov_offset) return false; /* We can't send whole iov. */ if (iov_iter->count > pkt_len) return false; /* Check that transport can send data in zerocopy mode. */ if (t_ops->can_msgzerocopy) { int pages_to_send = iov_iter_npages(iov_iter, MAX_SKB_FRAGS); /* +1 is for packet header. */ return t_ops->can_msgzerocopy(pages_to_send + 1); } return true; } static int virtio_transport_fill_skb(struct sk_buff *skb, struct virtio_vsock_pkt_info *info, size_t len, bool zcopy) { struct msghdr *msg = info->msg; if (zcopy) return __zerocopy_sg_from_iter(msg, NULL, skb, &msg->msg_iter, len, NULL); virtio_vsock_skb_put(skb, len); return skb_copy_datagram_from_iter_full(skb, 0, &msg->msg_iter, len); } static void virtio_transport_init_hdr(struct sk_buff *skb, struct virtio_vsock_pkt_info *info, size_t payload_len, u32 src_cid, u32 src_port, u32 dst_cid, u32 dst_port) { struct virtio_vsock_hdr *hdr; hdr = virtio_vsock_hdr(skb); hdr->type = cpu_to_le16(info->type); hdr->op = cpu_to_le16(info->op); hdr->src_cid = cpu_to_le64(src_cid); hdr->dst_cid = cpu_to_le64(dst_cid); hdr->src_port = cpu_to_le32(src_port); hdr->dst_port = cpu_to_le32(dst_port); hdr->flags = cpu_to_le32(info->flags); hdr->len = cpu_to_le32(payload_len); hdr->buf_alloc = cpu_to_le32(0); hdr->fwd_cnt = cpu_to_le32(0); } /* Packet capture */ static struct sk_buff *virtio_transport_build_skb(void *opaque) { struct virtio_vsock_hdr *pkt_hdr; struct sk_buff *pkt = opaque; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; size_t payload_len; /* A packet could be split to fit the RX buffer, so we use * the payload length from the header, which has been updated * by the sender to reflect the fragment size. */ pkt_hdr = virtio_vsock_hdr(pkt); payload_len = le32_to_cpu(pkt_hdr->len); skb = alloc_skb(sizeof(*hdr) + sizeof(*pkt_hdr) + payload_len, GFP_ATOMIC); if (!skb) return NULL; hdr = skb_put(skb, sizeof(*hdr)); /* pkt->hdr is little-endian so no need to byteswap here */ hdr->src_cid = pkt_hdr->src_cid; hdr->src_port = pkt_hdr->src_port; hdr->dst_cid = pkt_hdr->dst_cid; hdr->dst_port = pkt_hdr->dst_port; hdr->transport = cpu_to_le16(AF_VSOCK_TRANSPORT_VIRTIO); hdr->len = cpu_to_le16(sizeof(*pkt_hdr)); memset(hdr->reserved, 0, sizeof(hdr->reserved)); switch (le16_to_cpu(pkt_hdr->op)) { case VIRTIO_VSOCK_OP_REQUEST: case VIRTIO_VSOCK_OP_RESPONSE: hdr->op = cpu_to_le16(AF_VSOCK_OP_CONNECT); break; case VIRTIO_VSOCK_OP_RST: case VIRTIO_VSOCK_OP_SHUTDOWN: hdr->op = cpu_to_le16(AF_VSOCK_OP_DISCONNECT); break; case VIRTIO_VSOCK_OP_RW: hdr->op = cpu_to_le16(AF_VSOCK_OP_PAYLOAD); break; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: case VIRTIO_VSOCK_OP_CREDIT_REQUEST: hdr->op = cpu_to_le16(AF_VSOCK_OP_CONTROL); break; default: hdr->op = cpu_to_le16(AF_VSOCK_OP_UNKNOWN); break; } skb_put_data(skb, pkt_hdr, sizeof(*pkt_hdr)); if (payload_len) { struct iov_iter iov_iter; struct kvec kvec; void *data = skb_put(skb, payload_len); kvec.iov_base = data; kvec.iov_len = payload_len; iov_iter_kvec(&iov_iter, ITER_DEST, &kvec, 1, payload_len); if (skb_copy_datagram_iter(pkt, VIRTIO_VSOCK_SKB_CB(pkt)->offset, &iov_iter, payload_len)) { kfree_skb(skb); return NULL; } } return skb; } void virtio_transport_deliver_tap_pkt(struct sk_buff *skb) { if (virtio_vsock_skb_tap_delivered(skb)) return; vsock_deliver_tap(virtio_transport_build_skb, skb); virtio_vsock_skb_set_tap_delivered(skb); } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); static u16 virtio_transport_get_type(struct sock *sk) { if (sk->sk_type == SOCK_STREAM) return VIRTIO_VSOCK_TYPE_STREAM; else return VIRTIO_VSOCK_TYPE_SEQPACKET; } /* Returns new sk_buff on success, otherwise returns NULL. */ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, size_t payload_len, bool zcopy, struct ubuf_info *uarg, u32 src_cid, u32 src_port, u32 dst_cid, u32 dst_port) { struct vsock_sock *vsk; struct sk_buff *skb; size_t skb_len; skb_len = VIRTIO_VSOCK_SKB_HEADROOM; if (!zcopy) skb_len += payload_len; skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL); if (!skb) return NULL; virtio_transport_init_hdr(skb, info, payload_len, src_cid, src_port, dst_cid, dst_port); vsk = info->vsk; /* If 'vsk' != NULL then payload is always present, so we * will never call '__zerocopy_sg_from_iter()' below without * setting skb owner in 'skb_set_owner_w()'. The only case * when 'vsk' == NULL is VIRTIO_VSOCK_OP_RST control message * without payload. */ WARN_ON_ONCE(!(vsk && (info->msg && payload_len)) && zcopy); /* Set owner here, because '__zerocopy_sg_from_iter()' uses * owner of skb without check to update 'sk_wmem_alloc'. */ if (vsk) skb_set_owner_w(skb, sk_vsock(vsk)); if (info->msg && payload_len > 0) { int err; /* Bind the zerocopy lifetime before filling frags so error * rollback frees managed fixed-buffer pages through * the uarg-aware path. */ skb_zcopy_set(skb, uarg, NULL); err = virtio_transport_fill_skb(skb, info, payload_len, zcopy); if (err) goto out; if (msg_data_left(info->msg) == 0 && info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); if (info->msg->msg_flags & MSG_EOR) hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); } } if (info->reply) virtio_vsock_skb_set_reply(skb); trace_virtio_transport_alloc_pkt(src_cid, src_port, dst_cid, dst_port, payload_len, info->type, info->op, info->flags, zcopy); return skb; out: kfree_skb(skb); return NULL; } /* This function can only be used on connecting/connected sockets, * since a socket assigned to a transport is required. * * Do not use on listener sockets! */ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt_info *info) { u32 max_skb_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE; u32 src_cid, src_port, dst_cid, dst_port; const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; struct ubuf_info *uarg = NULL; u32 pkt_len = info->pkt_len; bool can_zcopy = false; bool have_uref = false; u32 rest_len; int ret; info->type = virtio_transport_get_type(sk_vsock(vsk)); t_ops = virtio_transport_get_ops(vsk); if (unlikely(!t_ops)) return -EFAULT; src_cid = t_ops->transport.get_local_cid(); src_port = vsk->local_addr.svm_port; if (!info->remote_cid) { dst_cid = vsk->remote_addr.svm_cid; dst_port = vsk->remote_addr.svm_port; } else { dst_cid = info->remote_cid; dst_port = info->remote_port; } vvs = vsk->trans; /* virtio_transport_get_credit might return less than pkt_len credit */ pkt_len = virtio_transport_get_credit(vvs, pkt_len); /* Do not send zero length OP_RW pkt */ if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW) return pkt_len; if (info->msg) { /* If zerocopy is not enabled by 'setsockopt()', we behave as * there is no MSG_ZEROCOPY flag set. */ if (!sock_flag(sk_vsock(vsk), SOCK_ZEROCOPY)) info->msg->msg_flags &= ~MSG_ZEROCOPY; if (info->msg->msg_flags & MSG_ZEROCOPY) can_zcopy = virtio_transport_can_zcopy(t_ops, info, pkt_len); if (can_zcopy) max_skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE, (MAX_SKB_FRAGS * PAGE_SIZE)); if (info->msg->msg_flags & MSG_ZEROCOPY && info->op == VIRTIO_VSOCK_OP_RW) { uarg = info->msg->msg_ubuf; if (!uarg) { uarg = msg_zerocopy_realloc(sk_vsock(vsk), pkt_len, NULL, false); if (!uarg) { virtio_transport_put_credit(vvs, pkt_len); return -ENOMEM; } if (!can_zcopy) uarg_to_msgzc(uarg)->zerocopy = 0; have_uref = true; } } } rest_len = pkt_len; do { struct sk_buff *skb; size_t skb_len; skb_len = min(max_skb_len, rest_len); skb = virtio_transport_alloc_skb(info, skb_len, can_zcopy, uarg, src_cid, src_port, dst_cid, dst_port); if (!skb) { ret = -ENOMEM; break; } virtio_transport_inc_tx_pkt(vvs, skb); ret = t_ops->send_pkt(skb, info->net); if (ret < 0) break; /* Both virtio and vhost 'send_pkt()' returns 'skb_len', * but for reliability use 'ret' instead of 'skb_len'. * Also if partial send happens (e.g. 'ret' != 'skb_len') * somehow, we break this loop, but account such returned * value in 'virtio_transport_put_credit()'. */ rest_len -= ret; if (WARN_ONCE(ret != skb_len, "'send_pkt()' returns %i, but %zu expected\n", ret, skb_len)) break; } while (rest_len); virtio_transport_put_credit(vvs, rest_len); /* msg_zerocopy_realloc() initializes the ubuf_info refcnt to 1. * skb_zcopy_set() increases it for each skb, so we can drop that * initial reference to keep it balanced. */ if (have_uref) { if (rest_len == pkt_len) /* No data sent, abort the notification. */ net_zcopy_put_abort(uarg, true); else net_zcopy_put(uarg); } /* Return number of bytes, if any data has been sent. */ if (rest_len != pkt_len) ret = pkt_len - rest_len; return ret; } static bool virtio_transport_can_collapse(struct sk_buff *skb) { /* skbs that are partially consumed, mark a SEQPACKET message boundary, * or are already large enough should not be collapsed: they either * need special accounting, carry protocol state, or already have a * good data-to-overhead ratio. */ if (VIRTIO_VSOCK_SKB_CB(skb)->offset) return false; if (le32_to_cpu(virtio_vsock_hdr(skb)->flags) & VIRTIO_VSOCK_SEQ_EOM) return false; if (skb->len >= MAX_COLLAPSE_LEN) return false; return true; } /* Iterate through the packets in the queue starting from the current skb to * count the number of bytes we can collapse. */ static unsigned int virtio_transport_collapse_size(struct sk_buff *skb, struct sk_buff_head *queue) { unsigned int target = skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset; while ((skb = skb_peek_next(skb, queue)) && virtio_transport_can_collapse(skb)) { unsigned int len = skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset; if (len > MAX_COLLAPSE_LEN - target) return target; target += len; } return target; } /* Called under lock_sock to compact the receive queue by merging small skbs. * @min_to_free: minimum number of skbs to eliminate from the queue. May free * more to fill each collapsed skb to capacity. */ static void virtio_transport_collapse_rx_queue(struct virtio_vsock_sock *vvs, u32 min_to_free) { struct sk_buff *skb, *next_skb, *new_skb = NULL; struct sk_buff_head new_queue; u32 saved = 0; __skb_queue_head_init(&new_queue); skb_queue_walk_safe(&vvs->rx_queue, skb, next_skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); u32 src_off = VIRTIO_VSOCK_SKB_CB(skb)->offset; u32 src_len = skb->len - src_off; bool keep; keep = !virtio_transport_can_collapse(skb); if (keep) { /* Finalize pending collapsed skb to preserve packet * ordering. */ if (new_skb) { __skb_queue_tail(&new_queue, new_skb); new_skb = NULL; saved--; } goto next; } /* Finalize if this packet won't fit in the remaining tailroom, * so we can allocate a right-sized new_skb. */ if (new_skb && src_len > skb_tailroom(new_skb)) { __skb_queue_tail(&new_queue, new_skb); new_skb = NULL; saved--; } if (!new_skb) { unsigned int alloc_size; /* Check after finalizing to opportunistically fill * each collapsed skb to capacity, merging more skbs * than strictly required. */ if (saved >= min_to_free) break; alloc_size = virtio_transport_collapse_size(skb, &vvs->rx_queue); /* Only this skb's data is eligible, nothing to merge * with. Keep as-is. */ if (alloc_size <= src_len) { keep = true; goto next; } new_skb = virtio_vsock_alloc_linear_skb(alloc_size + VIRTIO_VSOCK_SKB_HEADROOM, GFP_KERNEL); if (!new_skb) break; memcpy(virtio_vsock_hdr(new_skb), hdr, sizeof(struct virtio_vsock_hdr)); virtio_vsock_hdr(new_skb)->len = 0; } /* Cannot fail since src_off/src_len are within bounds, but if * it does, discard new_skb to avoid queuing corrupted data. */ if (WARN_ON_ONCE(skb_copy_bits(skb, src_off, skb_put(new_skb, src_len), src_len))) { kfree_skb(new_skb); new_skb = NULL; break; } le32_add_cpu(&virtio_vsock_hdr(new_skb)->len, src_len); virtio_vsock_hdr(new_skb)->flags |= hdr->flags; next: __skb_unlink(skb, &vvs->rx_queue); if (keep) { __skb_queue_tail(&new_queue, skb); } else { consume_skb(skb); saved++; } } if (new_skb) __skb_queue_tail(&new_queue, new_skb); skb_queue_splice(&new_queue, &vvs->rx_queue); } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, u32 len) { u64 skb_overhead = (skb_queue_len(&vvs->rx_queue) + 1) * SKB_TRUESIZE(0); /* Allow at most buf_alloc * 2 total budget (payload + overhead), * similar to how SO_RCVBUF is doubled to reserve space for sk_buff * metadata. Check payload against buf_alloc to be sure the other * peer is respecting the credit, and sk_buff overhead to bound * queue growth. */ if ((u64)vvs->buf_used + len > vvs->buf_alloc || skb_overhead > vvs->buf_alloc) return false; vvs->rx_bytes += len; vvs->buf_used += len; return true; } static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, u32 bytes_read, u32 bytes_dequeued) { vvs->rx_bytes -= bytes_read; vvs->buf_used -= bytes_dequeued; vvs->fwd_cnt += bytes_dequeued; } void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); spin_lock_bh(&vvs->rx_lock); vvs->last_fwd_cnt = vvs->fwd_cnt; hdr->fwd_cnt = cpu_to_le32(vvs->fwd_cnt); hdr->buf_alloc = cpu_to_le32(vvs->buf_alloc); spin_unlock_bh(&vvs->rx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); void virtio_transport_consume_skb_sent(struct sk_buff *skb, bool consume) { struct sock *s = skb->sk; if (s && skb->len) { struct vsock_sock *vs = vsock_sk(s); struct virtio_vsock_sock *vvs; vvs = vs->trans; spin_lock_bh(&vvs->tx_lock); vvs->bytes_unsent -= skb->len; spin_unlock_bh(&vvs->tx_lock); } if (consume) consume_skb(skb); } EXPORT_SYMBOL_GPL(virtio_transport_consume_skb_sent); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) { u32 ret; if (!credit) return 0; spin_lock_bh(&vvs->tx_lock); ret = min_t(u32, credit, virtio_transport_has_space(vvs)); vvs->tx_cnt += ret; vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); return ret; } EXPORT_SYMBOL_GPL(virtio_transport_get_credit); void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) { if (!credit) return; spin_lock_bh(&vvs->tx_lock); vvs->tx_cnt -= credit; vvs->bytes_unsent -= credit; spin_unlock_bh(&vvs->tx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); static int virtio_transport_send_credit_update(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, .vsk = vsk, .net = sock_net(sk_vsock(vsk)), }; return virtio_transport_send_pkt_info(vsk, &info); } static ssize_t virtio_transport_stream_do_peek(struct vsock_sock *vsk, struct msghdr *msg, size_t len) { struct virtio_vsock_sock *vvs = vsk->trans; struct sk_buff *skb; size_t total = 0; int err; spin_lock_bh(&vvs->rx_lock); skb_queue_walk(&vvs->rx_queue, skb) { size_t bytes; bytes = min_t(size_t, len - total, skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset); spin_unlock_bh(&vvs->rx_lock); /* sk_lock is held by caller so no one else can dequeue. * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ err = skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, &msg->msg_iter, bytes); if (err) goto out; total += bytes; spin_lock_bh(&vvs->rx_lock); if (total == len) break; } spin_unlock_bh(&vvs->rx_lock); return total; out: if (total) err = total; return err; } static ssize_t virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len) { struct virtio_vsock_sock *vvs = vsk->trans; struct sk_buff *skb; u32 fwd_cnt_delta; bool low_rx_bytes; int err = -EFAULT; size_t total = 0; u32 free_space; spin_lock_bh(&vvs->rx_lock); if (WARN_ONCE(skb_queue_empty(&vvs->rx_queue) && vvs->rx_bytes, "rx_queue is empty, but rx_bytes is non-zero\n")) { spin_unlock_bh(&vvs->rx_lock); return err; } while (total < len && !skb_queue_empty(&vvs->rx_queue)) { size_t bytes, dequeued = 0; skb = skb_peek(&vvs->rx_queue); bytes = min_t(size_t, len - total, skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset); /* sk_lock is held by caller so no one else can dequeue. * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ spin_unlock_bh(&vvs->rx_lock); err = skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, &msg->msg_iter, bytes); if (err) goto out; spin_lock_bh(&vvs->rx_lock); total += bytes; VIRTIO_VSOCK_SKB_CB(skb)->offset += bytes; if (skb->len == VIRTIO_VSOCK_SKB_CB(skb)->offset) { dequeued = le32_to_cpu(virtio_vsock_hdr(skb)->len); __skb_unlink(skb, &vvs->rx_queue); consume_skb(skb); } virtio_transport_dec_rx_pkt(vvs, bytes, dequeued); } fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt; free_space = vvs->buf_alloc - fwd_cnt_delta; low_rx_bytes = (vvs->rx_bytes < sock_rcvlowat(sk_vsock(vsk), 0, INT_MAX)); spin_unlock_bh(&vvs->rx_lock); /* To reduce the number of credit update messages, * don't update credits as long as lots of space is available. * Note: the limit chosen here is arbitrary. Setting the limit * too high causes extra messages. Too low causes transmitter * stalls. As stalls are in theory more expensive than extra * messages, we set the limit to a high value. TODO: experiment * with different values. Also send credit update message when * number of bytes in rx queue is not enough to wake up reader. */ if (fwd_cnt_delta && (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || low_rx_bytes)) virtio_transport_send_credit_update(vsk); return total; out: if (total) err = total; return err; } static ssize_t virtio_transport_seqpacket_do_peek(struct vsock_sock *vsk, struct msghdr *msg) { struct virtio_vsock_sock *vvs = vsk->trans; struct sk_buff *skb; size_t total, len; spin_lock_bh(&vvs->rx_lock); if (!vvs->msg_count) { spin_unlock_bh(&vvs->rx_lock); return 0; } total = 0; len = msg_data_left(msg); skb_queue_walk(&vvs->rx_queue, skb) { struct virtio_vsock_hdr *hdr; if (total < len) { size_t bytes; int err; bytes = len - total; if (bytes > skb->len) bytes = skb->len; spin_unlock_bh(&vvs->rx_lock); /* sk_lock is held by caller so no one else can dequeue. * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ err = skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, &msg->msg_iter, bytes); if (err) return err; spin_lock_bh(&vvs->rx_lock); } total += skb->len; hdr = virtio_vsock_hdr(skb); if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) { if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) msg->msg_flags |= MSG_EOR; break; } } spin_unlock_bh(&vvs->rx_lock); return total; } static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, struct msghdr *msg, int flags) { struct virtio_vsock_sock *vvs = vsk->trans; int dequeued_len = 0; size_t user_buf_len = msg_data_left(msg); bool msg_ready = false; struct sk_buff *skb; spin_lock_bh(&vvs->rx_lock); if (vvs->msg_count == 0) { spin_unlock_bh(&vvs->rx_lock); return 0; } while (!msg_ready) { struct virtio_vsock_hdr *hdr; size_t pkt_len; skb = __skb_dequeue(&vvs->rx_queue); if (!skb) break; hdr = virtio_vsock_hdr(skb); pkt_len = (size_t)le32_to_cpu(hdr->len); if (dequeued_len >= 0) { size_t bytes_to_copy; bytes_to_copy = min(user_buf_len, pkt_len); if (bytes_to_copy) { int err; /* sk_lock is held by caller so no one else can dequeue. * Unlock rx_lock since skb_copy_datagram_iter() may sleep. */ spin_unlock_bh(&vvs->rx_lock); err = skb_copy_datagram_iter(skb, 0, &msg->msg_iter, bytes_to_copy); if (err) { /* Copy of message failed. Rest of * fragments will be freed without copy. */ dequeued_len = err; } else { user_buf_len -= bytes_to_copy; } spin_lock_bh(&vvs->rx_lock); } if (dequeued_len >= 0) dequeued_len += pkt_len; } if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) { msg_ready = true; vvs->msg_count--; if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) msg->msg_flags |= MSG_EOR; } virtio_transport_dec_rx_pkt(vvs, pkt_len, pkt_len); kfree_skb(skb); } spin_unlock_bh(&vvs->rx_lock); virtio_transport_send_credit_update(vsk); return dequeued_len; } ssize_t virtio_transport_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags) { if (flags & MSG_PEEK) return virtio_transport_stream_do_peek(vsk, msg, len); else return virtio_transport_stream_do_dequeue(vsk, msg, len); } EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); ssize_t virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, struct msghdr *msg, int flags) { if (flags & MSG_PEEK) return virtio_transport_seqpacket_do_peek(vsk, msg); else return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags); } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); static u32 virtio_transport_tx_buf_size(struct virtio_vsock_sock *vvs) { /* The peer advertises its receive buffer via peer_buf_alloc, but we * cap it to our local buf_alloc so a remote peer cannot force us to * queue more data than our own buffer configuration allows. */ return min(vvs->peer_buf_alloc, vvs->buf_alloc); } int virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, struct msghdr *msg, size_t len) { struct virtio_vsock_sock *vvs = vsk->trans; spin_lock_bh(&vvs->tx_lock); if (len > virtio_transport_tx_buf_size(vvs)) { spin_unlock_bh(&vvs->tx_lock); return -EMSGSIZE; } spin_unlock_bh(&vvs->tx_lock); return virtio_transport_stream_enqueue(vsk, msg, len); } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue); int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; spin_lock_bh(&vvs->rx_lock); bytes = vvs->rx_bytes; spin_unlock_bh(&vvs->rx_lock); return bytes; } EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; u32 msg_count; spin_lock_bh(&vvs->rx_lock); msg_count = vvs->msg_count; spin_unlock_bh(&vvs->rx_lock); return msg_count; } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs) { s64 bytes; /* Use s64 arithmetic so if the peer shrinks peer_buf_alloc while * we have bytes in flight (tx_cnt - peer_fwd_cnt), the subtraction * does not underflow. */ bytes = (s64)virtio_transport_tx_buf_size(vvs) - (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; return bytes; } s64 virtio_transport_stream_has_space(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; spin_lock_bh(&vvs->tx_lock); bytes = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return bytes; } EXPORT_SYMBOL_GPL(virtio_transport_stream_has_space); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk) { struct virtio_vsock_sock *vvs; vvs = kzalloc_obj(*vvs); if (!vvs) return -ENOMEM; vsk->trans = vvs; vvs->vsk = vsk; if (psk && psk->trans) { struct virtio_vsock_sock *ptrans = psk->trans; vvs->peer_buf_alloc = ptrans->peer_buf_alloc; } if (vsk->buffer_size > VIRTIO_VSOCK_MAX_BUF_SIZE) vsk->buffer_size = VIRTIO_VSOCK_MAX_BUF_SIZE; vvs->buf_alloc = vsk->buffer_size; spin_lock_init(&vvs->rx_lock); spin_lock_init(&vvs->tx_lock); skb_queue_head_init(&vvs->rx_queue); return 0; } EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init); /* sk_lock held by the caller */ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val) { struct virtio_vsock_sock *vvs = vsk->trans; if (*val > VIRTIO_VSOCK_MAX_BUF_SIZE) *val = VIRTIO_VSOCK_MAX_BUF_SIZE; vvs->buf_alloc = *val; virtio_transport_send_credit_update(vsk); } EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size); int virtio_transport_notify_poll_in(struct vsock_sock *vsk, size_t target, bool *data_ready_now) { *data_ready_now = vsock_stream_has_data(vsk) >= target; return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_in); int virtio_transport_notify_poll_out(struct vsock_sock *vsk, size_t target, bool *space_avail_now) { s64 free_space; free_space = vsock_stream_has_space(vsk); if (free_space > 0) *space_avail_now = true; else if (free_space == 0) *space_avail_now = false; return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_out); int virtio_transport_notify_recv_init(struct vsock_sock *vsk, size_t target, struct vsock_transport_recv_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_init); int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk, size_t target, struct vsock_transport_recv_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_block); int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk, size_t target, struct vsock_transport_recv_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_dequeue); int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk, size_t target, ssize_t copied, bool data_read, struct vsock_transport_recv_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_post_dequeue); int virtio_transport_notify_send_init(struct vsock_sock *vsk, struct vsock_transport_send_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_send_init); int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk, struct vsock_transport_send_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_block); int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, struct vsock_transport_send_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_enqueue); int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written, struct vsock_transport_send_notify_data *data) { return 0; } EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue); u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk) { return vsk->buffer_size; } EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat); bool virtio_transport_stream_is_active(struct vsock_sock *vsk) { return true; } EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active); int virtio_transport_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr) { return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind); bool virtio_transport_dgram_allow(struct vsock_sock *vsk, u32 cid, u32 port) { return false; } EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow); int virtio_transport_connect(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, .vsk = vsk, .net = sock_net(sk_vsock(vsk)), }; return virtio_transport_send_pkt_info(vsk, &info); } EXPORT_SYMBOL_GPL(virtio_transport_connect); int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_SHUTDOWN, .flags = (mode & RCV_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | (mode & SEND_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_SEND : 0), .vsk = vsk, .net = sock_net(sk_vsock(vsk)), }; return virtio_transport_send_pkt_info(vsk, &info); } EXPORT_SYMBOL_GPL(virtio_transport_shutdown); int virtio_transport_dgram_enqueue(struct vsock_sock *vsk, struct sockaddr_vm *remote_addr, struct msghdr *msg, size_t dgram_len) { return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue); ssize_t virtio_transport_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg, size_t len) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RW, .msg = msg, .pkt_len = len, .vsk = vsk, .net = sock_net(sk_vsock(vsk)), }; return virtio_transport_send_pkt_info(vsk, &info); } EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue); void virtio_transport_destruct(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; virtio_transport_cancel_close_work(vsk, true); kfree(vvs); vsk->trans = NULL; } EXPORT_SYMBOL_GPL(virtio_transport_destruct); ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; size_t ret; spin_lock_bh(&vvs->tx_lock); ret = vvs->bytes_unsent; spin_unlock_bh(&vvs->tx_lock); return ret; } EXPORT_SYMBOL_GPL(virtio_transport_unsent_bytes); static int virtio_transport_reset(struct vsock_sock *vsk, struct sk_buff *skb) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, .reply = !!skb, .vsk = vsk, .net = sock_net(sk_vsock(vsk)), }; /* Send RST only if the original pkt is not a RST pkt */ if (skb && le16_to_cpu(virtio_vsock_hdr(skb)->op) == VIRTIO_VSOCK_OP_RST) return 0; return virtio_transport_send_pkt_info(vsk, &info); } /* Normally packets are associated with a socket. There may be no socket if an * attempt was made to connect to a socket that does not exist. * * net refers to the namespace of whoever sent the invalid message. For * loopback, this is the namespace of the socket. For vhost, this is the * namespace of the VM (i.e., vhost_vsock). */ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, struct sk_buff *skb, struct net *net) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, .type = le16_to_cpu(hdr->type), .reply = true, /* Set sk owner to socket we are replying to (may be NULL for * non-loopback). This keeps a reference to the sock and * sock_net(sk) until the reply skb is freed. */ .vsk = vsock_sk(skb->sk), /* net is not defined here because we pass it directly to * t->send_pkt(), instead of relying on * virtio_transport_send_pkt_info() to pass it. It is not needed * by virtio_transport_alloc_skb(). */ }; struct sk_buff *reply; /* Send RST only if the original pkt is not a RST pkt */ if (le16_to_cpu(hdr->op) == VIRTIO_VSOCK_OP_RST) return 0; if (!t) return -ENOTCONN; reply = virtio_transport_alloc_skb(&info, 0, false, NULL, le64_to_cpu(hdr->dst_cid), le32_to_cpu(hdr->dst_port), le64_to_cpu(hdr->src_cid), le32_to_cpu(hdr->src_port)); if (!reply) return -ENOMEM; return t->send_pkt(reply, net); } /* This function should be called with sk_lock held and SOCK_DONE set */ static void virtio_transport_remove_sock(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; /* We don't need to take rx_lock, as the socket is closing and we are * removing it. */ __skb_queue_purge(&vvs->rx_queue); vsock_remove_sock(vsk); } static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, bool cancel_timeout) { struct sock *sk = sk_vsock(vsk); if (vsk->close_work_scheduled && (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) { vsk->close_work_scheduled = false; virtio_transport_remove_sock(vsk); /* Release refcnt obtained when we scheduled the timeout */ sock_put(sk); } } static void virtio_transport_do_close(struct vsock_sock *vsk, bool cancel_timeout) { struct sock *sk = sk_vsock(vsk); sock_set_flag(sk, SOCK_DONE); WRITE_ONCE(vsk->peer_shutdown, SHUTDOWN_MASK); if (vsock_stream_has_data(vsk) <= 0) sk->sk_state = TCP_CLOSING; sk->sk_state_change(sk); virtio_transport_cancel_close_work(vsk, cancel_timeout); } static void virtio_transport_close_timeout(struct work_struct *work) { struct vsock_sock *vsk = container_of(work, struct vsock_sock, close_work.work); struct sock *sk = sk_vsock(vsk); sock_hold(sk); lock_sock(sk); if (!sock_flag(sk, SOCK_DONE)) { (void)virtio_transport_reset(vsk, NULL); virtio_transport_do_close(vsk, false); } vsk->close_work_scheduled = false; release_sock(sk); sock_put(sk); } /* User context, vsk->sk is locked */ static bool virtio_transport_close(struct vsock_sock *vsk) { struct sock *sk = &vsk->sk; if (!(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_CLOSING)) return true; /* Already received SHUTDOWN from peer, reply with RST */ if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) { (void)virtio_transport_reset(vsk, NULL); return true; } if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK) (void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK); if (!(current->flags & PF_EXITING)) vsock_linger(sk); if (sock_flag(sk, SOCK_DONE)) { return true; } sock_hold(sk); INIT_DELAYED_WORK(&vsk->close_work, virtio_transport_close_timeout); vsk->close_work_scheduled = true; schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT); return false; } void virtio_transport_release(struct vsock_sock *vsk) { struct sock *sk = &vsk->sk; bool remove_sock = true; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) remove_sock = virtio_transport_close(vsk); if (remove_sock) { sock_set_flag(sk, SOCK_DONE); virtio_transport_remove_sock(vsk); } } EXPORT_SYMBOL_GPL(virtio_transport_release); static int virtio_transport_recv_connecting(struct sock *sk, struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); int skerr; int err; switch (le16_to_cpu(hdr->op)) { case VIRTIO_VSOCK_OP_RESPONSE: sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; vsock_insert_connected(vsk); sk->sk_state_change(sk); break; case VIRTIO_VSOCK_OP_INVALID: break; case VIRTIO_VSOCK_OP_RST: skerr = ECONNRESET; err = 0; goto destroy; default: skerr = EPROTO; err = -EINVAL; goto destroy; } return 0; destroy: virtio_transport_reset(vsk, skb); sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; sk_error_report(sk); return err; } static bool virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct sk_buff *skb) { struct virtio_vsock_sock *vvs = vsk->trans; bool can_enqueue, free_pkt = false; u32 len, queue_max, queue_len; struct virtio_vsock_hdr *hdr; hdr = virtio_vsock_hdr(skb); len = le32_to_cpu(hdr->len); /* virtio_transport_inc_rx_pkt() rejects packets when the per-skb * overhead (skb_queue_len * SKB_TRUESIZE(0)) exceeds buf_alloc. * Proactively collapse the queue before that happens. * No rx_lock needed: lock_sock is held by caller, preventing * concurrent enqueue or dequeue. */ queue_max = vvs->buf_alloc / SKB_TRUESIZE(0); queue_len = skb_queue_len(&vvs->rx_queue); if (queue_len >= queue_max) { /* Walking a large queue may take a significant amount of time * and cache misses, causing traffic burstiness. Limit the * collapse to freeing room for this packet and the next one. * It may free more to fill each collapsed skb to capacity. */ virtio_transport_collapse_rx_queue(vvs, queue_len + 2 - queue_max); } spin_lock_bh(&vvs->rx_lock); can_enqueue = virtio_transport_inc_rx_pkt(vvs, len); if (!can_enqueue) goto out; if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) vvs->msg_count++; /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small * payload. Skip non-linear (e.g. zerocopy) skbs; these carry payload * in skb_shinfo. */ if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue) && !skb_is_nonlinear(skb)) { struct virtio_vsock_hdr *last_hdr; struct sk_buff *last_skb; last_skb = skb_peek_tail(&vvs->rx_queue); last_hdr = virtio_vsock_hdr(last_skb); /* If there is space in the last packet queued, we copy the * new packet in its buffer. We avoid this if the last packet * queued has VIRTIO_VSOCK_SEQ_EOM set, because this is * delimiter of SEQPACKET message, so 'pkt' is the first packet * of a new message. */ if (skb->len < skb_tailroom(last_skb) && !(le32_to_cpu(last_hdr->flags) & VIRTIO_VSOCK_SEQ_EOM)) { memcpy(skb_put(last_skb, skb->len), skb->data, skb->len); free_pkt = true; last_hdr->flags |= hdr->flags; le32_add_cpu(&last_hdr->len, len); goto out; } } __skb_queue_tail(&vvs->rx_queue, skb); out: spin_unlock_bh(&vvs->rx_lock); if (free_pkt) kfree_skb(skb); return can_enqueue; } static int virtio_transport_recv_connected(struct sock *sk, struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); int err = 0; switch (le16_to_cpu(hdr->op)) { case VIRTIO_VSOCK_OP_RW: if (!virtio_transport_recv_enqueue(vsk, skb)) { /* There is no more space to queue the packet, so let's * close the connection; otherwise, we'll lose data. */ (void)virtio_transport_reset(vsk, skb); virtio_transport_do_close(vsk, true); sk->sk_err = ENOBUFS; sk_error_report(sk); vsock_remove_sock(vsk); break; } vsock_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_REQUEST: virtio_transport_send_credit_update(vsk); break; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: sk->sk_write_space(sk); break; case VIRTIO_VSOCK_OP_SHUTDOWN: { u32 peer_shutdown = READ_ONCE(vsk->peer_shutdown); if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SHUTDOWN_RCV) peer_shutdown |= RCV_SHUTDOWN; if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) peer_shutdown |= SEND_SHUTDOWN; WRITE_ONCE(vsk->peer_shutdown, peer_shutdown); if (peer_shutdown == SHUTDOWN_MASK) { if (vsock_stream_has_data(vsk) <= 0 && !sock_flag(sk, SOCK_DONE)) { (void)virtio_transport_reset(vsk, NULL); virtio_transport_do_close(vsk, true); } /* Remove this socket anyway because the remote peer sent * the shutdown. This way a new connection will succeed * if the remote peer uses the same source port, * even if the old socket is still unreleased, but now disconnected. */ vsock_remove_sock(vsk); } if (le32_to_cpu(virtio_vsock_hdr(skb)->flags)) sk->sk_state_change(sk); break; } case VIRTIO_VSOCK_OP_RST: virtio_transport_do_close(vsk, true); break; default: err = -EINVAL; break; } kfree_skb(skb); return err; } static void virtio_transport_recv_disconnecting(struct sock *sk, struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); if (le16_to_cpu(hdr->op) == VIRTIO_VSOCK_OP_RST) virtio_transport_do_close(vsk, true); } static int virtio_transport_send_response(struct vsock_sock *vsk, struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RESPONSE, .remote_cid = le64_to_cpu(hdr->src_cid), .remote_port = le32_to_cpu(hdr->src_port), .reply = true, .vsk = vsk, .net = sock_net(sk_vsock(vsk)), }; return virtio_transport_send_pkt_info(vsk, &info); } static bool virtio_transport_space_update(struct sock *sk, struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); struct virtio_vsock_sock *vvs = vsk->trans; bool space_available; /* Listener sockets are not associated with any transport, so we are * not able to take the state to see if there is space available in the * remote peer, but since they are only used to receive requests, we * can assume that there is always space available in the other peer. */ if (!vvs) return true; /* buf_alloc and fwd_cnt is always included in the hdr */ spin_lock_bh(&vvs->tx_lock); vvs->peer_buf_alloc = le32_to_cpu(hdr->buf_alloc); vvs->peer_fwd_cnt = le32_to_cpu(hdr->fwd_cnt); space_available = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return space_available; } /* Handle server socket */ static int virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, struct virtio_transport *t) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); struct vsock_sock *vchild; struct sock *child; int ret; if (le16_to_cpu(hdr->op) != VIRTIO_VSOCK_OP_REQUEST) { virtio_transport_reset_no_sock(t, skb, sock_net(sk)); return -EINVAL; } if (sk_acceptq_is_full(sk)) { virtio_transport_reset_no_sock(t, skb, sock_net(sk)); return -ENOMEM; } /* __vsock_release() might have already flushed accept_queue. * Subsequent enqueues would lead to a memory |