| 33 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* * net/tipc/addr.c: TIPC address utility routines * * Copyright (c) 2000-2006, 2018, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "addr.h" #include "core.h" bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr) { if (!domain || (domain == addr)) return true; if (!legacy_format) return false; if (domain == tipc_cluster_mask(addr)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_CLUSTER_MASK)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_MASK)) /* domain <Z.0.0> */ return true; return false; } void tipc_set_node_id(struct net *net, u8 *id) { struct tipc_net *tn = tipc_net(net); memcpy(tn->node_id, id, NODE_ID_LEN); tipc_nodeid2string(tn->node_id_string, id); tn->trial_addr = hash128to32(id); pr_info("Node identity %s, cluster identity %u\n", tipc_own_id_string(net), tn->net_id); } void tipc_set_node_addr(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); u8 node_id[NODE_ID_LEN] = {0,}; tn->node_addr = addr; if (!tipc_own_id(net)) { sprintf(node_id, "%x", addr); tipc_set_node_id(net, node_id); } tn->trial_addr = addr; tn->addr_trial_end = jiffies; pr_info("Node number set to %u\n", addr); } char *tipc_nodeid2string(char *str, u8 *id) { int i; u8 c; /* Already a string ? */ for (i = 0; i < NODE_ID_LEN; i++) { c = id[i]; if (c >= '0' && c <= '9') continue; if (c >= 'A' && c <= 'Z') continue; if (c >= 'a' && c <= 'z') continue; if (c == '.') continue; if (c == ':') continue; if (c == '_') continue; if (c == '-') continue; if (c == '@') continue; if (c != 0) break; } if (i == NODE_ID_LEN) { memcpy(str, id, NODE_ID_LEN); str[NODE_ID_LEN] = 0; return str; } /* Translate to hex string */ for (i = 0; i < NODE_ID_LEN; i++) sprintf(&str[2 * i], "%02x", id[i]); /* Strip off trailing zeroes */ for (i = NODE_ID_STR_LEN - 2; str[i] == '0'; i--) str[i] = 0; return str; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * acpi_bus.h - ACPI Bus Driver ($Revision: 22 $) * * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> */ #ifndef __ACPI_BUS_H__ #define __ACPI_BUS_H__ #include <linux/completion.h> #include <linux/container_of.h> #include <linux/device.h> #include <linux/kobject.h> #include <linux/mutex.h> #include <linux/property.h> #include <linux/types.h> struct acpi_handle_list { u32 count; acpi_handle *handles; }; /* acpi_utils.h */ acpi_status acpi_extract_package(union acpi_object *package, struct acpi_buffer *format, struct acpi_buffer *buffer); acpi_status acpi_evaluate_integer(acpi_handle handle, acpi_string pathname, struct acpi_object_list *arguments, unsigned long long *data); bool acpi_evaluate_reference(acpi_handle handle, acpi_string pathname, struct acpi_object_list *arguments, struct acpi_handle_list *list); bool acpi_handle_list_equal(struct acpi_handle_list *list1, struct acpi_handle_list *list2); void acpi_handle_list_replace(struct acpi_handle_list *dst, struct acpi_handle_list *src); void acpi_handle_list_free(struct acpi_handle_list *list); bool acpi_device_dep(acpi_handle target, acpi_handle match); acpi_status acpi_evaluate_ost(acpi_handle handle, u32 source_event, u32 status_code, struct acpi_buffer *status_buf); bool acpi_has_method(acpi_handle handle, char *name); acpi_status acpi_execute_simple_method(acpi_handle handle, char *method, u64 arg); acpi_status acpi_evaluate_ej0(acpi_handle handle); acpi_status acpi_evaluate_lck(acpi_handle handle, int lock); acpi_status acpi_evaluate_reg(acpi_handle handle, u8 space_id, u32 function); bool acpi_ata_match(acpi_handle handle); bool acpi_bay_match(acpi_handle handle); bool acpi_dock_match(acpi_handle handle); bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs); union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4); #ifdef CONFIG_ACPI bool acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld); static inline union acpi_object * acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4, acpi_object_type type) { union acpi_object *obj; obj = acpi_evaluate_dsm(handle, guid, rev, func, argv4); if (obj && obj->type != type) { ACPI_FREE(obj); obj = NULL; } return obj; } #endif #define ACPI_INIT_DSM_ARGV4(cnt, eles) \ { \ .package.type = ACPI_TYPE_PACKAGE, \ .package.count = (cnt), \ .package.elements = (eles) \ } bool acpi_dev_found(const char *hid); bool acpi_dev_present(const char *hid, const char *uid, s64 hrv); bool acpi_reduced_hardware(void); #ifdef CONFIG_ACPI struct proc_dir_entry; #define ACPI_BUS_FILE_ROOT "acpi" extern struct proc_dir_entry *acpi_root_dir; enum acpi_bus_device_type { ACPI_BUS_TYPE_DEVICE = 0, ACPI_BUS_TYPE_POWER, ACPI_BUS_TYPE_PROCESSOR, ACPI_BUS_TYPE_THERMAL, ACPI_BUS_TYPE_POWER_BUTTON, ACPI_BUS_TYPE_SLEEP_BUTTON, ACPI_BUS_TYPE_ECDT_EC, ACPI_BUS_DEVICE_TYPE_COUNT }; struct acpi_driver; struct acpi_device; /* * ACPI Scan Handler * ----------------- */ struct acpi_hotplug_profile { struct kobject kobj; int (*scan_dependent)(struct acpi_device *adev); void (*notify_online)(struct acpi_device *adev); bool enabled:1; bool demand_offline:1; }; static inline struct acpi_hotplug_profile *to_acpi_hotplug_profile( struct kobject *kobj) { return container_of(kobj, struct acpi_hotplug_profile, kobj); } struct acpi_scan_handler { struct list_head list_node; const struct acpi_device_id *ids; bool (*match)(const char *idstr, const struct acpi_device_id **matchid); int (*attach)(struct acpi_device *dev, const struct acpi_device_id *id); void (*detach)(struct acpi_device *dev); void (*post_eject)(struct acpi_device *dev); void (*bind)(struct device *phys_dev); void (*unbind)(struct device *phys_dev); struct acpi_hotplug_profile hotplug; }; /* * ACPI Hotplug Context * -------------------- */ typedef int (*acpi_hp_notify) (struct acpi_device *, u32); typedef void (*acpi_hp_uevent) (struct acpi_device *, u32); typedef void (*acpi_hp_fixup) (struct acpi_device *); struct acpi_hotplug_context { struct acpi_device *self; acpi_hp_notify notify; acpi_hp_uevent uevent; acpi_hp_fixup fixup; }; /* * ACPI Driver * ----------- */ typedef int (*acpi_op_add) (struct acpi_device * device); typedef void (*acpi_op_remove) (struct acpi_device *device); typedef void (*acpi_op_notify) (struct acpi_device * device, u32 event); struct acpi_device_ops { acpi_op_add add; acpi_op_remove remove; acpi_op_notify notify; }; #define ACPI_DRIVER_ALL_NOTIFY_EVENTS 0x1 /* system AND device events */ struct acpi_driver { char name[80]; char class[80]; const struct acpi_device_id *ids; /* Supported Hardware IDs */ unsigned int flags; struct acpi_device_ops ops; struct device_driver drv; }; /* * ACPI Device * ----------- */ /* Status (_STA) */ struct acpi_device_status { u32 present:1; u32 enabled:1; u32 show_in_ui:1; u32 functional:1; u32 battery_present:1; u32 reserved:27; }; /* Flags */ struct acpi_device_flags { u32 dynamic_status:1; u32 removable:1; u32 ejectable:1; u32 power_manageable:1; u32 match_driver:1; u32 initialized:1; u32 visited:1; u32 hotplug_notify:1; u32 is_dock_station:1; u32 of_compatible_ok:1; u32 coherent_dma:1; u32 cca_seen:1; u32 enumeration_by_parent:1; u32 honor_deps:1; u32 reserved:18; }; /* File System */ struct acpi_device_dir { struct proc_dir_entry *entry; }; #define acpi_device_dir(d) ((d)->dir.entry) /* Plug and Play */ #define MAX_ACPI_DEVICE_NAME_LEN 40 #define MAX_ACPI_CLASS_NAME_LEN 20 typedef char acpi_bus_id[8]; typedef u64 acpi_bus_address; typedef char acpi_device_name[MAX_ACPI_DEVICE_NAME_LEN]; typedef char acpi_device_class[MAX_ACPI_CLASS_NAME_LEN]; struct acpi_hardware_id { struct list_head list; const char *id; }; struct acpi_pnp_type { u32 hardware_id:1; u32 bus_address:1; u32 platform_id:1; u32 backlight:1; u32 reserved:28; }; struct acpi_device_pnp { acpi_bus_id bus_id; /* Object name */ int instance_no; /* Instance number of this object */ struct acpi_pnp_type type; /* ID type */ acpi_bus_address bus_address; /* _ADR */ char *unique_id; /* _UID */ struct list_head ids; /* _HID and _CIDs */ acpi_device_name device_name; /* Driver-determined */ acpi_device_class device_class; /* " */ }; #define acpi_device_bid(d) ((d)->pnp.bus_id) #define acpi_device_adr(d) ((d)->pnp.bus_address) const char *acpi_device_hid(struct acpi_device *device); #define acpi_device_uid(d) ((d)->pnp.unique_id) #define acpi_device_name(d) ((d)->pnp.device_name) #define acpi_device_class(d) ((d)->pnp.device_class) /* Power Management */ struct acpi_device_power_flags { u32 explicit_get:1; /* _PSC present? */ u32 power_resources:1; /* Power resources */ u32 inrush_current:1; /* Serialize Dx->D0 */ u32 power_removed:1; /* Optimize Dx->D0 */ u32 ignore_parent:1; /* Power is independent of parent power state */ u32 dsw_present:1; /* _DSW present? */ u32 reserved:26; }; struct acpi_device_power_state { struct list_head resources; /* Power resources referenced */ struct { u8 valid:1; u8 explicit_set:1; /* _PSx present? */ u8 reserved:6; } flags; int power; /* % Power (compared to D0) */ int latency; /* Dx->D0 time (microseconds) */ }; struct acpi_device_power { int state; /* Current state */ struct acpi_device_power_flags flags; struct acpi_device_power_state states[ACPI_D_STATE_COUNT]; /* Power states (D0-D3Cold) */ u8 state_for_enumeration; /* Deepest power state for enumeration */ }; struct acpi_dep_data { struct list_head node; acpi_handle supplier; acpi_handle consumer; bool honor_dep; bool met; bool free_when_met; }; /* Performance Management */ struct acpi_device_perf_flags { u8 reserved:8; }; struct acpi_device_perf_state { struct { u8 valid:1; u8 reserved:7; } flags; u8 power; /* % Power (compared to P0) */ u8 performance; /* % Performance ( " ) */ int latency; /* Px->P0 time (microseconds) */ }; struct acpi_device_perf { int state; struct acpi_device_perf_flags flags; int state_count; struct acpi_device_perf_state *states; }; /* Wakeup Management */ struct acpi_device_wakeup_flags { u8 valid:1; /* Can successfully enable wakeup? */ u8 notifier_present:1; /* Wake-up notify handler has been installed */ }; struct acpi_device_wakeup_context { void (*func)(struct acpi_device_wakeup_context *context); struct device *dev; }; struct acpi_device_wakeup { acpi_handle gpe_device; u64 gpe_number; u64 sleep_state; struct list_head resources; struct acpi_device_wakeup_flags flags; struct acpi_device_wakeup_context context; struct wakeup_source *ws; int prepare_count; int enable_count; }; struct acpi_device_physical_node { struct list_head node; struct device *dev; unsigned int node_id; bool put_online:1; }; struct acpi_device_properties { struct list_head list; const guid_t *guid; union acpi_object *properties; void **bufs; }; /* ACPI Device Specific Data (_DSD) */ struct acpi_device_data { const union acpi_object *pointer; struct list_head properties; const union acpi_object *of_compatible; struct list_head subnodes; }; struct acpi_gpio_mapping; #define ACPI_DEVICE_SWNODE_ROOT 0 /* * The maximum expected number of CSI-2 data lanes. * * This number is not expected to ever have to be equal to or greater than the * number of bits in an unsigned long variable, but if it needs to be increased * above that limit, code will need to be adjusted accordingly. */ #define ACPI_DEVICE_CSI2_DATA_LANES 8 #define ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH 8 enum acpi_device_swnode_dev_props { ACPI_DEVICE_SWNODE_DEV_ROTATION, ACPI_DEVICE_SWNODE_DEV_CLOCK_FREQUENCY, ACPI_DEVICE_SWNODE_DEV_LED_MAX_MICROAMP, ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_MICROAMP, ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_TIMEOUT_US, ACPI_DEVICE_SWNODE_DEV_NUM_OF, ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES }; enum acpi_device_swnode_port_props { ACPI_DEVICE_SWNODE_PORT_REG, ACPI_DEVICE_SWNODE_PORT_NUM_OF, ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES }; enum acpi_device_swnode_ep_props { ACPI_DEVICE_SWNODE_EP_REMOTE_EP, ACPI_DEVICE_SWNODE_EP_BUS_TYPE, ACPI_DEVICE_SWNODE_EP_REG, ACPI_DEVICE_SWNODE_EP_CLOCK_LANES, ACPI_DEVICE_SWNODE_EP_DATA_LANES, ACPI_DEVICE_SWNODE_EP_LANE_POLARITIES, /* TX only */ ACPI_DEVICE_SWNODE_EP_LINK_FREQUENCIES, ACPI_DEVICE_SWNODE_EP_NUM_OF, ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES }; /* * Each device has a root software node plus two times as many nodes as the * number of CSI-2 ports. */ #define ACPI_DEVICE_SWNODE_PORT(port) (2 * (port) + 1) #define ACPI_DEVICE_SWNODE_EP(endpoint) \ (ACPI_DEVICE_SWNODE_PORT(endpoint) + 1) /** * struct acpi_device_software_node_port - MIPI DisCo for Imaging CSI-2 port * @port_name: Port name. * @data_lanes: "data-lanes" property values. * @lane_polarities: "lane-polarities" property values. * @link_frequencies: "link_frequencies" property values. * @port_nr: Port number. * @crs_crs2_local: _CRS CSI2 record present (i.e. this is a transmitter one). * @port_props: Port properties. * @ep_props: Endpoint properties. * @remote_ep: Reference to the remote endpoint. */ struct acpi_device_software_node_port { char port_name[ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH + 1]; u32 data_lanes[ACPI_DEVICE_CSI2_DATA_LANES]; u32 lane_polarities[ACPI_DEVICE_CSI2_DATA_LANES + 1 /* clock lane */]; u64 link_frequencies[ACPI_DEVICE_CSI2_DATA_LANES]; unsigned int port_nr; bool crs_csi2_local; struct property_entry port_props[ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES]; struct property_entry ep_props[ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES]; struct software_node_ref_args remote_ep[1]; }; /** * struct acpi_device_software_nodes - Software nodes for an ACPI device * @dev_props: Device properties. * @nodes: Software nodes for root as well as ports and endpoints. * @nodeprts: Array of software node pointers, for (un)registering them. * @ports: Information related to each port and endpoint within a port. * @num_ports: The number of ports. */ struct acpi_device_software_nodes { struct property_entry dev_props[ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES]; struct software_node *nodes; const struct software_node **nodeptrs; struct acpi_device_software_node_port *ports; unsigned int num_ports; }; /* Device */ struct acpi_device { u32 pld_crc; int device_type; acpi_handle handle; /* no handle for fixed hardware */ struct fwnode_handle fwnode; struct list_head wakeup_list; struct list_head del_list; struct acpi_device_status status; struct acpi_device_flags flags; struct acpi_device_pnp pnp; struct acpi_device_power power; struct acpi_device_wakeup wakeup; struct acpi_device_perf performance; struct acpi_device_dir dir; struct acpi_device_data data; struct acpi_scan_handler *handler; struct acpi_hotplug_context *hp; struct acpi_device_software_nodes *swnodes; const struct acpi_gpio_mapping *driver_gpios; void *driver_data; struct device dev; unsigned int physical_node_count; unsigned int dep_unmet; struct list_head physical_node_list; struct mutex physical_node_lock; void (*remove)(struct acpi_device *); }; /* Non-device subnode */ struct acpi_data_node { struct list_head sibling; const char *name; acpi_handle handle; struct fwnode_handle fwnode; struct fwnode_handle *parent; struct acpi_device_data data; struct kobject kobj; struct completion kobj_done; }; extern const struct fwnode_operations acpi_device_fwnode_ops; extern const struct fwnode_operations acpi_data_fwnode_ops; extern const struct fwnode_operations acpi_static_fwnode_ops; bool is_acpi_device_node(const struct fwnode_handle *fwnode); bool is_acpi_data_node(const struct fwnode_handle *fwnode); static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return (is_acpi_device_node(fwnode) || is_acpi_data_node(fwnode)); } #define to_acpi_device_node(__fwnode) \ ({ \ typeof(__fwnode) __to_acpi_device_node_fwnode = __fwnode; \ \ is_acpi_device_node(__to_acpi_device_node_fwnode) ? \ container_of(__to_acpi_device_node_fwnode, \ struct acpi_device, fwnode) : \ NULL; \ }) #define to_acpi_data_node(__fwnode) \ ({ \ typeof(__fwnode) __to_acpi_data_node_fwnode = __fwnode; \ \ is_acpi_data_node(__to_acpi_data_node_fwnode) ? \ container_of(__to_acpi_data_node_fwnode, \ struct acpi_data_node, fwnode) : \ NULL; \ }) static inline bool is_acpi_static_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_static_fwnode_ops; } static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return is_acpi_data_node(fwnode) ? (!strcmp(to_acpi_data_node(fwnode)->name, name)) : false; } static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return &adev->fwnode; } static inline void *acpi_driver_data(struct acpi_device *d) { return d->driver_data; } #define to_acpi_device(d) container_of(d, struct acpi_device, dev) #define to_acpi_driver(d) container_of_const(d, struct acpi_driver, drv) static inline struct acpi_device *acpi_dev_parent(struct acpi_device *adev) { if (adev->dev.parent) return to_acpi_device(adev->dev.parent); return NULL; } static inline void acpi_set_device_status(struct acpi_device *adev, u32 sta) { *((u32 *)&adev->status) = sta; } static inline void acpi_set_hp_context(struct acpi_device *adev, struct acpi_hotplug_context *hp) { hp->self = adev; adev->hp = hp; } void acpi_initialize_hp_context(struct acpi_device *adev, struct acpi_hotplug_context *hp, acpi_hp_notify notify, acpi_hp_uevent uevent); /* acpi_device.dev.bus == &acpi_bus_type */ extern const struct bus_type acpi_bus_type; int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); int acpi_dev_for_each_child(struct acpi_device *adev, int (*fn)(struct acpi_device *, void *), void *data); int acpi_dev_for_each_child_reverse(struct acpi_device *adev, int (*fn)(struct acpi_device *, void *), void *data); /* * Events * ------ */ struct acpi_bus_event { struct list_head node; acpi_device_class device_class; acpi_bus_id bus_id; u32 type; u32 data; }; extern struct kobject *acpi_kobj; extern int acpi_bus_generate_netlink_event(const char*, const char*, u8, int); void acpi_bus_private_data_handler(acpi_handle, void *); int acpi_bus_get_private_data(acpi_handle, void **); int acpi_bus_attach_private_data(acpi_handle, void *); void acpi_bus_detach_private_data(acpi_handle); int acpi_dev_install_notify_handler(struct acpi_device *adev, u32 handler_type, acpi_notify_handler handler, void *context); void acpi_dev_remove_notify_handler(struct acpi_device *adev, u32 handler_type, acpi_notify_handler handler); extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32); extern int register_acpi_notifier(struct notifier_block *); extern int unregister_acpi_notifier(struct notifier_block *); /* * External Functions */ acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); int acpi_bus_get_status(struct acpi_device *device); int acpi_bus_set_power(acpi_handle handle, int state); const char *acpi_power_state_string(int state); int acpi_device_set_power(struct acpi_device *device, int state); int acpi_bus_init_power(struct acpi_device *device); int acpi_device_fix_up_power(struct acpi_device *device); void acpi_device_fix_up_power_extended(struct acpi_device *adev); void acpi_device_fix_up_power_children(struct acpi_device *adev); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); void acpi_dev_power_up_children_with_adr(struct acpi_device *adev); u8 acpi_dev_power_state_for_wake(struct acpi_device *adev); int acpi_device_power_add_dependent(struct acpi_device *adev, struct device *dev); void acpi_device_power_remove_dependent(struct acpi_device *adev, struct device *dev); #ifdef CONFIG_PM bool acpi_bus_can_wakeup(acpi_handle handle); #else static inline bool acpi_bus_can_wakeup(acpi_handle handle) { return false; } #endif void acpi_scan_lock_acquire(void); void acpi_scan_lock_release(void); void acpi_lock_hp_context(void); void acpi_unlock_hp_context(void); int acpi_scan_add_handler(struct acpi_scan_handler *handler); /* * use a macro to avoid include chaining to get THIS_MODULE */ #define acpi_bus_register_driver(drv) \ __acpi_bus_register_driver(drv, THIS_MODULE) int __acpi_bus_register_driver(struct acpi_driver *driver, struct module *owner); void acpi_bus_unregister_driver(struct acpi_driver *driver); int acpi_bus_scan(acpi_handle handle); void acpi_bus_trim(struct acpi_device *start); acpi_status acpi_bus_get_ejd(acpi_handle handle, acpi_handle * ejd); int acpi_match_device_ids(struct acpi_device *device, const struct acpi_device_id *ids); void acpi_set_modalias(struct acpi_device *adev, const char *default_id, char *modalias, size_t len); static inline bool acpi_device_enumerated(struct acpi_device *adev) { return adev && adev->flags.initialized && adev->flags.visited; } /** * module_acpi_driver(acpi_driver) - Helper macro for registering an ACPI driver * @__acpi_driver: acpi_driver struct * * Helper macro for ACPI drivers which do not do anything special in module * init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() */ #define module_acpi_driver(__acpi_driver) \ module_driver(__acpi_driver, acpi_bus_register_driver, \ acpi_bus_unregister_driver) /* * Bind physical devices with ACPI devices */ struct acpi_bus_type { struct list_head list; const char *name; bool (*match)(struct device *dev); struct acpi_device * (*find_companion)(struct device *); void (*setup)(struct device *); }; int register_acpi_bus_type(struct acpi_bus_type *); int unregister_acpi_bus_type(struct acpi_bus_type *); int acpi_bind_one(struct device *dev, struct acpi_device *adev); int acpi_unbind_one(struct device *dev); enum acpi_bridge_type { ACPI_BRIDGE_TYPE_PCIE = 1, ACPI_BRIDGE_TYPE_CXL, }; struct acpi_pci_root { struct acpi_device * device; struct pci_bus *bus; u16 segment; int bridge_type; struct resource secondary; /* downstream bus range */ u32 osc_support_set; /* _OSC state of support bits */ u32 osc_control_set; /* _OSC state of control bits */ u32 osc_ext_support_set; /* _OSC state of extended support bits */ u32 osc_ext_control_set; /* _OSC state of extended control bits */ phys_addr_t mcfg_addr; }; /* helper */ struct iommu_ops; bool acpi_dma_supported(const struct acpi_device *adev); enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev); int acpi_iommu_fwspec_init(struct device *dev, u32 id, struct fwnode_handle *fwnode); int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map); int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id); static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { return acpi_dma_configure_id(dev, attr, NULL); } struct acpi_device *acpi_find_child_device(struct acpi_device *parent, u64 address, bool check_children); struct acpi_device *acpi_find_child_by_adr(struct acpi_device *adev, acpi_bus_address adr); int acpi_is_root_bridge(acpi_handle); struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle); int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state); int acpi_disable_wakeup_device_power(struct acpi_device *dev); #ifdef CONFIG_X86 bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *status); bool acpi_quirk_skip_acpi_ac_and_battery(void); int acpi_install_cmos_rtc_space_handler(acpi_handle handle); void acpi_remove_cmos_rtc_space_handler(acpi_handle handle); int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip); #else static inline bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *status) { return false; } static inline bool acpi_quirk_skip_acpi_ac_and_battery(void) { return false; } static inline int acpi_install_cmos_rtc_space_handler(acpi_handle handle) { return 1; } static inline void acpi_remove_cmos_rtc_space_handler(acpi_handle handle) { } static inline int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) { *skip = false; return 0; } #endif #if IS_ENABLED(CONFIG_X86_ANDROID_TABLETS) bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev); bool acpi_quirk_skip_gpio_event_handlers(void); #else static inline bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev) { return false; } static inline bool acpi_quirk_skip_gpio_event_handlers(void) { return false; } #endif #ifdef CONFIG_PM void acpi_pm_wakeup_event(struct device *dev); acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev, void (*func)(struct acpi_device_wakeup_context *context)); acpi_status acpi_remove_pm_notifier(struct acpi_device *adev); bool acpi_pm_device_can_wakeup(struct device *dev); int acpi_pm_device_sleep_state(struct device *, int *, int); int acpi_pm_set_device_wakeup(struct device *dev, bool enable); #else static inline void acpi_pm_wakeup_event(struct device *dev) { } static inline acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev, void (*func)(struct acpi_device_wakeup_context *context)) { return AE_SUPPORT; } static inline acpi_status acpi_remove_pm_notifier(struct acpi_device *adev) { return AE_SUPPORT; } static inline bool acpi_pm_device_can_wakeup(struct device *dev) { return false; } static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m) { if (p) *p = ACPI_STATE_D0; return (m >= ACPI_STATE_D0 && m <= ACPI_STATE_D3_COLD) ? m : ACPI_STATE_D0; } static inline int acpi_pm_set_device_wakeup(struct device *dev, bool enable) { return -ENODEV; } #endif #ifdef CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT bool acpi_sleep_state_supported(u8 sleep_state); #else static inline bool acpi_sleep_state_supported(u8 sleep_state) { return false; } #endif #ifdef CONFIG_ACPI_SLEEP u32 acpi_target_system_state(void); #else static inline u32 acpi_target_system_state(void) { return ACPI_STATE_S0; } #endif static inline bool acpi_device_power_manageable(struct acpi_device *adev) { return adev->flags.power_manageable; } static inline bool acpi_device_can_wakeup(struct acpi_device *adev) { return adev->wakeup.flags.valid; } static inline bool acpi_device_can_poweroff(struct acpi_device *adev) { return adev->power.states[ACPI_STATE_D3_COLD].flags.valid || ((acpi_gbl_FADT.header.revision < 6) && adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set); } int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer); static inline bool acpi_dev_hid_match(struct acpi_device *adev, const char *hid2) { const char *hid1 = acpi_device_hid(adev); return hid1 && hid2 && !strcmp(hid1, hid2); } static inline bool acpi_str_uid_match(struct acpi_device *adev, const char *uid2) { const char *uid1 = acpi_device_uid(adev); return uid1 && uid2 && !strcmp(uid1, uid2); } static inline bool acpi_int_uid_match(struct acpi_device *adev, u64 uid2) { u64 uid1; return !acpi_dev_uid_to_integer(adev, &uid1) && uid1 == uid2; } #define TYPE_ENTRY(type, x) \ const type: x, \ type: x #define ACPI_STR_TYPES(match) \ TYPE_ENTRY(unsigned char *, match), \ TYPE_ENTRY(signed char *, match), \ TYPE_ENTRY(char *, match), \ TYPE_ENTRY(void *, match) /** * acpi_dev_uid_match - Match device by supplied UID * @adev: ACPI device to match. * @uid2: Unique ID of the device. * * Matches UID in @adev with given @uid2. * * Returns: %true if matches, %false otherwise. */ #define acpi_dev_uid_match(adev, uid2) \ _Generic(uid2, \ /* Treat @uid2 as a string for acpi string types */ \ ACPI_STR_TYPES(acpi_str_uid_match), \ /* Treat as an integer otherwise */ \ default: acpi_int_uid_match)(adev, uid2) /** * acpi_dev_hid_uid_match - Match device by supplied HID and UID * @adev: ACPI device to match. * @hid2: Hardware ID of the device. * @uid2: Unique ID of the device, pass NULL to not check _UID. * * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2 * will be treated as a match. If user wants to validate @uid2, it should be * done before calling this function. * * Returns: %true if matches or @uid2 is NULL, %false otherwise. */ #define acpi_dev_hid_uid_match(adev, hid2, uid2) \ (acpi_dev_hid_match(adev, hid2) && \ /* Distinguish integer 0 from NULL @uid2 */ \ (_Generic(uid2, ACPI_STR_TYPES(!(uid2)), default: 0) || \ acpi_dev_uid_match(adev, uid2))) void acpi_dev_clear_dependencies(struct acpi_device *supplier); bool acpi_dev_ready_for_enumeration(const struct acpi_device *device); struct acpi_device *acpi_dev_get_next_consumer_dev(struct acpi_device *supplier, struct acpi_device *start); /** * for_each_acpi_consumer_dev - iterate over the consumer ACPI devices for a * given supplier * @supplier: Pointer to the supplier's ACPI device * @consumer: Pointer to &struct acpi_device to hold the consumer, initially NULL */ #define for_each_acpi_consumer_dev(supplier, consumer) \ for (consumer = acpi_dev_get_next_consumer_dev(supplier, NULL); \ consumer; \ consumer = acpi_dev_get_next_consumer_dev(supplier, consumer)) struct acpi_device * acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const char *uid, s64 hrv); struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); /** * for_each_acpi_dev_match - iterate over ACPI devices that matching the criteria * @adev: pointer to the matching ACPI device, NULL at the end of the loop * @hid: Hardware ID of the device. * @uid: Unique ID of the device, pass NULL to not check _UID * @hrv: Hardware Revision of the device, pass -1 to not check _HRV * * The caller is responsible for invoking acpi_dev_put() on the returned device. */ #define for_each_acpi_dev_match(adev, hid, uid, hrv) \ for (adev = acpi_dev_get_first_match_dev(hid, uid, hrv); \ adev; \ adev = acpi_dev_get_next_match_dev(adev, hid, uid, hrv)) static inline struct acpi_device *acpi_dev_get(struct acpi_device *adev) { return adev ? to_acpi_device(get_device(&adev->dev)) : NULL; } static inline void acpi_dev_put(struct acpi_device *adev) { if (adev) put_device(&adev->dev); } struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); struct acpi_device *acpi_get_acpi_dev(acpi_handle handle); static inline void acpi_put_acpi_dev(struct acpi_device *adev) { acpi_dev_put(adev); } int acpi_wait_for_acpi_ipmi(void); int acpi_scan_add_dep(acpi_handle handle, struct acpi_handle_list *dep_devices); u32 arch_acpi_add_auto_dep(acpi_handle handle); #else /* CONFIG_ACPI */ static inline int register_acpi_bus_type(void *bus) { return 0; } static inline int unregister_acpi_bus_type(void *bus) { return 0; } static inline int acpi_wait_for_acpi_ipmi(void) { return 0; } static inline const char *acpi_device_hid(struct acpi_device *device) { return ""; } static inline bool acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld) { return false; } #define for_each_acpi_consumer_dev(supplier, consumer) \ for (consumer = NULL; false && (supplier);) #define for_each_acpi_dev_match(adev, hid, uid, hrv) \ for (adev = NULL; false && (hid) && (uid) && (hrv); ) #endif /* CONFIG_ACPI */ #endif /*__ACPI_BUS_H__*/ |
| 145 147 147 147 517 517 411 413 413 413 413 413 521 521 413 522 148 148 146 146 519 519 414 414 413 414 20 520 522 520 414 518 148 142 9 137 137 547 545 124 124 568 405 140 140 137 405 17 388 403 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net-sysfs.c - network device class and attributes * * Copyright (c) 2003 Stephen Hemminger <shemminger@osdl.org> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/sched/isolation.h> #include <linux/nsproxy.h> #include <net/sock.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/pm_runtime.h> #include <linux/of.h> #include <linux/of_net.h> #include <linux/cpu.h> #include <net/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/rps.h> #include "dev.h" #include "net-sysfs.h" #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; /* Caller holds RTNL, netdev->lock or RCU */ static inline int dev_isalive(const struct net_device *dev) { return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; } /* There is a possible ABBA deadlock between rtnl_lock and kernfs_node->active, * when unregistering a net device and accessing associated sysfs files. The * potential deadlock is as follow: * * CPU 0 CPU 1 * * rtnl_lock vfs_read * unregister_netdevice_many kernfs_seq_start * device_del / kobject_put kernfs_get_active (kn->active++) * kernfs_drain sysfs_kf_seq_show * wait_event( rtnl_lock * kn->active == KN_DEACTIVATED_BIAS) -> waits on CPU 0 to release * -> waits on CPU 1 to decrease kn->active the rtnl lock. * * The historical fix was to use rtnl_trylock with restart_syscall to bail out * of sysfs operations when the lock couldn't be taken. This fixed the above * issue as it allowed CPU 1 to bail out of the ABBA situation. * * But it came with performances issues, as syscalls are being restarted in * loops when there was contention on the rtnl lock, with huge slow downs in * specific scenarios (e.g. lots of virtual interfaces created and userspace * daemons querying their attributes). * * The idea below is to bail out of the active kernfs_node protection * (kn->active) while trying to take the rtnl lock. * * This replaces rtnl_lock() and still has to be used with rtnl_unlock(). The * net device is guaranteed to be alive if this returns successfully. */ static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr, struct net_device *ndev) { struct kernfs_node *kn; int ret = 0; /* First, we hold a reference to the net device as the unregistration * path might run in parallel. This will ensure the net device and the * associated sysfs objects won't be freed while we try to take the rtnl * lock. */ dev_hold(ndev); /* sysfs_break_active_protection was introduced to allow self-removal of * devices and their associated sysfs files by bailing out of the * sysfs/kernfs protection. We do this here to allow the unregistration * path to complete in parallel. The following takes a reference on the * kobject and the kernfs_node being accessed. * * This works because we hold a reference onto the net device and the * unregistration path will wait for us eventually in netdev_run_todo * (outside an rtnl lock section). */ kn = sysfs_break_active_protection(kobj, attr); /* We can now try to take the rtnl lock. This can't deadlock us as the * unregistration path is able to drain sysfs files (kernfs_node) thanks * to the above dance. */ if (rtnl_lock_interruptible()) { ret = -ERESTARTSYS; goto unbreak; } /* Check dismantle on the device hasn't started, otherwise deny the * operation. */ if (!dev_isalive(ndev)) { rtnl_unlock(); ret = -ENODEV; goto unbreak; } /* We are now sure the device dismantle hasn't started nor that it can * start before we exit the locking section as we hold the rtnl lock. * There's no need to keep unbreaking the sysfs protection nor to hold * a net device reference from that point; that was only needed to take * the rtnl lock. */ unbreak: sysfs_unbreak_active_protection(kn); dev_put(ndev); return ret; } /* use same locking rules as GIF* ioctl's */ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf, ssize_t (*format)(const struct net_device *, char *)) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; rcu_read_lock(); if (dev_isalive(ndev)) ret = (*format)(ndev, buf); rcu_read_unlock(); return ret; } /* generate a show function for simple field */ #define NETDEVICE_SHOW(field, format_string) \ static ssize_t format_##field(const struct net_device *dev, char *buf) \ { \ return sysfs_emit(buf, format_string, READ_ONCE(dev->field)); \ } \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ return netdev_show(dev, attr, buf, format_##field); \ } \ #define NETDEVICE_SHOW_RO(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RO(field) #define NETDEVICE_SHOW_RW(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RW(field) /* use same locking and permission rules as SIF* ioctl's */ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); if (ret) goto err; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) goto err; ret = (*set)(netdev, new); if (ret == 0) ret = len; rtnl_unlock(); err: return ret; } /* Same as netdev_store() but takes netdev_lock() instead of rtnl_lock() */ static ssize_t netdev_lock_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); if (ret) return ret; netdev_lock(netdev); if (dev_isalive(netdev)) { ret = (*set)(netdev, new); if (ret == 0) ret = len; } netdev_unlock(netdev); return ret; } NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); NETDEVICE_SHOW_RO(ifindex, fmt_dec); NETDEVICE_SHOW_RO(type, fmt_dec); NETDEVICE_SHOW_RO(link_mode, fmt_dec); static ssize_t iflink_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, dev_get_iflink(ndev)); } static DEVICE_ATTR_RO(iflink); static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) { return sysfs_emit(buf, fmt_dec, READ_ONCE(dev->name_assign_type)); } static ssize_t name_assign_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; if (READ_ONCE(ndev->name_assign_type) != NET_NAME_UNKNOWN) ret = netdev_show(dev, attr, buf, format_name_assign_type); return ret; } static DEVICE_ATTR_RO(name_assign_type); /* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; down_read(&dev_addr_sem); rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } static DEVICE_ATTR_RO(address); static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); int ret = -EINVAL; rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); rcu_read_unlock(); return ret; } static DEVICE_ATTR_RO(broadcast); static int change_carrier(struct net_device *dev, unsigned long new_carrier) { if (!netif_running(dev)) return -EINVAL; return dev_change_carrier(dev, (bool)new_carrier); } static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_carrier; this helps returning early * without hitting the locking section in netdev_store. */ if (!netdev->netdev_ops->ndo_change_carrier) return -EOPNOTSUPP; return netdev_store(dev, attr, buf, len, change_carrier); } static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; if (netif_running(netdev)) { /* Synchronize carrier state with link watch, * see also rtnl_getlink(). */ linkwatch_sync_dev(netdev); ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RW(carrier); static ssize_t speed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) ret = sysfs_emit(buf, fmt_dec, cmd.base.speed); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(speed); static ssize_t duplex_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) { const char *duplex; switch (cmd.base.duplex) { case DUPLEX_HALF: duplex = "half"; break; case DUPLEX_FULL: duplex = "full"; break; default: duplex = "unknown"; break; } ret = sysfs_emit(buf, "%s\n", duplex); } } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(duplex); static ssize_t testing_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sysfs_emit(buf, fmt_dec, !!netif_testing(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(testing); static ssize_t dormant_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sysfs_emit(buf, fmt_dec, !!netif_dormant(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(dormant); static const char *const operstates[] = { "unknown", "notpresent", /* currently unused */ "down", "lowerlayerdown", "testing", "dormant", "up" }; static ssize_t operstate_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; operstate = READ_ONCE(netdev->operstate); if (!netif_running(netdev)) operstate = IF_OPER_DOWN; if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ return sysfs_emit(buf, "%s\n", operstates[operstate]); } static DEVICE_ATTR_RO(operstate); static ssize_t carrier_changes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_up_count) + atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_changes); static ssize_t carrier_up_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_up_count)); } static DEVICE_ATTR_RO(carrier_up_count); static ssize_t carrier_down_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_down_count); /* read-write attributes */ static int change_mtu(struct net_device *dev, unsigned long new_mtu) { return dev_set_mtu(dev, (int)new_mtu); } static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_mtu); } NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *dev, unsigned long new_flags) { return dev_change_flags(dev, (unsigned int)new_flags, NULL); } static ssize_t flags_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_flags); } NETDEVICE_SHOW_RW(flags, fmt_hex); static ssize_t tx_queue_len_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, dev_change_tx_queue_len); } NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec); static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) { netdev_set_gro_flush_timeout(dev, val); return 0; } static ssize_t gro_flush_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_lock_store(dev, attr, buf, len, change_gro_flush_timeout); } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) { if (val > S32_MAX) return -ERANGE; netdev_set_defer_hard_irqs(dev, (u32)val); return 0; } static ssize_t napi_defer_hard_irqs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_lock_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); size_t count = len; ssize_t ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ if (len > 0 && buf[len - 1] == '\n') --count; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = dev_set_alias(netdev, buf, count); if (ret < 0) goto err; ret = len; netdev_state_change(netdev); err: rtnl_unlock(); return ret; } static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); char tmp[IFALIASZ]; ssize_t ret; ret = dev_get_alias(netdev, tmp, sizeof(tmp)); if (ret > 0) ret = sysfs_emit(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); static int change_group(struct net_device *dev, unsigned long new_group) { dev_set_group(dev, (int)new_group); return 0; } static ssize_t group_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_group); } NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, 0644, group_show, group_store); static int change_proto_down(struct net_device *dev, unsigned long proto_down) { return dev_change_proto_down(dev, (bool)proto_down); } static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); struct netdev_phys_item_id ppid; ssize_t ret; /* The check is also done in dev_get_phys_port_id; this helps returning * early without hitting the locking section below. */ if (!netdev->netdev_ops->ndo_get_phys_port_id) return -EOPNOTSUPP; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = dev_get_phys_port_id(netdev, &ppid); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_id); static ssize_t phys_port_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); char name[IFNAMSIZ]; ssize_t ret; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the locking section below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->devlink_port) return -EOPNOTSUPP; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = dev_get_phys_port_name(netdev, name, sizeof(name)); if (!ret) ret = sysfs_emit(buf, "%s\n", name); rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_name); static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); struct netdev_phys_item_id ppid = { }; ssize_t ret; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the locking section below. This works * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->devlink_port) return -EOPNOTSUPP; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_switch_id); static ssize_t threaded_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; rcu_read_lock(); if (dev_isalive(netdev)) ret = sysfs_emit(buf, fmt_dec, READ_ONCE(netdev->threaded)); rcu_read_unlock(); return ret; } static int modify_napi_threaded(struct net_device *dev, unsigned long val) { int ret; if (list_empty(&dev->napi_list)) return -EOPNOTSUPP; if (val != 0 && val != 1) return -EOPNOTSUPP; ret = dev_set_threaded(dev, val); return ret; } static ssize_t threaded_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_lock_store(dev, attr, buf, len, modify_napi_threaded); } static DEVICE_ATTR_RW(threaded); static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, &dev_attr_name_assign_type.attr, &dev_attr_addr_assign_type.attr, &dev_attr_addr_len.attr, &dev_attr_link_mode.attr, &dev_attr_address.attr, &dev_attr_broadcast.attr, &dev_attr_speed.attr, &dev_attr_duplex.attr, &dev_attr_dormant.attr, &dev_attr_testing.attr, &dev_attr_operstate.attr, &dev_attr_carrier_changes.attr, &dev_attr_ifalias.attr, &dev_attr_carrier.attr, &dev_attr_mtu.attr, &dev_attr_flags.attr, &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_napi_defer_hard_irqs.attr, &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, &dev_attr_threaded.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); /* Show a given an attribute in the statistics group */ static ssize_t netstat_show(const struct device *d, struct device_attribute *attr, char *buf, unsigned long offset) { struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; WARN_ON(offset > sizeof(struct rtnl_link_stats64) || offset % sizeof(u64) != 0); rcu_read_lock(); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); ret = sysfs_emit(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } rcu_read_unlock(); return ret; } /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ static ssize_t name##_show(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ offsetof(struct rtnl_link_stats64, name)); \ } \ static DEVICE_ATTR_RO(name) NETSTAT_ENTRY(rx_packets); NETSTAT_ENTRY(tx_packets); NETSTAT_ENTRY(rx_bytes); NETSTAT_ENTRY(tx_bytes); NETSTAT_ENTRY(rx_errors); NETSTAT_ENTRY(tx_errors); NETSTAT_ENTRY(rx_dropped); NETSTAT_ENTRY(tx_dropped); NETSTAT_ENTRY(multicast); NETSTAT_ENTRY(collisions); NETSTAT_ENTRY(rx_length_errors); NETSTAT_ENTRY(rx_over_errors); NETSTAT_ENTRY(rx_crc_errors); NETSTAT_ENTRY(rx_frame_errors); NETSTAT_ENTRY(rx_fifo_errors); NETSTAT_ENTRY(rx_missed_errors); NETSTAT_ENTRY(tx_aborted_errors); NETSTAT_ENTRY(tx_carrier_errors); NETSTAT_ENTRY(tx_fifo_errors); NETSTAT_ENTRY(tx_heartbeat_errors); NETSTAT_ENTRY(tx_window_errors); NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); NETSTAT_ENTRY(rx_nohandler); static struct attribute *netstat_attrs[] __ro_after_init = { &dev_attr_rx_packets.attr, &dev_attr_tx_packets.attr, &dev_attr_rx_bytes.attr, &dev_attr_tx_bytes.attr, &dev_attr_rx_errors.attr, &dev_attr_tx_errors.attr, &dev_attr_rx_dropped.attr, &dev_attr_tx_dropped.attr, &dev_attr_multicast.attr, &dev_attr_collisions.attr, &dev_attr_rx_length_errors.attr, &dev_attr_rx_over_errors.attr, &dev_attr_rx_crc_errors.attr, &dev_attr_rx_frame_errors.attr, &dev_attr_rx_fifo_errors.attr, &dev_attr_rx_missed_errors.attr, &dev_attr_tx_aborted_errors.attr, &dev_attr_tx_carrier_errors.attr, &dev_attr_tx_fifo_errors.attr, &dev_attr_tx_heartbeat_errors.attr, &dev_attr_tx_window_errors.attr, &dev_attr_rx_compressed.attr, &dev_attr_tx_compressed.attr, &dev_attr_rx_nohandler.attr, NULL }; static const struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; static struct attribute *wireless_attrs[] = { NULL }; static const struct attribute_group wireless_group = { .name = "wireless", .attrs = wireless_attrs, }; static bool wireless_group_needed(struct net_device *ndev) { #if IS_ENABLED(CONFIG_CFG80211) if (ndev->ieee80211_ptr) return true; #endif #if IS_ENABLED(CONFIG_WIRELESS_EXT) if (ndev->wireless_handlers) return true; #endif return false; } #else /* CONFIG_SYSFS */ #define net_class_groups NULL #endif /* CONFIG_SYSFS */ #ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) \ container_of(_attr, struct rx_queue_attribute, attr) #define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops rx_queue_sysfs_ops = { .show = rx_queue_attr_show, .store = rx_queue_attr_store, }; #ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) { struct rps_map *map; cpumask_var_t mask; int i, len; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rcu_read_lock(); map = rcu_dereference(queue->rps_map); if (map) for (i = 0; i < map->len; i++) cpumask_set_cpu(map->cpus[i], mask); len = sysfs_emit(buf, "%*pb\n", cpumask_pr_args(mask)); rcu_read_unlock(); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; } static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue, cpumask_var_t mask) { static DEFINE_MUTEX(rps_map_mutex); struct rps_map *old_map, *map; int cpu, i; map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) return -ENOMEM; i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) map->cpus[i++] = cpu; if (i) { map->len = i; } else { kfree(map); map = NULL; } mutex_lock(&rps_map_mutex); old_map = rcu_dereference_protected(queue->rps_map, mutex_is_locked(&rps_map_mutex)); rcu_assign_pointer(queue->rps_map, map); if (map) static_branch_inc(&rps_needed); if (old_map) static_branch_dec(&rps_needed); mutex_unlock(&rps_map_mutex); if (old_map) kfree_rcu(old_map, rcu); return 0; } int rps_cpumask_housekeeping(struct cpumask *mask) { if (!cpumask_empty(mask)) { cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); if (cpumask_empty(mask)) return -EINVAL; } return 0; } static ssize_t store_rps_map(struct netdev_rx_queue *queue, const char *buf, size_t len) { cpumask_var_t mask; int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) goto out; err = rps_cpumask_housekeeping(mask); if (err) goto out; err = netdev_rx_queue_set_rps_mask(queue, mask); out: free_cpumask_var(mask); return err ? : len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, char *buf) { struct rps_dev_flow_table *flow_table; unsigned long val = 0; rcu_read_lock(); flow_table = rcu_dereference(queue->rps_flow_table); if (flow_table) val = 1UL << flow_table->log; rcu_read_unlock(); return sysfs_emit(buf, "%lu\n", val); } static void rps_dev_flow_table_release(struct rcu_head *rcu) { struct rps_dev_flow_table *table = container_of(rcu, struct rps_dev_flow_table, rcu); vfree(table); } static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, const char *buf, size_t len) { unsigned long mask, count; struct rps_dev_flow_table *table, *old_table; static DEFINE_SPINLOCK(rps_dev_flow_lock); int rc; if (!capable(CAP_NET_ADMIN)) return -EPERM; rc = kstrtoul(buf, 0, &count); if (rc < 0) return rc; if (count) { mask = count - 1; /* mask = roundup_pow_of_two(count) - 1; * without overflows... */ while ((mask | (mask >> 1)) != mask) mask |= (mask >> 1); /* On 64 bit arches, must check mask fits in table->mask (u32), * and on 32bit arches, must check * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. */ #if BITS_PER_LONG > 32 if (mask > (unsigned long)(u32)mask) return -EINVAL; #else if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1)) / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } #endif table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1)); if (!table) return -ENOMEM; table->log = ilog2(mask) + 1; for (count = 0; count <= mask; count++) table->flows[count].cpu = RPS_NO_CPU; } else { table = NULL; } spin_lock(&rps_dev_flow_lock); old_table = rcu_dereference_protected(queue->rps_flow_table, lockdep_is_held(&rps_dev_flow_lock)); rcu_assign_pointer(queue->rps_flow_table, table); spin_unlock(&rps_dev_flow_lock); if (old_table) call_rcu(&old_table->rcu, rps_dev_flow_table_release); return len; } static struct rx_queue_attribute rps_cpus_attribute __ro_after_init = __ATTR(rps_cpus, 0644, show_rps_map, store_rps_map); static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute __ro_after_init = __ATTR(rps_flow_cnt, 0644, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); #endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] __ro_after_init = { #ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, #endif NULL }; ATTRIBUTE_GROUPS(rx_queue_default); static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); #ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); kfree_rcu(map, rcu); } flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); if (flow_table) { RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } #endif memset(kobj, 0, sizeof(*kobj)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *rx_queue_namespace(const struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; } static void rx_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = rx_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static const struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .namespace = rx_queue_namespace, .get_ownership = rx_queue_get_ownership, }; static int rx_queue_default_mask(struct net_device *dev, struct netdev_rx_queue *queue) { #if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL) struct cpumask *rps_default_mask = READ_ONCE(dev_net(dev)->core.rps_default_mask); if (rps_default_mask && !cpumask_empty(rps_default_mask)) return netdev_rx_queue_set_rps_mask(queue, rps_default_mask); #endif return 0; } static int rx_queue_add_kobject(struct net_device *dev, int index) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Rx queues are cleared in rx_queue_release to allow later * re-registration. This is triggered when their kobj refcount is * dropped. * * If a queue is removed while both a read (or write) operation and a * the re-addition of the same queue are pending (waiting on rntl_lock) * it might happen that the re-addition will execute before the read, * making the initial removal to never happen (queue's kobj refcount * won't drop enough because of the pending read). In such rare case, * return to allow the removal operation to complete. */ if (unlikely(kobj->state_initialized)) { netdev_warn_once(dev, "Cannot re-add rx queues before their removal completed"); return -EAGAIN; } /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; queue->groups = rx_queue_default_groups; error = sysfs_create_groups(kobj, queue->groups); if (error) goto err; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto err_default_groups; } error = rx_queue_default_mask(dev, queue); if (error) goto err_default_groups; kobject_uevent(kobj, KOBJ_ADD); return error; err_default_groups: sysfs_remove_groups(kobj, queue->groups); err: kobject_put(kobj); return error; } static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (dev->sysfs_rx_queue_group) error = sysfs_group_change_owner( kobj, dev->sysfs_rx_queue_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct netdev_rx_queue *queue = &dev->_rx[i]; struct kobject *kobj = &queue->kobj; if (!refcount_read(&dev_net(dev)->ns.count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); sysfs_remove_groups(kobj, queue->groups); kobject_put(kobj); } return error; #else return 0; #endif } static int net_rx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = 0; i < num; i++) { error = rx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif } #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ struct netdev_queue_attribute { struct attribute attr; ssize_t (*show)(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf); ssize_t (*store)(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len); }; #define to_netdev_queue_attr(_attr) \ container_of(_attr, struct netdev_queue_attribute, attr) #define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) static ssize_t netdev_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(kobj, attr, queue, buf); } static ssize_t netdev_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(kobj, attr, queue, buf, count); } static const struct sysfs_ops netdev_queue_sysfs_ops = { .show = netdev_queue_attr_show, .store = netdev_queue_attr_store, }; static ssize_t tx_timeout_show(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout); return sysfs_emit(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; unsigned int i; i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; } static ssize_t traffic_class_show(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; int num_tc, tc, index, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; ret = sysfs_rtnl_lock(kobj, attr, queue->dev); if (ret) return ret; index = get_netdev_queue_index(queue); /* If queue belongs to subordinate dev use its TC mapping */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); if (tc < 0) return -EINVAL; /* We can report the traffic class one of two ways: * Subordinate device traffic classes are reported with the traffic * class first, and then the subordinate class so for example TC0 on * subordinate device 2 will be reported as "0-2". If the queue * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ return num_tc < 0 ? sysfs_emit(buf, "%d%d\n", tc, num_tc) : sysfs_emit(buf, "%d\n", tc); } #ifdef CONFIG_XPS static ssize_t tx_maxrate_show(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%lu\n", queue->tx_maxrate); } static ssize_t tx_maxrate_store(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { int err, index = get_netdev_queue_index(queue); struct net_device *dev = queue->dev; u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without * hitting the locking section below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; err = kstrtou32(buf, 10, &rate); if (err < 0) return err; err = sysfs_rtnl_lock(kobj, attr, dev); if (err) return err; err = -EOPNOTSUPP; netdev_lock_ops(dev); if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); netdev_unlock_ops(dev); if (!err) { queue->tx_maxrate = rate; rtnl_unlock(); return len; } rtnl_unlock(); return err; } static struct netdev_queue_attribute queue_tx_maxrate __ro_after_init = __ATTR_RW(tx_maxrate); #endif static struct netdev_queue_attribute queue_trans_timeout __ro_after_init = __ATTR_RO(tx_timeout); static struct netdev_queue_attribute queue_traffic_class __ro_after_init = __ATTR_RO(traffic_class); #ifdef CONFIG_BQL /* * Byte queue limits sysfs structures and functions. */ static ssize_t bql_show(char *buf, unsigned int value) { return sysfs_emit(buf, "%u\n", value); } static ssize_t bql_set(const char *buf, const size_t count, unsigned int *pvalue) { unsigned int value; int err; if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) { value = DQL_MAX_LIMIT; } else { err = kstrtouint(buf, 10, &value); if (err < 0) return err; if (value > DQL_MAX_LIMIT) return -EINVAL; } *pvalue = value; return count; } static ssize_t bql_show_hold_time(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); } static ssize_t bql_set_hold_time(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; dql->slack_hold_time = msecs_to_jiffies(value); return len; } static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); static ssize_t bql_show_stall_thrs(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); } static ssize_t bql_set_stall_thrs(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; value = msecs_to_jiffies(value); if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) return -ERANGE; if (!dql->stall_thrs && value) dql->last_reap = jiffies; /* Force last_reap to be live */ smp_wmb(); dql->stall_thrs = value; return len; } static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); static ssize_t bql_show_stall_max(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); } static ssize_t bql_set_stall_max(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { WRITE_ONCE(queue->dql.stall_max, 0); return len; } static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); static ssize_t bql_show_stall_cnt(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%lu\n", dql->stall_cnt); } static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); static ssize_t bql_show_inflight(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", dql->num_queued - dql->num_completed); } static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init = __ATTR(inflight, 0444, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ static ssize_t bql_show_ ## NAME(struct kobject *kobj, \ struct attribute *attr, \ struct netdev_queue *queue, char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct kobject *kobj, \ struct attribute *attr, \ struct netdev_queue *queue, \ const char *buf, size_t len) \ { \ return bql_set(buf, len, &queue->dql.FIELD); \ } \ \ static struct netdev_queue_attribute bql_ ## NAME ## _attribute __ro_after_init \ = __ATTR(NAME, 0644, \ bql_show_ ## NAME, bql_set_ ## NAME) BQL_ATTR(limit, limit); BQL_ATTR(limit_max, max_limit); BQL_ATTR(limit_min, min_limit); static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_attribute.attr, &bql_limit_max_attribute.attr, &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, &bql_stall_thrs_attribute.attr, &bql_stall_cnt_attribute.attr, &bql_stall_max_attribute.attr, NULL }; static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; #else /* Fake declaration, all the code using it should be dead */ static const struct attribute_group dql_group = {}; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS static ssize_t xps_queue_show(struct net_device *dev, unsigned int index, int tc, char *buf, enum xps_map_type type) { struct xps_dev_maps *dev_maps; unsigned long *mask; unsigned int nr_ids; int j, len; rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps[type]); /* Default to nr_cpu_ids/dev->num_rx_queues and do not just return 0 * when dev_maps hasn't been allocated yet, to be backward compatible. */ nr_ids = dev_maps ? dev_maps->nr_ids : (type == XPS_CPUS ? nr_cpu_ids : dev->num_rx_queues); mask = bitmap_zalloc(nr_ids, GFP_NOWAIT); if (!mask) { rcu_read_unlock(); return -ENOMEM; } if (!dev_maps || tc >= dev_maps->num_tc) goto out_no_maps; for (j = 0; j < nr_ids; j++) { int i, tci = j * dev_maps->num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; for (i = map->len; i--;) { if (map->queues[i] == index) { __set_bit(j, mask); break; } } } out_no_maps: rcu_read_unlock(); len = bitmap_print_to_pagebuf(false, buf, mask, nr_ids); bitmap_free(mask); return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t xps_cpus_show(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int len, tc, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); ret = sysfs_rtnl_lock(kobj, attr, queue->dev); if (ret) return ret; /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) { rtnl_unlock(); return -EINVAL; } /* Increase the net device refcnt to make sure it won't be freed while * xps_queue_show is running. */ dev_hold(dev); rtnl_unlock(); len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); dev_put(dev); return len; } static ssize_t xps_cpus_store(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; unsigned int index; cpumask_var_t mask; int err; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) { free_cpumask_var(mask); return err; } err = sysfs_rtnl_lock(kobj, attr, dev); if (err) { free_cpumask_var(mask); return err; } err = netif_set_xps_queue(dev, mask, index); rtnl_unlock(); free_cpumask_var(mask); return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init = __ATTR_RW(xps_cpus); static ssize_t xps_rxqs_show(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int tc, ret; index = get_netdev_queue_index(queue); ret = sysfs_rtnl_lock(kobj, attr, dev); if (ret) return ret; tc = netdev_txq_to_tc(dev, index); /* Increase the net device refcnt to make sure it won't be freed while * xps_queue_show is running. */ dev_hold(dev); rtnl_unlock(); ret = tc >= 0 ? xps_queue_show(dev, index, tc, buf, XPS_RXQS) : -EINVAL; dev_put(dev); return ret; } static ssize_t xps_rxqs_store(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; struct net *net = dev_net(dev); unsigned long *mask; unsigned int index; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); if (!mask) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, mask, dev->num_rx_queues); if (err) { bitmap_free(mask); return err; } err = sysfs_rtnl_lock(kobj, attr, dev); if (err) { bitmap_free(mask); return err; } cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, XPS_RXQS); cpus_read_unlock(); rtnl_unlock(); bitmap_free(mask); return err ? : len; } static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init = __ATTR_RW(xps_rxqs); #endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { &queue_trans_timeout.attr, &queue_traffic_class.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, &xps_rxqs_attribute.attr, &queue_tx_maxrate.attr, #endif NULL }; ATTRIBUTE_GROUPS(netdev_queue_default); static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); memset(kobj, 0, sizeof(*kobj)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *netdev_queue_namespace(const struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; } static void netdev_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = netdev_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static const struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .namespace = netdev_queue_namespace, .get_ownership = netdev_queue_get_ownership, }; static bool netdev_uses_bql(const struct net_device *dev) { if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE)) return false; return IS_ENABLED(CONFIG_BQL); } static int netdev_queue_add_kobject(struct net_device *dev, int index) { struct netdev_queue *queue = dev->_tx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Tx queues are cleared in netdev_queue_release to allow later * re-registration. This is triggered when their kobj refcount is * dropped. * * If a queue is removed while both a read (or write) operation and a * the re-addition of the same queue are pending (waiting on rntl_lock) * it might happen that the re-addition will execute before the read, * making the initial removal to never happen (queue's kobj refcount * won't drop enough because of the pending read). In such rare case, * return to allow the removal operation to complete. */ if (unlikely(kobj->state_initialized)) { netdev_warn_once(dev, "Cannot re-add tx queues before their removal completed"); return -EAGAIN; } /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) goto err; queue->groups = netdev_queue_default_groups; error = sysfs_create_groups(kobj, queue->groups); if (error) goto err; if (netdev_uses_bql(dev)) { error = sysfs_create_group(kobj, &dql_group); if (error) goto err_default_groups; } kobject_uevent(kobj, KOBJ_ADD); return 0; err_default_groups: sysfs_remove_groups(kobj, queue->groups); err: kobject_put(kobj); return error; } static int tx_queue_change_owner(struct net_device *ndev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_queue *queue = ndev->_tx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (netdev_uses_bql(ndev)) error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; /* Tx queue kobjects are allowed to be updated when a device is being * unregistered, but solely to remove queues from qdiscs. Any path * adding queues should be fixed. */ WARN(dev->reg_state == NETREG_UNREGISTERING && new_num > old_num, "New queues can't be registered after device unregistration."); for (i = old_num; i < new_num; i++) { error = netdev_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; if (!refcount_read(&dev_net(dev)->ns.count)) queue->kobj.uevent_suppress = 1; if (netdev_uses_bql(dev)) sysfs_remove_group(&queue->kobj, &dql_group); sysfs_remove_groups(&queue->kobj, queue->groups); kobject_put(&queue->kobj); } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int net_tx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; for (i = 0; i < num; i++) { error = tx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS dev->queues_kset = kset_create_and_add("queues", NULL, &dev->dev.kobj); if (!dev->queues_kset) return -ENOMEM; real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; error = net_rx_queue_update_kobjects(dev, 0, real_rx); if (error) goto error; rxq = real_rx; error = netdev_queue_update_kobjects(dev, 0, real_tx); if (error) goto error; txq = real_tx; return 0; error: netdev_queue_update_kobjects(dev, txq, 0); net_rx_queue_update_kobjects(dev, rxq, 0); #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif return error; } static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) { int error = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS if (ndev->queues_kset) { error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); if (error) return error; } real_rx = ndev->real_num_rx_queues; #endif real_tx = ndev->real_num_tx_queues; error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); if (error) return error; error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); if (error) return error; return 0; } static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); netdev_lock_ops(dev); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; netdev_unlock_ops(dev); #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif } static bool net_current_may_mount(void) { struct net *net = current->nsproxy->net_ns; return ns_capable(net->user_ns, CAP_SYS_ADMIN); } static void *net_grab_current_ns(void) { struct net *ns = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS if (ns) refcount_inc(&ns->passive); #endif return ns; } static const void *net_initial_ns(void) { return &init_net; } static const void *net_netlink_ns(struct sock *sk) { return sock_net(sk); } const struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); static int netdev_uevent(const struct device *d, struct kobj_uevent_env *env) { const struct net_device *dev = to_net_dev(d); int retval; /* pass interface to uevent. */ retval = add_uevent_var(env, "INTERFACE=%s", dev->name); if (retval) goto exit; /* pass ifindex to uevent. * ifindex is useful as it won't change (interface name may change) * and is what RtNetlink uses natively. */ retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex); exit: return retval; } /* * netdev_release -- destroy and free a dead device. * Called when last reference to device kobject is gone. */ static void netdev_release(struct device *d) { struct net_device *dev = to_net_dev(d); BUG_ON(dev->reg_state != NETREG_RELEASED); /* no need to wait for rcu grace period: * device is dead and about to be freed. */ kfree(rcu_access_pointer(dev->ifalias)); kvfree(dev); } static const void *net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d); return dev_net(dev); } static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid) { const struct net_device *dev = to_net_dev(d); const struct net *net = dev_net(dev); net_ns_get_ownership(net, uid, gid); } static const struct class net_class = { .name = "net", .dev_release = netdev_release, .dev_groups = net_class_groups, .dev_uevent = netdev_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, .get_ownership = net_get_ownership, }; #ifdef CONFIG_OF static int of_dev_node_match(struct device *dev, const void *data) { for (; dev; dev = dev->parent) { if (dev->of_node == data) return 1; } return 0; } /* * of_find_net_device_by_node - lookup the net device for the device node * @np: OF device node * * Looks up the net_device structure corresponding with the device node. * If successful, returns a pointer to the net_device with the embedded * struct device refcount incremented by one, or NULL on failure. The * refcount must be dropped when done with the net_device. */ struct net_device *of_find_net_device_by_node(struct device_node *np) { struct device *dev; dev = class_find_device(&net_class, NULL, np, of_dev_node_match); if (!dev) return NULL; return to_net_dev(dev); } EXPORT_SYMBOL(of_find_net_device_by_node); #endif /* Delete sysfs entries but hold kobject reference until after all * netdev references are gone. */ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; if (!refcount_read(&dev_net(ndev)->ns.count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); remove_queue_kobjects(ndev); pm_runtime_set_memalloc_noio(dev, false); device_del(dev); } /* Create sysfs entries for network device. */ int netdev_register_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; const struct attribute_group **groups = ndev->sysfs_groups; int error = 0; device_initialize(dev); dev->class = &net_class; dev->platform_data = ndev; dev->groups = groups; dev_set_name(dev, "%s", ndev->name); #ifdef CONFIG_SYSFS /* Allow for a device specific group */ if (*groups) groups++; *groups++ = &netstat_group; if (wireless_group_needed(ndev)) *groups++ = &wireless_group; #endif /* CONFIG_SYSFS */ error = device_add(dev); if (error) return error; error = register_queue_kobjects(ndev); if (error) { device_del(dev); return error; } pm_runtime_set_memalloc_noio(dev, true); return error; } /* Change owner for sysfs entries when moving network devices across network * namespaces owned by different user namespaces. */ int netdev_change_owner(struct net_device *ndev, const struct net *net_old, const struct net *net_new) { kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID; kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID; struct device *dev = &ndev->dev; int error; net_ns_get_ownership(net_old, &old_uid, &old_gid); net_ns_get_ownership(net_new, &new_uid, &new_gid); /* The network namespace was changed but the owning user namespace is * identical so there's no need to change the owner of sysfs entries. */ if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) return 0; error = device_change_owner(dev, new_uid, new_gid); if (error) return error; error = queue_change_owner(ndev, new_uid, new_gid); if (error) return error; return 0; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { return class_create_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_create_file_ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns) { class_remove_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_remove_file_ns); int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); } |
| 482 4569 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/mempool.h> #include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ /* * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify * which does not support FS_ERROR. */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ /* #define FS_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ #define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */ #define FS_MNT_ATTACH 0x01000000 /* Mount was attached */ #define FS_MNT_DETACH 0x02000000 /* Mount was detached */ #define FS_MNT_MOVE (FS_MNT_ATTACH | FS_MNT_DETACH) /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) /* Mount namespace events */ #define FSNOTIFY_MNT_EVENTS (FS_MNT_ATTACH | FS_MNT_DETACH) /* Content events can be used to inspect file content */ #define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \ FS_ACCESS_PERM) /* Pre-content events can be used to fill file content */ #define FSNOTIFY_PRE_CONTENT_EVENTS (FS_PRE_ACCESS) #define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \ FSNOTIFY_PRE_CONTENT_EVENTS) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FSNOTIFY_MNT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; }; /* * fsnotify group priorities. * Events are sent in order from highest priority to lowest priority. */ enum fsnotify_group_prio { FSNOTIFY_PRIO_NORMAL = 0, /* normal notifiers, no permissions */ FSNOTIFY_PRIO_CONTENT, /* fanotify permission events */ FSNOTIFY_PRIO_PRE_CONTENT, /* fanotify pre-content events */ __FSNOTIFY_PRIO_NUM }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ enum fsnotify_group_prio priority; /* priority for sending events */ bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* Hash table of events for merge */ struct hlist_head *merge_hash; /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* * These helpers are used to prevent deadlock when reclaiming inodes with * evictable marks of the same group that is allocating a new mark. */ static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_FILE_RANGE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, FSNOTIFY_EVENT_MNT, FSNOTIFY_EVENT_ERROR, }; struct fs_error_report { int error; struct inode *inode; struct super_block *sb; }; struct file_range { const struct path *path; loff_t pos; size_t count; }; static inline const struct path *file_range_path(const struct file_range *range) { return range->path; } struct fsnotify_mnt { const struct mnt_namespace *ns; u64 mnt_id; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_DENTRY: return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); case FSNOTIFY_EVENT_FILE_RANGE: return d_inode(file_range_path(data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: return NULL; } } static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_DENTRY: /* Non const is needed for dget() */ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; case FSNOTIFY_EVENT_FILE_RANGE: return file_range_path(data)->dentry; default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; case FSNOTIFY_EVENT_FILE_RANGE: return file_range_path(data); default: return NULL; } } static inline struct super_block *fsnotify_data_sb(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return ((struct inode *)data)->i_sb; case FSNOTIFY_EVENT_DENTRY: return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; case FSNOTIFY_EVENT_FILE_RANGE: return file_range_path(data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: return NULL; } } static inline const struct fsnotify_mnt *fsnotify_data_mnt(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_MNT: return data; default: return NULL; } } static inline u64 fsnotify_data_mnt_id(const void *data, int data_type) { const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type); return mnt_data ? mnt_data->mnt_id : 0; } static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_ERROR: return (struct fs_error_report *) data; default: return NULL; } } static inline const struct file_range *fsnotify_data_file_range( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_FILE_RANGE: return (struct file_range *)data; default: return NULL; } } /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not * the other way around, because an event can match different watched objects * of the same object type. * For example, both parent and child are watching an object of type inode. */ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_INODE, FSNOTIFY_ITER_TYPE_VFSMOUNT, FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, FSNOTIFY_ITER_TYPE_MNTNS, FSNOTIFY_ITER_TYPE_COUNT }; /* The type of object that a mark is attached to */ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_MNTNS, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { iter_info->report_mask |= (1U << iter_type); } static inline struct fsnotify_mark *fsnotify_iter_mark( struct fsnotify_iter_info *iter_info, int iter_type) { if (fsnotify_iter_should_report_type(iter_info, iter_type)) return iter_info->marks[iter_type]; return NULL; } static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, struct fsnotify_mark **markp) { while (type < FSNOTIFY_ITER_TYPE_COUNT) { *markp = fsnotify_iter_mark(iter, type); if (*markp) break; type++; } return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) #define fsnotify_foreach_iter_mark_type(iter, mark, type) \ for (type = 0; \ type = fsnotify_iter_step(iter, type, &mark), \ type < FSNOTIFY_ITER_TYPE_COUNT; \ type++) /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned char type; /* Type of object [lock] */ unsigned char prio; /* Highest priority group */ #define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ union { /* Object pointer [lock] */ void *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; /* * Container for per-sb fsnotify state (sb marks and more). * Attached lazily on first marked object on the sb and freed when killing sb. */ struct fsnotify_sb_info { struct fsnotify_mark_connector __rcu *sb_marks; /* * Number of inode/mount/sb objects that are being watched in this sb. * Note that inodes objects are currently double-accounted. * * The value in watched_objects[prio] is the number of objects that are * watched by groups of priority >= prio, so watched_objects[0] is the * total number of watched objects in this sb. */ atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM]; }; static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb) { #ifdef CONFIG_FSNOTIFY return READ_ONCE(sb->s_fsnotify_info); #else return NULL; #endif } static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb) { return &fsnotify_sb_info(sb)->watched_objects[0]; } /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ __u32 ignore_mask; /* General fsnotify mark flags */ #define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 /* inotify mark flags */ #define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 #define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 #define FSNOTIFY_MARK_FLAG_HAS_FSID 0x0800 #define FSNOTIFY_MARK_FLAG_WEAK_FSID 0x1000 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern void __fsnotify_mntns_delete(struct mnt_namespace *mntns); extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); extern void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask); /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(parent_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return parent_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following fsnotify_set_children_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)); static inline int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *)) { return fsnotify_insert_event(group, event, merge, NULL); } /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) { return mask & FS_Q_OVERFLOW; } static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); return list_empty(&group->notification_list); } extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* * Canonical "ignore mask" including event flags. * * Note the subtle semantic difference from the legacy ->ignored_mask. * ->ignored_mask traditionally only meant which events should be ignored, * while ->ignore_mask also includes flags regarding the type of objects on * which events should be ignored. */ static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) { __u32 ignore_mask = mark->ignore_mask; /* The event flags in ignore mask take effect */ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) return ignore_mask; /* * Legacy behavior: * - Always ignore events on dir * - Ignore events on child if parent is watching children */ ignore_mask |= FS_ISDIR; ignore_mask &= ~FS_EVENT_ON_CHILD; ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; return ignore_mask; } /* Legacy ignored_mask - only event types to ignore */ static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) { return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; } /* * Check if mask (or ignore mask) should be applied depending if victim is a * directory and whether it is reported to a watching parent. */ static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, int iter_type) { /* Should mask be applied to a directory? */ if (is_dir && !(mask & FS_ISDIR)) return false; /* Should mask be applied to a child? */ if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && !(mask & FS_EVENT_ON_CHILD)) return false; return true; } /* * Effective ignore mask taking into account if event victim is a * directory and whether it is reported to a watching parent. */ static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, bool is_dir, int iter_type) { __u32 ignore_mask = fsnotify_ignored_events(mark); if (!ignore_mask) return 0; /* For non-dir and non-child, no need to consult the event flags */ if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) return ignore_mask; ignore_mask = fsnotify_ignore_mask(mark); if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) return 0; return ignore_mask & ALL_FSNOTIFY_EVENTS; } /* Get mask for calculating object interest taking ignore mask into account */ static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) { __u32 mask = mark->mask; if (!fsnotify_ignored_events(mark)) return mask; /* Interest in FS_MODIFY may be needed for clearing ignore mask */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mask |= FS_MODIFY; /* * If mark is interested in ignoring events on children, the object must * show interest in those events for fsnotify_parent() to notice it. */ return mask | mark->ignore_mask; } /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, struct fsnotify_group *group); /* attach the mark to the object */ int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline struct fsnotify_mark *fsnotify_find_inode_mark( struct inode *inode, struct fsnotify_group *group) { return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* Clear all of the marks of a group attached to a given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } int fsnotify_pre_content(const struct path *path, const loff_t *ppos, size_t count); #else static inline int fsnotify_pre_content(const struct path *path, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void __fsnotify_mntns_delete(struct mnt_namespace *mntns) {} static inline void fsnotify_sb_free(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} static inline void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_H */ |
| 52 275 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_INTERNAL_H #define __CGROUP_INTERNAL_H #include <linux/cgroup.h> #include <linux/kernfs.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/fs_parser.h> #define TRACE_CGROUP_PATH_LEN 1024 extern spinlock_t trace_cgroup_path_lock; extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; extern void __init enable_debug_cgroup(void); /* * cgroup_path() takes a spin lock. It is good practice not to take * spin locks within trace point handlers, as they are mostly hidden * from normal view. As cgroup_path() can take the kernfs_rename_lock * spin lock, it is best to not call that function from the trace event * handler. * * Note: trace_cgroup_##type##_enabled() is a static branch that will only * be set when the trace event is enabled. */ #define TRACE_CGROUP_PATH(type, cgrp, ...) \ do { \ if (trace_cgroup_##type##_enabled()) { \ unsigned long flags; \ spin_lock_irqsave(&trace_cgroup_path_lock, \ flags); \ cgroup_path(cgrp, trace_cgroup_path, \ TRACE_CGROUP_PATH_LEN); \ trace_cgroup_##type(cgrp, trace_cgroup_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_cgroup_path_lock, \ flags); \ } \ } while (0) /* * The cgroup filesystem superblock creation/mount context. */ struct cgroup_fs_context { struct kernfs_fs_context kfc; struct cgroup_root *root; struct cgroup_namespace *ns; unsigned int flags; /* CGRP_ROOT_* flags */ /* cgroup1 bits */ bool cpuset_clone_children; bool none; /* User explicitly requested empty subsystem */ bool all_ss; /* Seen 'all' option */ u16 subsys_mask; /* Selected subsystems */ char *name; /* Hierarchy name */ char *release_agent; /* Path for release notifications */ }; static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; return container_of(kfc, struct cgroup_fs_context, kfc); } struct cgroup_pidlist; struct cgroup_file_ctx { struct cgroup_namespace *ns; struct { void *trigger; } psi; struct { bool started; struct css_task_iter iter; } procs; struct { struct cgroup_pidlist *pidlist; } procs1; struct cgroup_of_peak peak; }; /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. * This M:N relationship is represented by the following link structure * which exists for each association and allows traversing the associations * from both sides. */ struct cgrp_cset_link { /* the cgroup and css_set this link associates */ struct cgroup *cgrp; struct css_set *cset; /* list of cgrp_cset_links anchored at cgrp->cset_links */ struct list_head cset_link; /* list of cgrp_cset_links anchored at css_set->cgrp_links */ struct list_head cgrp_link; }; /* used to track tasks and csets during migration */ struct cgroup_taskset { /* the src and dst cset list running through cset->mg_node */ struct list_head src_csets; struct list_head dst_csets; /* the number of tasks in the set */ int nr_tasks; /* the subsys currently being processed */ int ssid; /* * Fields for cgroup_taskset_*() iteration. * * Before migration is committed, the target migration tasks are on * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of * the csets on ->dst_csets. ->csets point to either ->src_csets * or ->dst_csets depending on whether migration is committed. * * ->cur_csets and ->cur_task point to the current task position * during iteration. */ struct list_head *csets; struct css_set *cur_cset; struct task_struct *cur_task; }; /* migration context also tracks preloading */ struct cgroup_mgctx { /* * Preloaded source and destination csets. Used to guarantee * atomic success or failure on actual migration. */ struct list_head preloaded_src_csets; struct list_head preloaded_dst_csets; /* tasks and csets to migrate */ struct cgroup_taskset tset; /* subsystems affected by migration */ u16 ss_mask; }; #define CGROUP_TASKSET_INIT(tset) \ { \ .src_csets = LIST_HEAD_INIT(tset.src_csets), \ .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ .csets = &tset.src_csets, \ } #define CGROUP_MGCTX_INIT(name) \ { \ LIST_HEAD_INIT(name.preloaded_src_csets), \ LIST_HEAD_INIT(name.preloaded_dst_csets), \ CGROUP_TASKSET_INIT(name.tset), \ } #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; extern bool cgrp_dfl_visible; /* iterate across the hierarchies */ #define for_each_root(root) \ list_for_each_entry_rcu((root), &cgroup_roots, root_list, \ lockdep_is_held(&cgroup_mutex)) /** * for_each_subsys - iterate all enabled cgroup subsystems * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end */ #define for_each_subsys(ss, ssid) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) static inline bool cgroup_is_dead(const struct cgroup *cgrp) { return !(cgrp->self.flags & CSS_ONLINE); } static inline bool notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } void put_css_set_locked(struct css_set *cset); static inline void put_css_set(struct css_set *cset) { unsigned long flags; /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an * rwlock */ if (refcount_dec_not_one(&cset->refcount)) return; spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); spin_unlock_irqrestore(&css_set_lock, flags); } /* * refcounted get/put for css_set objects */ static inline void get_css_set(struct css_set *cset) { refcount_inc(&cset->refcount); } bool cgroup_ssid_enabled(int ssid); bool cgroup_on_dfl(const struct cgroup *cgrp); struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root); struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline); void cgroup_kn_unlock(struct kernfs_node *kn); int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); void cgroup_favor_dynmods(struct cgroup_root *root, bool favor); void cgroup_free_root(struct cgroup_root *root); void init_cgroup_root(struct cgroup_fs_context *ctx); int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask); int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); int cgroup_do_get_tree(struct fs_context *fc); int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx); int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx); int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx); int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup); void cgroup_attach_lock(bool lock_threadgroup); void cgroup_attach_unlock(bool lock_threadgroup); struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *locked) __acquires(&cgroup_threadgroup_rwsem); void cgroup_procs_write_finish(struct task_struct *task, bool locked) __releases(&cgroup_threadgroup_rwsem); void cgroup_lock_and_drain_offline(struct cgroup *cgrp); int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode); int cgroup_rmdir(struct kernfs_node *kn); int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root); int __cgroup_task_count(const struct cgroup *cgrp); int cgroup_task_count(const struct cgroup *cgrp); /* * rstat.c */ int cgroup_rstat_init(struct cgroup *cgrp); void cgroup_rstat_exit(struct cgroup *cgrp); void cgroup_rstat_boot(void); void cgroup_base_stat_cputime_show(struct seq_file *seq); /* * namespace.c */ extern const struct proc_ns_operations cgroupns_operations; /* * cgroup-v1.c */ extern struct cftype cgroup1_base_files[]; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; extern const struct fs_parameter_spec cgroup1_fs_parameters[]; int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); void cgroup1_release_agent(struct work_struct *work); void cgroup1_check_for_release(struct cgroup *cgrp); int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param); int cgroup1_get_tree(struct fs_context *fc); int cgroup1_reconfigure(struct fs_context *ctx); #endif /* __CGROUP_INTERNAL_H */ |
| 8 8 8 8 8 8 167 167 167 165 167 167 8 14 7 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * VMA-specific functions. */ #include "vma_internal.h" #include "vma.h" struct mmap_state { struct mm_struct *mm; struct vma_iterator *vmi; unsigned long addr; unsigned long end; pgoff_t pgoff; unsigned long pglen; unsigned long flags; struct file *file; unsigned long charged; bool retry_merge; struct vm_area_struct *prev; struct vm_area_struct *next; /* Unmapping state. */ struct vma_munmap_struct vms; struct ma_state mas_detach; struct maple_tree mt_detach; }; #define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, flags_, file_) \ struct mmap_state name = { \ .mm = mm_, \ .vmi = vmi_, \ .addr = addr_, \ .end = (addr_) + (len_), \ .pgoff = pgoff_, \ .pglen = PHYS_PFN(len_), \ .flags = flags_, \ .file = file_, \ } #define VMG_MMAP_STATE(name, map_, vma_) \ struct vma_merge_struct name = { \ .mm = (map_)->mm, \ .vmi = (map_)->vmi, \ .start = (map_)->addr, \ .end = (map_)->end, \ .flags = (map_)->flags, \ .pgoff = (map_)->pgoff, \ .file = (map_)->file, \ .prev = (map_)->prev, \ .middle = vma_, \ .next = (vma_) ? NULL : (map_)->next, \ .state = VMA_MERGE_START, \ } static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_next) { struct vm_area_struct *vma = merge_next ? vmg->next : vmg->prev; if (!mpol_equal(vmg->policy, vma_policy(vma))) return false; /* * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ if ((vma->vm_flags ^ vmg->flags) & ~VM_SOFTDIRTY) return false; if (vma->vm_file != vmg->file) return false; if (!is_mergeable_vm_userfaultfd_ctx(vma, vmg->uffd_ctx)) return false; if (!anon_vma_name_eq(anon_vma_name(vma), vmg->anon_name)) return false; return true; } static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return true; return anon_vma1 == anon_vma2; } /* Are the anon_vma's belonging to each VMA compatible with one another? */ static inline bool are_anon_vmas_compatible(struct vm_area_struct *vma1, struct vm_area_struct *vma2) { return is_mergeable_anon_vma(vma1->anon_vma, vma2->anon_vma, NULL); } /* * init_multi_vma_prep() - Initializer for struct vma_prepare * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked * @vmg: The merge state that will be used to determine adjustment and VMA * removal. */ static void init_multi_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma, struct vma_merge_struct *vmg) { struct vm_area_struct *adjust; struct vm_area_struct **remove = &vp->remove; memset(vp, 0, sizeof(struct vma_prepare)); vp->vma = vma; vp->anon_vma = vma->anon_vma; if (vmg && vmg->__remove_middle) { *remove = vmg->middle; remove = &vp->remove2; } if (vmg && vmg->__remove_next) *remove = vmg->next; if (vmg && vmg->__adjust_middle_start) adjust = vmg->middle; else if (vmg && vmg->__adjust_next_start) adjust = vmg->next; else adjust = NULL; vp->adj_next = adjust; if (!vp->anon_vma && adjust) vp->anon_vma = adjust->anon_vma; VM_WARN_ON(vp->anon_vma && adjust && adjust->anon_vma && vp->anon_vma != adjust->anon_vma); vp->file = vma->vm_file; if (vp->file) vp->mapping = vma->vm_file->f_mapping; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. * * We assume the vma may be removed as part of the merge. */ static bool can_vma_merge_before(struct vma_merge_struct *vmg) { pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); if (is_mergeable_vma(vmg, /* merge_next = */ true) && is_mergeable_anon_vma(vmg->anon_vma, vmg->next->anon_vma, vmg->next)) { if (vmg->next->vm_pgoff == vmg->pgoff + pglen) return true; } return false; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We assume that vma is not removed as part of the merge. */ static bool can_vma_merge_after(struct vma_merge_struct *vmg) { if (is_mergeable_vma(vmg, /* merge_next = */ false) && is_mergeable_anon_vma(vmg->anon_vma, vmg->prev->anon_vma, vmg->prev)) { if (vmg->prev->vm_pgoff + vma_pages(vmg->prev) == vmg->pgoff) return true; } return false; } static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ static void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } static void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } /* * vma_prepare() - Helper function for handling locking VMAs prior to altering * @vp: The initialized vma_prepare struct */ static void vma_prepare(struct vma_prepare *vp) { if (vp->file) { uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); if (vp->adj_next) uprobe_munmap(vp->adj_next, vp->adj_next->vm_start, vp->adj_next->vm_end); i_mmap_lock_write(vp->mapping); if (vp->insert && vp->insert->vm_file) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(vp->insert, vp->insert->vm_file->f_mapping); } } if (vp->anon_vma) { anon_vma_lock_write(vp->anon_vma); anon_vma_interval_tree_pre_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_pre_update_vma(vp->adj_next); } if (vp->file) { flush_dcache_mmap_lock(vp->mapping); vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap); if (vp->adj_next) vma_interval_tree_remove(vp->adj_next, &vp->mapping->i_mmap); } } /* * vma_complete- Helper function for handling the unlocking after altering VMAs, * or for inserting a VMA. * * @vp: The vma_prepare struct * @vmi: The vma iterator * @mm: The mm_struct */ static void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi, struct mm_struct *mm) { if (vp->file) { if (vp->adj_next) vma_interval_tree_insert(vp->adj_next, &vp->mapping->i_mmap); vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap); flush_dcache_mmap_unlock(vp->mapping); } if (vp->remove && vp->file) { __remove_shared_vm_struct(vp->remove, vp->mapping); if (vp->remove2) __remove_shared_vm_struct(vp->remove2, vp->mapping); } else if (vp->insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ vma_iter_store_new(vmi, vp->insert); mm->map_count++; } if (vp->anon_vma) { anon_vma_interval_tree_post_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_post_update_vma(vp->adj_next); anon_vma_unlock_write(vp->anon_vma); } if (vp->file) { i_mmap_unlock_write(vp->mapping); uprobe_mmap(vp->vma); if (vp->adj_next) uprobe_mmap(vp->adj_next); } if (vp->remove) { again: vma_mark_detached(vp->remove); if (vp->file) { uprobe_munmap(vp->remove, vp->remove->vm_start, vp->remove->vm_end); fput(vp->file); } if (vp->remove->anon_vma) anon_vma_merge(vp->vma, vp->remove); mm->map_count--; mpol_put(vma_policy(vp->remove)); if (!vp->remove2) WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end); vm_area_free(vp->remove); /* * In mprotect's case 6 (see comments on vma_merge), * we are removing both mid and next vmas */ if (vp->remove2) { vp->remove = vp->remove2; vp->remove2 = NULL; goto again; } } if (vp->insert && vp->file) uprobe_mmap(vp->insert); } /* * init_vma_prep() - Initializer wrapper for vma_prepare struct * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked */ static void init_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma) { init_multi_vma_prep(vp, vma, NULL); } /* * Can the proposed VMA be merged with the left (previous) VMA taking into * account the start position of the proposed range. */ static bool can_vma_merge_left(struct vma_merge_struct *vmg) { return vmg->prev && vmg->prev->vm_end == vmg->start && can_vma_merge_after(vmg); } /* * Can the proposed VMA be merged with the right (next) VMA taking into * account the end position of the proposed range. * * In addition, if we can merge with the left VMA, ensure that left and right * anon_vma's are also compatible. */ static bool can_vma_merge_right(struct vma_merge_struct *vmg, bool can_merge_left) { if (!vmg->next || vmg->end != vmg->next->vm_start || !can_vma_merge_before(vmg)) return false; if (!can_merge_left) return true; /* * If we can merge with prev (left) and next (right), indicating that * each VMA's anon_vma is compatible with the proposed anon_vma, this * does not mean prev and next are compatible with EACH OTHER. * * We therefore check this in addition to mergeability to either side. */ return are_anon_vmas_compatible(vmg->prev, vmg->next); } /* * Close a vm structure and free it. */ void remove_vma(struct vm_area_struct *vma) { might_sleep(); vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); vm_area_free(vma); } /* * Get rid of page table information in the indicated region. * * Called with the mm semaphore held. */ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next) { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); unmap_vmas(&tlb, mas, vma, vma->vm_start, vma->vm_end, vma->vm_end, /* mm_wr_locked = */ true); mas_set(mas, vma->vm_end); free_pgtables(&tlb, mas, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING, /* mm_wr_locked = */ true); tlb_finish_mmu(&tlb); } /* * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. * VMA Iterator will point to the original VMA. */ static __must_check int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vma_prepare vp; struct vm_area_struct *new; int err; WARN_ON(vma->vm_start >= addr); WARN_ON(vma->vm_end <= addr); if (vma->vm_ops && vma->vm_ops->may_split) { err = vma->vm_ops->may_split(vma, addr); if (err) return err; } new = vm_area_dup(vma); if (!new) return -ENOMEM; if (new_below) { new->vm_end = addr; } else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = -ENOMEM; vma_iter_config(vmi, new->vm_start, new->vm_end); if (vma_iter_prealloc(vmi, new)) goto out_free_vma; err = vma_dup_policy(vma, new); if (err) goto out_free_vmi; err = anon_vma_clone(new, vma); if (err) goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); vma_start_write(vma); vma_start_write(new); init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); vma_adjust_trans_huge(vma, vma->vm_start, addr, NULL); if (new_below) { vma->vm_start = addr; vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT; } else { vma->vm_end = addr; } /* vma_complete stores the new vma */ vma_complete(&vp, vmi, vma->vm_mm); validate_mm(vma->vm_mm); /* Success. */ if (new_below) vma_next(vmi); else vma_prev(vmi); return 0; out_free_mpol: mpol_put(vma_policy(new)); out_free_vmi: vma_iter_free(vmi); out_free_vma: vm_area_free(new); return err; } /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (vma->vm_mm->map_count >= sysctl_max_map_count) return -ENOMEM; return __split_vma(vmi, vma, addr, new_below); } /* * dup_anon_vma() - Helper function to duplicate anon_vma * @dst: The destination VMA * @src: The source VMA * @dup: Pointer to the destination VMA when successful. * * Returns: 0 on success. */ static int dup_anon_vma(struct vm_area_struct *dst, struct vm_area_struct *src, struct vm_area_struct **dup) { /* * Easily overlooked: when mprotect shifts the boundary, make sure the * expanding vma has anon_vma set if the shrinking vma had, to cover any * anon pages imported. */ if (src->anon_vma && !dst->anon_vma) { int ret; vma_assert_write_locked(dst); dst->anon_vma = src->anon_vma; ret = anon_vma_clone(dst, src); if (ret) return ret; *dup = dst; } return 0; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mt_validate(&mm->mm_mt); for_each_vma(vmi, vma) { #ifdef CONFIG_DEBUG_VM_RB struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; #endif unsigned long vmi_start, vmi_end; bool warn = 0; vmi_start = vma_iter_addr(&vmi); vmi_end = vma_iter_end(&vmi); if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm)) warn = 1; if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm)) warn = 1; if (warn) { pr_emerg("issue in %s\n", current->comm); dump_stack(); dump_vma(vma); pr_emerg("tree range: %px start %lx end %lx\n", vma, vmi_start, vmi_end - 1); vma_iter_dump_tree(&vmi); } #ifdef CONFIG_DEBUG_VM_RB if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } #endif /* Check for a infinite loop */ if (++i > mm->map_count + 10) { i = -1; break; } } if (i != mm->map_count) { pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ /* * Based on the vmg flag indicating whether we need to adjust the vm_start field * for the middle or next VMA, we calculate what the range of the newly adjusted * VMA ought to be, and set the VMA's range accordingly. */ static void vmg_adjust_set_range(struct vma_merge_struct *vmg) { struct vm_area_struct *adjust; pgoff_t pgoff; if (vmg->__adjust_middle_start) { adjust = vmg->middle; pgoff = adjust->vm_pgoff + PHYS_PFN(vmg->end - adjust->vm_start); } else if (vmg->__adjust_next_start) { adjust = vmg->next; pgoff = adjust->vm_pgoff - PHYS_PFN(adjust->vm_start - vmg->end); } else { return; } vma_set_range(adjust, vmg->end, adjust->vm_end, pgoff); } /* * Actually perform the VMA merge operation. * * IMPORTANT: We guarantee that, should vmg->give_up_on_oom is set, to not * modify any VMAs or cause inconsistent state should an OOM condition arise. * * Returns 0 on success, or an error value on failure. */ static int commit_merge(struct vma_merge_struct *vmg) { struct vm_area_struct *vma; struct vma_prepare vp; if (vmg->__adjust_next_start) { /* We manipulate middle and adjust next, which is the target. */ vma = vmg->middle; vma_iter_config(vmg->vmi, vmg->end, vmg->next->vm_end); } else { vma = vmg->target; /* Note: vma iterator must be pointing to 'start'. */ vma_iter_config(vmg->vmi, vmg->start, vmg->end); } init_multi_vma_prep(&vp, vma, vmg); /* * If vmg->give_up_on_oom is set, we're safe, because we don't actually * manipulate any VMAs until we succeed at preallocation. * * Past this point, we will not return an error. */ if (vma_iter_prealloc(vmg->vmi, vma)) return -ENOMEM; vma_prepare(&vp); /* * THP pages may need to do additional splits if we increase * middle->vm_start. */ vma_adjust_trans_huge(vma, vmg->start, vmg->end, vmg->__adjust_middle_start ? vmg->middle : NULL); vma_set_range(vma, vmg->start, vmg->end, vmg->pgoff); vmg_adjust_set_range(vmg); vma_iter_store_overwrite(vmg->vmi, vmg->target); vma_complete(&vp, vmg->vmi, vma->vm_mm); return 0; } /* We can only remove VMAs when merging if they do not have a close hook. */ static bool can_merge_remove_vma(struct vm_area_struct *vma) { return !vma->vm_ops || !vma->vm_ops->close; } /* * vma_merge_existing_range - Attempt to merge VMAs based on a VMA having its * attributes modified. * * @vmg: Describes the modifications being made to a VMA and associated * metadata. * * When the attributes of a range within a VMA change, then it might be possible * for immediately adjacent VMAs to be merged into that VMA due to having * identical properties. * * This function checks for the existence of any such mergeable VMAs and updates * the maple tree describing the @vmg->middle->vm_mm address space to account * for this, as well as any VMAs shrunk/expanded/deleted as a result of this * merge. * * As part of this operation, if a merge occurs, the @vmg object will have its * vma, start, end, and pgoff fields modified to execute the merge. Subsequent * calls to this function should reset these fields. * * Returns: The merged VMA if merge succeeds, or NULL otherwise. * * ASSUMPTIONS: * - The caller must assign the VMA to be modifed to @vmg->middle. * - The caller must have set @vmg->prev to the previous VMA, if there is one. * - The caller must not set @vmg->next, as we determine this. * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - vmi must be positioned within [@vmg->middle->vm_start, @vmg->middle->vm_end). */ static __must_check struct vm_area_struct *vma_merge_existing_range( struct vma_merge_struct *vmg) { struct vm_area_struct *middle = vmg->middle; struct vm_area_struct *prev = vmg->prev; struct vm_area_struct *next; struct vm_area_struct *anon_dup = NULL; unsigned long start = vmg->start; unsigned long end = vmg->end; bool left_side = middle && start == middle->vm_start; bool right_side = middle && end == middle->vm_end; int err = 0; bool merge_left, merge_right, merge_both; mmap_assert_write_locked(vmg->mm); VM_WARN_ON_VMG(!middle, vmg); /* We are modifying a VMA, so caller must specify. */ VM_WARN_ON_VMG(vmg->next, vmg); /* We set this. */ VM_WARN_ON_VMG(prev && start <= prev->vm_start, vmg); VM_WARN_ON_VMG(start >= end, vmg); /* * If middle == prev, then we are offset into a VMA. Otherwise, if we are * not, we must span a portion of the VMA. */ VM_WARN_ON_VMG(middle && ((middle != prev && vmg->start != middle->vm_start) || vmg->end > middle->vm_end), vmg); /* The vmi must be positioned within vmg->middle. */ VM_WARN_ON_VMG(middle && !(vma_iter_addr(vmg->vmi) >= middle->vm_start && vma_iter_addr(vmg->vmi) < middle->vm_end), vmg); vmg->state = VMA_MERGE_NOMERGE; /* * If a special mapping or if the range being modified is neither at the * furthermost left or right side of the VMA, then we have no chance of * merging and should abort. */ if (vmg->flags & VM_SPECIAL || (!left_side && !right_side)) return NULL; if (left_side) merge_left = can_vma_merge_left(vmg); else merge_left = false; if (right_side) { next = vmg->next = vma_iter_next_range(vmg->vmi); vma_iter_prev_range(vmg->vmi); merge_right = can_vma_merge_right(vmg, merge_left); } else { merge_right = false; next = NULL; } if (merge_left) /* If merging prev, position iterator there. */ vma_prev(vmg->vmi); else if (!merge_right) /* If we have nothing to merge, abort. */ return NULL; merge_both = merge_left && merge_right; /* If we span the entire VMA, a merge implies it will be deleted. */ vmg->__remove_middle = left_side && right_side; /* * If we need to remove middle in its entirety but are unable to do so, * we have no sensible recourse but to abort the merge. */ if (vmg->__remove_middle && !can_merge_remove_vma(middle)) return NULL; /* * If we merge both VMAs, then next is also deleted. This implies * merge_will_delete_vma also. */ vmg->__remove_next = merge_both; /* * If we cannot delete next, then we can reduce the operation to merging * prev and middle (thereby deleting middle). */ if (vmg->__remove_next && !can_merge_remove_vma(next)) { vmg->__remove_next = false; merge_right = false; merge_both = false; } /* No matter what happens, we will be adjusting middle. */ vma_start_write(middle); if (merge_right) { vma_start_write(next); vmg->target = next; } if (merge_left) { vma_start_write(prev); vmg->target = prev; } if (merge_both) { /* * |<-------------------->| * |-------********-------| * prev middle next * extend delete delete */ vmg->start = prev->vm_start; vmg->end = next->vm_end; vmg->pgoff = prev->vm_pgoff; /* * We already ensured anon_vma compatibility above, so now it's * simply a case of, if prev has no anon_vma object, which of * next or middle contains the anon_vma we must duplicate. */ err = dup_anon_vma(prev, next->anon_vma ? next : middle, &anon_dup); } else if (merge_left) { /* * |<------------>| OR * |<----------------->| * |-------************* * prev middle * extend shrink/delete */ vmg->start = prev->vm_start; vmg->pgoff = prev->vm_pgoff; if (!vmg->__remove_middle) vmg->__adjust_middle_start = true; err = dup_anon_vma(prev, middle, &anon_dup); } else { /* merge_right */ /* * |<------------->| OR * |<----------------->| * *************-------| * middle next * shrink/delete extend */ pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); VM_WARN_ON_VMG(!merge_right, vmg); /* If we are offset into a VMA, then prev must be middle. */ VM_WARN_ON_VMG(vmg->start > middle->vm_start && prev && middle != prev, vmg); if (vmg->__remove_middle) { vmg->end = next->vm_end; vmg->pgoff = next->vm_pgoff - pglen; } else { /* We shrink middle and expand next. */ vmg->__adjust_next_start = true; vmg->start = middle->vm_start; vmg->end = start; vmg->pgoff = middle->vm_pgoff; } err = dup_anon_vma(next, middle, &anon_dup); } if (err) goto abort; err = commit_merge(vmg); if (err) { VM_WARN_ON(err != -ENOMEM); if (anon_dup) unlink_anon_vmas(anon_dup); /* * We've cleaned up any cloned anon_vma's, no VMAs have been * modified, no harm no foul if the user requests that we not * report this and just give up, leaving the VMAs unmerged. */ if (!vmg->give_up_on_oom) vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } khugepaged_enter_vma(vmg->target, vmg->flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->target; abort: vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); /* * This means we have failed to clone anon_vma's correctly, but no * actual changes to VMAs have occurred, so no harm no foul - if the * user doesn't want this reported and instead just wants to give up on * the merge, allow it. */ if (!vmg->give_up_on_oom) vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } /* * vma_merge_new_range - Attempt to merge a new VMA into address space * * @vmg: Describes the VMA we are adding, in the range @vmg->start to @vmg->end * (exclusive), which we try to merge with any adjacent VMAs if possible. * * We are about to add a VMA to the address space starting at @vmg->start and * ending at @vmg->end. There are three different possible scenarios: * * 1. There is a VMA with identical properties immediately adjacent to the * proposed new VMA [@vmg->start, @vmg->end) either before or after it - * EXPAND that VMA: * * Proposed: |-----| or |-----| * Existing: |----| |----| * * 2. There are VMAs with identical properties immediately adjacent to the * proposed new VMA [@vmg->start, @vmg->end) both before AND after it - * EXPAND the former and REMOVE the latter: * * Proposed: |-----| * Existing: |----| |----| * * 3. There are no VMAs immediately adjacent to the proposed new VMA or those * VMAs do not have identical attributes - NO MERGE POSSIBLE. * * In instances where we can merge, this function returns the expanded VMA which * will have its range adjusted accordingly and the underlying maple tree also * adjusted. * * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer * to the VMA we expanded. * * This function adjusts @vmg to provide @vmg->next if not already specified, * and adjusts [@vmg->start, @vmg->end) to span the expanded range. * * ASSUMPTIONS: * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - The caller must have determined that [@vmg->start, @vmg->end) is empty, other than VMAs that will be unmapped should the operation succeed. * - The caller must have specified the previous vma in @vmg->prev. * - The caller must have specified the next vma in @vmg->next. * - The caller must have positioned the vmi at or before the gap. */ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) { struct vm_area_struct *prev = vmg->prev; struct vm_area_struct *next = vmg->next; unsigned long end = vmg->end; bool can_merge_left, can_merge_right; mmap_assert_write_locked(vmg->mm); VM_WARN_ON_VMG(vmg->middle, vmg); /* vmi must point at or before the gap. */ VM_WARN_ON_VMG(vma_iter_addr(vmg->vmi) > end, vmg); vmg->state = VMA_MERGE_NOMERGE; /* Special VMAs are unmergeable, also if no prev/next. */ if ((vmg->flags & VM_SPECIAL) || (!prev && !next)) return NULL; can_merge_left = can_vma_merge_left(vmg); can_merge_right = !vmg->just_expand && can_vma_merge_right(vmg, can_merge_left); /* If we can merge with the next VMA, adjust vmg accordingly. */ if (can_merge_right) { vmg->end = next->vm_end; vmg->middle = next; } /* If we can merge with the previous VMA, adjust vmg accordingly. */ if (can_merge_left) { vmg->start = prev->vm_start; vmg->middle = prev; vmg->pgoff = prev->vm_pgoff; /* * If this merge would result in removal of the next VMA but we * are not permitted to do so, reduce the operation to merging * prev and vma. */ if (can_merge_right && !can_merge_remove_vma(next)) vmg->end = end; /* In expand-only case we are already positioned at prev. */ if (!vmg->just_expand) { /* Equivalent to going to the previous range. */ vma_prev(vmg->vmi); } } /* * Now try to expand adjacent VMA(s). This takes care of removing the * following VMA if we have VMAs on both sides. */ if (vmg->middle && !vma_expand(vmg)) { khugepaged_enter_vma(vmg->middle, vmg->flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->middle; } return NULL; } /* * vma_expand - Expand an existing VMA * * @vmg: Describes a VMA expansion operation. * * Expand @vma to vmg->start and vmg->end. Can expand off the start and end. * Will expand over vmg->next if it's different from vmg->middle and vmg->end == * vmg->next->vm_end. Checking if the vmg->middle can expand and merge with * vmg->next needs to be handled by the caller. * * Returns: 0 on success. * * ASSUMPTIONS: * - The caller must hold a WRITE lock on vmg->middle->mm->mmap_lock. * - The caller must have set @vmg->middle and @vmg->next. */ int vma_expand(struct vma_merge_struct *vmg) { struct vm_area_struct *anon_dup = NULL; bool remove_next = false; struct vm_area_struct *middle = vmg->middle; struct vm_area_struct *next = vmg->next; mmap_assert_write_locked(vmg->mm); vma_start_write(middle); if (next && (middle != next) && (vmg->end == next->vm_end)) { int ret; remove_next = true; /* This should already have been checked by this point. */ VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); vma_start_write(next); /* * In this case we don't report OOM, so vmg->give_up_on_mm is * safe. */ ret = dup_anon_vma(middle, next, &anon_dup); if (ret) return ret; } /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON_VMG(next && !remove_next && next != middle && vmg->end > next->vm_start, vmg); /* Only handles expanding */ VM_WARN_ON_VMG(middle->vm_start < vmg->start || middle->vm_end > vmg->end, vmg); vmg->target = middle; if (remove_next) vmg->__remove_next = true; if (commit_merge(vmg)) goto nomem; return 0; nomem: if (anon_dup) unlink_anon_vmas(anon_dup); /* * If the user requests that we just give upon OOM, we are safe to do so * here, as commit merge provides this contract to us. Nothing has been * changed - no harm no foul, just don't report it. */ if (!vmg->give_up_on_oom) vmg->state = VMA_MERGE_ERROR_NOMEM; return -ENOMEM; } /* * vma_shrink() - Reduce an existing VMAs memory area * @vmi: The vma iterator * @vma: The VMA to modify * @start: The new start * @end: The new end * * Returns: 0 on success, -ENOMEM otherwise */ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { struct vma_prepare vp; WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); if (vma->vm_start < start) vma_iter_config(vmi, vma->vm_start, start); else vma_iter_config(vmi, end, vma->vm_end); if (vma_iter_prealloc(vmi, NULL)) return -ENOMEM; vma_start_write(vma); init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, NULL); vma_iter_clear(vmi); vma_set_range(vma, start, end, pgoff); vma_complete(&vp, vmi, vma->vm_mm); validate_mm(vma->vm_mm); return 0; } static inline void vms_clear_ptes(struct vma_munmap_struct *vms, struct ma_state *mas_detach, bool mm_wr_locked) { struct mmu_gather tlb; if (!vms->clear_ptes) /* Nothing to do */ return; /* * We can free page tables without write-locking mmap_lock because VMAs * were isolated before we downgraded mmap_lock. */ mas_set(mas_detach, 1); tlb_gather_mmu(&tlb, vms->vma->vm_mm); update_hiwater_rss(vms->vma->vm_mm); unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end, vms->vma_count, mm_wr_locked); mas_set(mas_detach, 1); /* start and end may be different if there is no prev or next vma. */ free_pgtables(&tlb, mas_detach, vms->vma, vms->unmap_start, vms->unmap_end, mm_wr_locked); tlb_finish_mmu(&tlb); vms->clear_ptes = false; } static void vms_clean_up_area(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; if (!vms->nr_pages) return; vms_clear_ptes(vms, mas_detach, true); mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) vma_close(vma); } /* * vms_complete_munmap_vmas() - Finish the munmap() operation * @vms: The vma munmap struct * @mas_detach: The maple state of the detached vmas * * This updates the mm_struct, unmaps the region, frees the resources * used for the munmap() and may downgrade the lock - if requested. Everything * needed to be done once the vma maple tree is updated. */ static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; struct mm_struct *mm; mm = current->mm; mm->map_count -= vms->vma_count; mm->locked_vm -= vms->locked_vm; if (vms->unlock) mmap_write_downgrade(mm); if (!vms->nr_pages) return; vms_clear_ptes(vms, mas_detach, !vms->unlock); /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); /* Stat accounting */ WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm) - vms->nr_pages); /* Paranoid bookkeeping */ VM_WARN_ON(vms->exec_vm > mm->exec_vm); VM_WARN_ON(vms->stack_vm > mm->stack_vm); VM_WARN_ON(vms->data_vm > mm->data_vm); mm->exec_vm -= vms->exec_vm; mm->stack_vm -= vms->stack_vm; mm->data_vm -= vms->data_vm; /* Remove and clean up vmas */ mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) remove_vma(vma); vm_unacct_memory(vms->nr_accounted); validate_mm(mm); if (vms->unlock) mmap_read_unlock(mm); __mt_destroy(mas_detach->tree); } /* * reattach_vmas() - Undo any munmap work and free resources * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas and free up the maple tree used to track the vmas. */ static void reattach_vmas(struct ma_state *mas_detach) { struct vm_area_struct *vma; mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) vma_mark_attached(vma); __mt_destroy(mas_detach->tree); } /* * vms_gather_munmap_vmas() - Put all VMAs within a range into a maple tree * for removal at a later date. Handles splitting first and last if necessary * and marking the vmas as isolated. * * @vms: The vma munmap struct * @mas_detach: The maple state tracking the detached tree * * Return: 0 on success, error otherwise */ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *next = NULL; int error; /* * If we need to split any vma, do it now to save pain later. * Does it split the first one? */ if (vms->start > vms->vma->vm_start) { /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (vms->end < vms->vma->vm_end && vms->vma->vm_mm->map_count >= sysctl_max_map_count) { error = -ENOMEM; goto map_count_exceeded; } /* Don't bother splitting the VMA if we can't unmap it anyway */ if (!can_modify_vma(vms->vma)) { error = -EPERM; goto start_split_failed; } error = __split_vma(vms->vmi, vms->vma, vms->start, 1); if (error) goto start_split_failed; } vms->prev = vma_prev(vms->vmi); if (vms->prev) vms->unmap_start = vms->prev->vm_end; /* * Detach a range of VMAs from the mm. Using next as a temp variable as * it is always overwritten. */ for_each_vma_range(*(vms->vmi), next, vms->end) { long nrpages; if (!can_modify_vma(next)) { error = -EPERM; goto modify_vma_failed; } /* Does it split the end? */ if (next->vm_end > vms->end) { error = __split_vma(vms->vmi, next, vms->end, 0); if (error) goto end_split_failed; } vma_start_write(next); mas_set(mas_detach, vms->vma_count++); error = mas_store_gfp(mas_detach, next, GFP_KERNEL); if (error) goto munmap_gather_failed; vma_mark_detached(next); nrpages = vma_pages(next); vms->nr_pages += nrpages; if (next->vm_flags & VM_LOCKED) vms->locked_vm += nrpages; if (next->vm_flags & VM_ACCOUNT) vms->nr_accounted += nrpages; if (is_exec_mapping(next->vm_flags)) vms->exec_vm += nrpages; else if (is_stack_mapping(next->vm_flags)) vms->stack_vm += nrpages; else if (is_data_mapping(next->vm_flags)) vms->data_vm += nrpages; if (vms->uf) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain split, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first * split, despite we could. This is unlikely enough * failure that it's not worth optimizing it for. */ error = userfaultfd_unmap_prep(next, vms->start, vms->end, vms->uf); if (error) goto userfaultfd_error; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE BUG_ON(next->vm_start < vms->start); BUG_ON(next->vm_start > vms->end); #endif } vms->next = vma_next(vms->vmi); if (vms->next) vms->unmap_end = vms->next->vm_start; #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) /* Make sure no VMAs are about to be lost. */ { MA_STATE(test, mas_detach->tree, 0, 0); struct vm_area_struct *vma_mas, *vma_test; int test_count = 0; vma_iter_set(vms->vmi, vms->start); rcu_read_lock(); vma_test = mas_find(&test, vms->vma_count - 1); for_each_vma_range(*(vms->vmi), vma_mas, vms->end) { BUG_ON(vma_mas != vma_test); test_count++; vma_test = mas_next(&test, vms->vma_count - 1); } rcu_read_unlock(); BUG_ON(vms->vma_count != test_count); } #endif while (vma_iter_addr(vms->vmi) > vms->start) vma_iter_prev_range(vms->vmi); vms->clear_ptes = true; return 0; userfaultfd_error: munmap_gather_failed: end_split_failed: modify_vma_failed: reattach_vmas(mas_detach); start_split_failed: map_count_exceeded: return error; } /* * init_vma_munmap() - Initializer wrapper for vma_munmap_struct * @vms: The vma munmap struct * @vmi: The vma iterator * @vma: The first vm_area_struct to munmap * @start: The aligned start address to munmap * @end: The aligned end address to munmap * @uf: The userfaultfd list_head * @unlock: Unlock after the operation. Only unlocked on success */ static void init_vma_munmap(struct vma_munmap_struct *vms, struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { vms->vmi = vmi; vms->vma = vma; if (vma) { vms->start = start; vms->end = end; } else { vms->start = vms->end = 0; } vms->unlock = unlock; vms->uf = uf; vms->vma_count = 0; vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0; vms->exec_vm = vms->stack_vm = vms->data_vm = 0; vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; vms->clear_ptes = false; } /* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator * @vma: The starting vm_area_struct * @mm: The mm_struct * @start: The aligned start address to munmap. * @end: The aligned end address to munmap. * @uf: The userfaultfd list_head * @unlock: Set to true to drop the mmap_lock. unlocking only happens on * success. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { struct maple_tree mt_detach; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_on_stack(mt_detach); struct vma_munmap_struct vms; int error; init_vma_munmap(&vms, vmi, vma, start, end, uf, unlock); error = vms_gather_munmap_vmas(&vms, &mas_detach); if (error) goto gather_failed; error = vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL); if (error) goto clear_tree_failed; /* Point of no return */ vms_complete_munmap_vmas(&vms, &mas_detach); return 0; clear_tree_failed: reattach_vmas(&mas_detach); gather_failed: validate_mm(mm); return error; } /* * do_vmi_munmap() - munmap a given range. * @vmi: The vma iterator * @mm: The mm_struct * @start: The start address to munmap * @len: The length of the range to munmap * @uf: The userfaultfd list_head * @unlock: set to true if the user wants to drop the mmap_lock on success * * This function takes a @mas that is either pointing to the previous VMA or set * to MA_START and sets it up to remove the mapping(s). The @len will be * aligned. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock) { unsigned long end; struct vm_area_struct *vma; if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; end = start + PAGE_ALIGN(len); if (end == start) return -EINVAL; /* Find the first overlapping VMA */ vma = vma_find(vmi, end); if (!vma) { if (unlock) mmap_write_unlock(mm); return 0; } return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } /* * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd * context and anonymous VMA name within the range [start, end). * * As a result, we might be able to merge the newly modified VMA range with an * adjacent VMA with identical properties. * * If no merge is possible and the range does not span the entirety of the VMA, * we then need to split the VMA to accommodate the change. * * The function returns either the merged VMA, the original VMA if a split was * required instead, or an error if the split failed. */ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg) { struct vm_area_struct *vma = vmg->middle; unsigned long start = vmg->start; unsigned long end = vmg->end; struct vm_area_struct *merged; /* First, try to merge. */ merged = vma_merge_existing_range(vmg); if (merged) return merged; if (vmg_nomem(vmg)) return ERR_PTR(-ENOMEM); /* * Split can fail for reasons other than OOM, so if the user requests * this it's probably a mistake. */ VM_WARN_ON(vmg->give_up_on_oom && (vma->vm_start != start || vma->vm_end != end)); /* Split any preceding portion of the VMA. */ if (vma->vm_start < start) { int err = split_vma(vmg->vmi, vma, start, 1); if (err) return ERR_PTR(err); } /* Split any trailing portion of the VMA. */ if (vma->vm_end > end) { int err = split_vma(vmg->vmi, vma, end, 0); if (err) return ERR_PTR(err); } return vma; } struct vm_area_struct *vma_modify_flags( struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_flags_name(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct anon_vma_name *new_name) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; vmg.anon_name = new_name; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_policy(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct mempolicy *new_pol) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.policy = new_pol; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_flags_uffd(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct vm_userfaultfd_ctx new_ctx, bool give_up_on_oom) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; vmg.uffd_ctx = new_ctx; if (give_up_on_oom) vmg.give_up_on_oom = true; return vma_modify(&vmg); } /* * Expand vma by delta bytes, potentially merging with an immediately adjacent * VMA with identical properties. */ struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta) { VMG_VMA_STATE(vmg, vmi, vma, vma, vma->vm_end, vma->vm_end + delta); vmg.next = vma_iter_next_rewind(vmi, NULL); vmg.middle = NULL; /* We use the VMA to populate VMG fields only. */ return vma_merge_new_range(&vmg); } void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb) { vb->count = 0; } static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb) { struct address_space *mapping; int i; mapping = vb->vmas[0]->vm_file->f_mapping; i_mmap_lock_write(mapping); for (i = 0; i < vb->count; i++) { VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping); __remove_shared_vm_struct(vb->vmas[i], mapping); } i_mmap_unlock_write(mapping); unlink_file_vma_batch_init(vb); } void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, struct vm_area_struct *vma) { if (vma->vm_file == NULL) return; if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) || vb->count == ARRAY_SIZE(vb->vmas)) unlink_file_vma_batch_process(vb); vb->vmas[vb->count] = vma; vb->count++; } void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb) { if (vb->count > 0) unlink_file_vma_batch_process(vb); } /* * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, mapping); i_mmap_unlock_write(mapping); } } void vma_link_file(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct address_space *mapping; if (file) { mapping = file->f_mapping; i_mmap_lock_write(mapping); __vma_link_file(vma, mapping); i_mmap_unlock_write(mapping); } } int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) { VMA_ITERATOR(vmi, mm, 0); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; vma_start_write(vma); vma_iter_store_new(&vmi, vma); vma_link_file(vma); mm->map_count++; validate_mm(mm); return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; bool faulted_in_anon_vma = true; VMA_ITERATOR(vmi, mm, addr); VMG_VMA_STATE(vmg, &vmi, NULL, vma, addr, addr + len); /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } new_vma = find_vma_prev(mm, addr, &vmg.prev); if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ vmg.middle = NULL; /* New VMA range. */ vmg.pgoff = pgoff; vmg.next = vma_iter_next_rewind(&vmi, NULL); new_vma = vma_merge_new_range(&vmg); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; vma_set_range(new_vma, addr, addr + len, pgoff); if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); if (vma_link(mm, new_vma)) goto out_vma_link; *need_rmap_locks = false; } return new_vma; out_vma_link: vma_close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: return NULL; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mmap_lock held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mmap_lock. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = NULL; struct vm_area_struct *prev, *next; VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); /* Try next first. */ next = vma_iter_load(&vmi); if (next) { anon_vma = reusable_anon_vma(next, vma, next); if (anon_vma) return anon_vma; } prev = vma_prev(&vmi); VM_BUG_ON_VMA(prev != vma, vma); prev = vma_prev(&vmi); /* Try prev next. */ if (prev) anon_vma = reusable_anon_vma(prev, prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops) { return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite); } static bool vma_is_shared_writable(struct vm_area_struct *vma) { return (vma->vm_flags & (VM_WRITE | VM_SHARED)) == (VM_WRITE | VM_SHARED); } static bool vma_fs_can_writeback(struct vm_area_struct *vma) { /* No managed pages to writeback. */ if (vma->vm_flags & VM_PFNMAP) return false; return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * Does this VMA require the underlying folios to have their dirty state * tracked? */ bool vma_needs_dirty_tracking(struct vm_area_struct *vma) { /* Only shared, writable VMAs require dirty tracking. */ if (!vma_is_shared_writable(vma)) return false; /* Does the filesystem need to be notified? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* * Even if the filesystem doesn't indicate a need for writenotify, if it * can writeback, dirty tracking is still required. */ return vma_fs_can_writeback(vma); } /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { /* If it was private or non-writable, the write bit is already clear */ if (!vma_is_shared_writable(vma)) return false; /* The backer wishes to know when pages are first written to? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) return false; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return true; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_wp(vma)) return true; /* Can the mapping track the dirty pages? */ return vma_fs_can_writeback(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all vmas marked locked * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); mutex_lock(&mm_all_locks_mutex); /* * vma_start_write() does not have a complement in mm_drop_all_locks() * because vma_start_write() is always asymmetrical; it marks a VMA as * being written to until mmap_write_unlock() or mmap_write_downgrade() * is reached. */ for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; vma_start_write(vma); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for_each_vma(vmi, vma) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static bool accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return false; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } /* * vms_abort_munmap_vmas() - Undo as much as possible from an aborted munmap() * operation. * @vms: The vma unmap structure * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas, free up the maple tree used to track the vmas. * If that's not possible because the ptes are cleared (and vm_ops->closed() may * have been called), then a NULL is written over the vmas and the vmas are * removed (munmap() completed). */ static void vms_abort_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct ma_state *mas = &vms->vmi->mas; if (!vms->nr_pages) return; if (vms->clear_ptes) return reattach_vmas(mas_detach); /* * Aborting cannot just call the vm_ops open() because they are often * not symmetrical and state data has been lost. Resort to the old * failure method of leaving a gap where the MAP_FIXED mapping failed. */ mas_set_range(mas, vms->start, vms->end - 1); mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL); /* Clean up the insertion of the unfortunate gap */ vms_complete_munmap_vmas(vms, mas_detach); } /* * __mmap_prepare() - Prepare to gather any overlapping VMAs that need to be * unmapped once the map operation is completed, check limits, account mapping * and clean up any pre-existing VMAs. * * @map: Mapping state. * @uf: Userfaultfd context list. * * Returns: 0 on success, error code otherwise. */ static int __mmap_prepare(struct mmap_state *map, struct list_head *uf) { int error; struct vma_iterator *vmi = map->vmi; struct vma_munmap_struct *vms = &map->vms; /* Find the first overlapping VMA and initialise unmap state. */ vms->vma = vma_find(vmi, map->end); init_vma_munmap(vms, vmi, vms->vma, map->addr, map->end, uf, /* unlock = */ false); /* OK, we have overlapping VMAs - prepare to unmap them. */ if (vms->vma) { mt_init_flags(&map->mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_on_stack(map->mt_detach); mas_init(&map->mas_detach, &map->mt_detach, /* addr = */ 0); /* Prepare to unmap any existing mapping in the area */ error = vms_gather_munmap_vmas(vms, &map->mas_detach); if (error) { /* On error VMAs will already have been reattached. */ vms->nr_pages = 0; return error; } map->next = vms->next; map->prev = vms->prev; } else { map->next = vma_iter_next_rewind(vmi, &map->prev); } /* Check against address space limit. */ if (!may_expand_vm(map->mm, map->flags, map->pglen - vms->nr_pages)) return -ENOMEM; /* Private writable mapping: check memory availability. */ if (accountable_mapping(map->file, map->flags)) { map->charged = map->pglen; map->charged -= vms->nr_accounted; if (map->charged) { error = security_vm_enough_memory_mm(map->mm, map->charged); if (error) return error; } vms->nr_accounted = 0; map->flags |= VM_ACCOUNT; } /* * Clear PTEs while the vma is still in the tree so that rmap * cannot race with the freeing later in the truncate scenario. * This is also needed for mmap_file(), which is why vm_ops * close function is called. */ vms_clean_up_area(vms, &map->mas_detach); return 0; } static int __mmap_new_file_vma(struct mmap_state *map, struct vm_area_struct *vma) { struct vma_iterator *vmi = map->vmi; int error; vma->vm_file = get_file(map->file); error = mmap_file(vma->vm_file, vma); if (error) { fput(vma->vm_file); vma->vm_file = NULL; vma_iter_set(vmi, vma->vm_end); /* Undo any partial mapping done by a device driver. */ unmap_region(&vmi->mas, vma, map->prev, map->next); return error; } /* Drivers cannot alter the address of the VMA. */ WARN_ON_ONCE(map->addr != vma->vm_start); /* * Drivers should not permit writability when previously it was * disallowed. */ VM_WARN_ON_ONCE(map->flags != vma->vm_flags && !(map->flags & VM_MAYWRITE) && (vma->vm_flags & VM_MAYWRITE)); /* If the flags change (and are mergeable), let's retry later. */ map->retry_merge = vma->vm_flags != map->flags && !(vma->vm_flags & VM_SPECIAL); map->flags = vma->vm_flags; return 0; } /* * __mmap_new_vma() - Allocate a new VMA for the region, as merging was not * possible. * * @map: Mapping state. * @vmap: Output pointer for the new VMA. * * Returns: Zero on success, or an error. */ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap) { struct vma_iterator *vmi = map->vmi; int error = 0; struct vm_area_struct *vma; /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(map->mm); if (!vma) return -ENOMEM; vma_iter_config(vmi, map->addr, map->end); vma_set_range(vma, map->addr, map->end, map->pgoff); vm_flags_init(vma, map->flags); vma->vm_page_prot = vm_get_page_prot(map->flags); if (vma_iter_prealloc(vmi, vma)) { error = -ENOMEM; goto free_vma; } if (map->file) error = __mmap_new_file_vma(map, vma); else if (map->flags & VM_SHARED) error = shmem_zero_setup(vma); else vma_set_anonymous(vma); if (error) goto free_iter_vma; #ifdef CONFIG_SPARC64 /* TODO: Fix SPARC ADI! */ WARN_ON_ONCE(!arch_validate_flags(map->flags)); #endif /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); vma_iter_store_new(vmi, vma); map->mm->map_count++; vma_link_file(vma); /* * vma_merge_new_range() calls khugepaged_enter_vma() too, the below * call covers the non-merge case. */ if (!vma_is_anonymous(vma)) khugepaged_enter_vma(vma, map->flags); ksm_add_vma(vma); *vmap = vma; return 0; free_iter_vma: vma_iter_free(vmi); free_vma: vm_area_free(vma); return error; } /* * __mmap_complete() - Unmap any VMAs we overlap, account memory mapping * statistics, handle locking and finalise the VMA. * * @map: Mapping state. * @vma: Merged or newly allocated VMA for the mmap()'d region. */ static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma) { struct mm_struct *mm = map->mm; unsigned long vm_flags = vma->vm_flags; perf_event_mmap(vma); /* Unmap any existing mapping in the area. */ vms_complete_munmap_vmas(&map->vms, &map->mas_detach); vm_stat_account(mm, vma->vm_flags, map->pglen); if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(mm)) vm_flags_clear(vma, VM_LOCKED_MASK); else mm->locked_vm += map->pglen; } if (vma->vm_file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ vm_flags_set(vma, VM_SOFTDIRTY); vma_set_page_prot(vma); } static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; int error; VMA_ITERATOR(vmi, mm, addr); MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vm_flags, file); error = __mmap_prepare(&map, uf); if (error) goto abort_munmap; /* Attempt to merge with adjacent VMAs... */ if (map.prev || map.next) { VMG_MMAP_STATE(vmg, &map, /* vma = */ NULL); vma = vma_merge_new_range(&vmg); } /* ...but if we can't, allocate a new VMA. */ if (!vma) { error = __mmap_new_vma(&map, &vma); if (error) goto unacct_error; } /* If flags changed, we might be able to merge, so try again. */ if (map.retry_merge) { struct vm_area_struct *merged; VMG_MMAP_STATE(vmg, &map, vma); vma_iter_config(map.vmi, map.addr, map.end); merged = vma_merge_existing_range(&vmg); if (merged) vma = merged; } __mmap_complete(&map, vma); return addr; /* Accounting was done by __mmap_prepare(). */ unacct_error: if (map.charged) vm_unacct_memory(map.charged); abort_munmap: vms_abort_munmap_vmas(&map.vms, &map.mas_detach); return error; } /** * mmap_region() - Actually perform the userland mapping of a VMA into * current->mm with known, aligned and overflow-checked @addr and @len, and * correctly determined VMA flags @vm_flags and page offset @pgoff. * * This is an internal memory management function, and should not be used * directly. * * The caller must write-lock current->mm->mmap_lock. * * @file: If a file-backed mapping, a pointer to the struct file describing the * file to be mapped, otherwise NULL. * @addr: The page-aligned address at which to perform the mapping. * @len: The page-aligned, non-zero, length of the mapping. * @vm_flags: The VMA flags which should be applied to the mapping. * @pgoff: If @file is specified, the page offset into the file, if not then * the virtual page offset in memory of the anonymous mapping. * @uf: Optionally, a pointer to a list head used for tracking userfaultfd unmap * events. * * Returns: Either an error, or the address at which the requested mapping has * been performed. */ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { unsigned long ret; bool writable_file_mapping = false; mmap_assert_write_locked(current->mm); /* Check to see if MDWE is applicable. */ if (map_deny_write_exec(vm_flags, vm_flags)) return -EACCES; /* Allow architectures to sanity-check the vm_flags. */ if (!arch_validate_flags(vm_flags)) return -EINVAL; /* Map writable and ensure this isn't a sealed memfd. */ if (file && is_shared_maywrite(vm_flags)) { int error = mapping_map_writable(file->f_mapping); if (error) return error; writable_file_mapping = true; } ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); /* Clear our write mapping regardless of error. */ if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); validate_mm(current->mm); return ret; } /* * do_brk_flags() - Increase the brk vma if the flags match. * @vmi: The vma iterator * @addr: The start address * @len: The length of the increase * @vma: The vma, * @flags: The VMA Flags * * Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags * do not match then create a new anonymous VMA. Eventually we may be able to * do some brk-specific accounting here. */ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, unsigned long len, unsigned long flags) { struct mm_struct *mm = current->mm; /* * Check against address space limits by the changed size * Note: This happens *after* clearing old mappings in some code paths. */ flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* * Expand the existing vma if possible; Note that singular lists do not * occur after forking, so the expand will only happen on new VMAs. */ if (vma && vma->vm_end == addr) { VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr)); vmg.prev = vma; /* vmi is positioned at prev, which this mode expects. */ vmg.just_expand = true; if (vma_merge_new_range(&vmg)) goto out; else if (vmg_nomem(&vmg)) goto unacct_fail; } if (vma) vma_iter_next_range(vmi); /* create a vma struct for an anonymous mapping */ vma = vm_area_alloc(mm); if (!vma) goto unacct_fail; vma_set_anonymous(vma); vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT); vm_flags_init(vma, flags); vma->vm_page_prot = vm_get_page_prot(flags); vma_start_write(vma); if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL)) goto mas_store_fail; mm->map_count++; validate_mm(mm); ksm_add_vma(vma); out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vm_flags_set(vma, VM_SOFTDIRTY); return 0; mas_store_fail: vm_area_free(vma); unacct_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } /** * unmapped_area() - Find an area between the low_limit and the high_limit with * the correct alignment and offset, all from @info. Note: current->mm is used * for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ unsigned long unmapped_area(struct vm_unmapped_area_info *info) { unsigned long length, gap; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length)) return -ENOMEM; /* * Adjust for the gap first so it doesn't interfere with the * later alignment. The first step is the minimum needed to * fulill the start gap, the next steps is the minimum to align * that. It is the minimum needed to fulill both. */ gap = vma_iter_addr(&vmi) + info->start_gap; gap += (info->align_offset - gap) & info->align_mask; tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap + length - 1) { low_limit = tmp->vm_end; vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { low_limit = vm_end_gap(tmp); vma_iter_reset(&vmi); goto retry; } } return gap; } /** * unmapped_area_topdown() - Find an area between the low_limit and the * high_limit with the correct alignment and offset at the highest available * address, all from @info. Note: current->mm is used for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { unsigned long length, gap, gap_end; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_highest(&vmi, low_limit, high_limit, length)) return -ENOMEM; gap = vma_iter_end(&vmi) - info->length; gap -= (gap - info->align_offset) & info->align_mask; gap_end = vma_iter_end(&vmi); tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap_end) { high_limit = vm_start_gap(tmp); vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { high_limit = tmp->vm_start; vma_iter_reset(&vmi); goto retry; } } return gap; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ if (size > rlimit(RLIMIT_STACK)) return -ENOMEM; /* mlock limit tests */ if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT)) return -ENOMEM; /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : vma->vm_end - size; if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; /* * Overcommit.. This must be the final test, as it will * update security statistics. */ if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; return 0; } #if defined(CONFIG_STACK_GROWSUP) /* * PA-RISC uses this for its stack. * vma is the last one with address > vma->vm_end. Have to extend vma. */ int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; unsigned long gap_addr; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; mmap_assert_write_locked(mm); /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; /* Guard against overflow */ if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE; next = find_vma_intersection(mm, vma->vm_end, gap_addr); if (next && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } if (next) vma_iter_prev_range_limit(&vmi, address); vma_iter_config(&vmi, vma->vm_start, address); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* We update the anon VMA tree. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; /* Overwrite old entry in mtree. */ vma_iter_store_overwrite(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } #endif /* CONFIG_STACK_GROWSUP */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. * mmap_lock held for writing. */ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *prev; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSDOWN)) return -EFAULT; mmap_assert_write_locked(mm); address &= PAGE_MASK; if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) return -EPERM; /* Enforce stack_guard_gap */ prev = vma_prev(&vmi); /* Check that both stack segments have the same anon_vma? */ if (prev) { if (!(prev->vm_flags & VM_GROWSDOWN) && vma_is_accessible(prev) && (address - prev->vm_end < stack_guard_gap)) return -ENOMEM; } if (prev) vma_iter_next_range_limit(&vmi, vma->vm_start); vma_iter_config(&vmi, address, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* We update the anon VMA tree. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; /* Overwrite old entry in mtree. */ vma_iter_store_overwrite(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } int __vm_munmap(unsigned long start, size_t len, bool unlock) { int ret; struct mm_struct *mm = current->mm; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, start); if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock); if (ret || !unlock) mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); return ret; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | #ifndef LLC_C_EV_H #define LLC_C_EV_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <net/sock.h> /* Connection component state transition event qualifiers */ /* Types of events (possible values in 'ev->type') */ #define LLC_CONN_EV_TYPE_SIMPLE 1 #define LLC_CONN_EV_TYPE_CONDITION 2 #define LLC_CONN_EV_TYPE_PRIM 3 #define LLC_CONN_EV_TYPE_PDU 4 /* command/response PDU */ #define LLC_CONN_EV_TYPE_ACK_TMR 5 #define LLC_CONN_EV_TYPE_P_TMR 6 #define LLC_CONN_EV_TYPE_REJ_TMR 7 #define LLC_CONN_EV_TYPE_BUSY_TMR 8 #define LLC_CONN_EV_TYPE_RPT_STATUS 9 #define LLC_CONN_EV_TYPE_SENDACK_TMR 10 #define NBR_CONN_EV 5 /* Connection events which cause state transitions when fully qualified */ #define LLC_CONN_EV_CONN_REQ 1 #define LLC_CONN_EV_CONN_RESP 2 #define LLC_CONN_EV_DATA_REQ 3 #define LLC_CONN_EV_DISC_REQ 4 #define LLC_CONN_EV_RESET_REQ 5 #define LLC_CONN_EV_RESET_RESP 6 #define LLC_CONN_EV_LOCAL_BUSY_DETECTED 7 #define LLC_CONN_EV_LOCAL_BUSY_CLEARED 8 #define LLC_CONN_EV_RX_BAD_PDU 9 #define LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X 10 #define LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X 11 #define LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X 12 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X 13 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_UNEXPD_Ns 14 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_INVAL_Ns 15 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X 16 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_UNEXPD_Ns 17 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_INVAL_Ns 18 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_X 19 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X 20 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_X 21 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_X 22 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_X 23 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_X 24 #define LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X 25 #define LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X 26 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_X 27 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_X 28 #define LLC_CONN_EV_RX_XXX_YYY 29 #define LLC_CONN_EV_RX_ZZZ_CMD_Pbit_SET_X_INVAL_Nr 30 #define LLC_CONN_EV_RX_ZZZ_RSP_Fbit_SET_X_INVAL_Nr 31 #define LLC_CONN_EV_P_TMR_EXP 32 #define LLC_CONN_EV_ACK_TMR_EXP 33 #define LLC_CONN_EV_REJ_TMR_EXP 34 #define LLC_CONN_EV_BUSY_TMR_EXP 35 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_1 36 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_0 37 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns 38 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns 39 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns 40 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns 41 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 42 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 43 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 44 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 45 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 46 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 47 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 48 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 49 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 50 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 51 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 52 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 53 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 54 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 55 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 56 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 57 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_1 58 #define LLC_CONN_EV_TX_BUFF_FULL 59 #define LLC_CONN_EV_INIT_P_F_CYCLE 100 /* * Connection event qualifiers; for some events a certain combination of * these qualifiers must be TRUE before event recognized valid for state; * these constants act as indexes into the Event Qualifier function * table */ #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_1 1 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_0 2 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_2 3 #define LLC_CONN_EV_QFY_P_FLAG_EQ_1 4 #define LLC_CONN_EV_QFY_P_FLAG_EQ_0 5 #define LLC_CONN_EV_QFY_P_FLAG_EQ_Fbit 6 #define LLC_CONN_EV_QFY_REMOTE_BUSY_EQ_0 7 #define LLC_CONN_EV_QFY_RETRY_CNT_LT_N2 8 #define LLC_CONN_EV_QFY_RETRY_CNT_GTE_N2 9 #define LLC_CONN_EV_QFY_S_FLAG_EQ_1 10 #define LLC_CONN_EV_QFY_S_FLAG_EQ_0 11 #define LLC_CONN_EV_QFY_INIT_P_F_CYCLE 12 struct llc_conn_state_ev { u8 type; u8 prim; u8 prim_type; u8 reason; u8 status; u8 ind_prim; u8 cfm_prim; }; static __inline__ struct llc_conn_state_ev *llc_conn_ev(struct sk_buff *skb) { return (struct llc_conn_state_ev *)skb->cb; } typedef int (*llc_conn_ev_t)(struct sock *sk, struct sk_buff *skb); typedef int (*llc_conn_ev_qfyr_t)(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_conn_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_data_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_disc_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rst_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_detected(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_cleared(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_bad_pdu(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_disc_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_dm_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_frmr_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_sabme_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_ua_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb); /* NOT_USED functions and their variations */ int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_any_frame(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_tx_buffer_full(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_init_p_f_cycle(struct sock *sk, struct sk_buff *skb); /* Available connection action qualifiers */ int llc_conn_ev_qlfy_data_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_f(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_lt_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_gte_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conn(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_disc(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_failed(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_remote_busy(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_refuse(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conflict(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_rst_done(struct sock *sk, struct sk_buff *skb); static __inline__ int llc_conn_space(struct sock *sk, struct sk_buff *skb) { return atomic_read(&sk->sk_rmem_alloc) + skb->truesize < (unsigned int)sk->sk_rcvbuf; } #endif /* LLC_C_EV_H */ |
| 223 222 224 223 86 161 222 224 223 224 224 224 149 104 10 19 224 224 223 294 224 5 69 70 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs * * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes * 2000-2002 x86-64 support by Andi Kleen */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> #include <linux/kstrtox.h> #include <linux/errno.h> #include <linux/wait.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/personality.h> #include <linux/uaccess.h> #include <linux/user-return-notifier.h> #include <linux/uprobes.h> #include <linux/context_tracking.h> #include <linux/entry-common.h> #include <linux/syscalls.h> #include <linux/rseq.h> #include <asm/processor.h> #include <asm/ucontext.h> #include <asm/fpu/signal.h> #include <asm/fpu/xstate.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> #include <asm/vm86.h> #include <asm/syscall.h> #include <asm/sigframe.h> #include <asm/signal.h> #include <asm/shstk.h> static inline int is_ia32_compat_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_IA32_EMULATION) && ksig->ka.sa.sa_flags & SA_IA32_ABI; } static inline int is_ia32_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); } static inline int is_x32_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_X86_X32_ABI) && ksig->ka.sa.sa_flags & SA_X32_ABI; } /* * Enable all pkeys temporarily, so as to ensure that both the current * execution stack as well as the alternate signal stack are writeable. * The application can use any of the available pkeys to protect the * alternate signal stack, and we don't know which one it is, so enable * all. The PKRU register will be reset to init_pkru later in the flow, * in fpu__clear_user_states(), and it is the application's responsibility * to enable the appropriate pkey as the first step in the signal handler * so that the handler does not segfault. */ static inline u32 sig_prepare_pkru(void) { u32 orig_pkru = read_pkru(); write_pkru(0); return orig_pkru; } /* * Set up a signal frame. */ /* x86 ABI requires 16-byte alignment */ #define FRAME_ALIGNMENT 16UL #define MAX_FRAME_PADDING (FRAME_ALIGNMENT - 1) /* * Determine which stack to use.. */ void __user * get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { struct k_sigaction *ka = &ksig->ka; int ia32_frame = is_ia32_frame(ksig); /* Default to using normal stack */ bool nested_altstack = on_sig_stack(regs->sp); bool entering_altstack = false; unsigned long math_size = 0; unsigned long sp = regs->sp; unsigned long buf_fx = 0; u32 pkru; /* redzone */ if (!ia32_frame) sp -= 128; /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { /* * This checks nested_altstack via sas_ss_flags(). Sensible * programs use SS_AUTODISARM, which disables that check, and * programs that don't use SS_AUTODISARM get compatible. */ if (sas_ss_flags(sp) == 0) { sp = current->sas_ss_sp + current->sas_ss_size; entering_altstack = true; } } else if (ia32_frame && !nested_altstack && regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && ka->sa.sa_restorer) { /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; entering_altstack = true; } sp = fpu__alloc_mathframe(sp, ia32_frame, &buf_fx, &math_size); *fpstate = (void __user *)sp; sp -= frame_size; if (ia32_frame) /* * Align the stack pointer according to the i386 ABI, * i.e. so that on function entry ((sp + 4) & 15) == 0. */ sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; else sp = round_down(sp, FRAME_ALIGNMENT) - 8; /* * If we are on the alternate signal stack and would overflow it, don't. * Return an always-bogus address instead so we will die with SIGSEGV. */ if (unlikely((nested_altstack || entering_altstack) && !__on_sig_stack(sp))) { if (show_unhandled_signals && printk_ratelimit()) pr_info("%s[%d] overflowed sigaltstack\n", current->comm, task_pid_nr(current)); return (void __user *)-1L; } /* Update PKRU to enable access to the alternate signal stack. */ pkru = sig_prepare_pkru(); /* save i387 and extended state */ if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru)) { /* * Restore PKRU to the original, user-defined value; disable * extra pkeys enabled for the alternate signal stack, if any. */ write_pkru(pkru); return (void __user *)-1L; } return (void __user *)sp; } /* * There are four different struct types for signal frame: sigframe_ia32, * rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case * -- the largest size. It means the size for 64-bit apps is a bit more * than needed, but this keeps the code simple. */ #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) # define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct sigframe_ia32) #else # define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct rt_sigframe) #endif /* * The FP state frame contains an XSAVE buffer which must be 64-byte aligned. * If a signal frame starts at an unaligned address, extra space is required. * This is the max alignment padding, conservatively. */ #define MAX_XSAVE_PADDING 63UL /* * The frame data is composed of the following areas and laid out as: * * ------------------------- * | alignment padding | * ------------------------- * | (f)xsave frame | * ------------------------- * | fsave header | * ------------------------- * | alignment padding | * ------------------------- * | siginfo + ucontext | * ------------------------- */ /* max_frame_size tells userspace the worst case signal stack size. */ static unsigned long __ro_after_init max_frame_size; static unsigned int __ro_after_init fpu_default_state_size; static int __init init_sigframe_size(void) { fpu_default_state_size = fpu__get_fpstate_size(); max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING; max_frame_size += fpu_default_state_size + MAX_XSAVE_PADDING; /* Userspace expects an aligned size. */ max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); pr_info("max sigframe size: %lu\n", max_frame_size); return 0; } early_initcall(init_sigframe_size); unsigned long get_sigframe_size(void) { return max_frame_size; } static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { /* Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) return ia32_setup_rt_frame(ksig, regs); else return ia32_setup_frame(ksig, regs); } else if (is_x32_frame(ksig)) { return x32_setup_rt_frame(ksig, regs); } else { return x64_setup_rt_frame(ksig, regs); } } static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { bool stepping, failed; struct fpu *fpu = ¤t->thread.fpu; if (v8086_mode(regs)) save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL); /* Are we from a system call? */ if (syscall_get_nr(current, regs) != -1) { /* If so, check system call restarting.. */ switch (syscall_get_error(current, regs)) { case -ERESTART_RESTARTBLOCK: case -ERESTARTNOHAND: regs->ax = -EINTR; break; case -ERESTARTSYS: if (!(ksig->ka.sa.sa_flags & SA_RESTART)) { regs->ax = -EINTR; break; } fallthrough; case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; break; } } /* * If TF is set due to a debugger (TIF_FORCED_TF), clear TF now * so that register information in the sigcontext is correct and * then notify the tracer before entering the signal handler. */ stepping = test_thread_flag(TIF_SINGLESTEP); if (stepping) user_disable_single_step(current); failed = (setup_rt_frame(ksig, regs) < 0); if (!failed) { /* * Clear the direction flag as per the ABI for function entry. * * Clear RF when entering the signal handler, because * it might disable possible debug exception from the * signal handler. * * Clear TF for the case when it wasn't set by debugger to * avoid the recursive send_sigtrap() in SIGTRAP handler. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); /* * Ensure the signal handler starts with the new fpu state. */ fpu__clear_user_states(fpu); } signal_setup_done(failed, ksig, stepping); } static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { #ifdef CONFIG_IA32_EMULATION if (current->restart_block.arch_data & TS_COMPAT) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); #else return __NR_restart_syscall; #endif } /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ void arch_do_signal_or_restart(struct pt_regs *regs) { struct ksignal ksig; if (get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; } /* Did we come from a system call? */ if (syscall_get_nr(current, regs) != -1) { /* Restart the system call - no handlers present */ switch (syscall_get_error(current, regs)) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; break; case -ERESTART_RESTARTBLOCK: regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } } /* * If there's no signal to deliver, we just put the saved sigmask * back. */ restore_saved_sigmask(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) { struct task_struct *me = current; if (show_unhandled_signals && printk_ratelimit()) { printk("%s" "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx", task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } force_sig(SIGSEGV); } #ifdef CONFIG_DYNAMIC_SIGFRAME #ifdef CONFIG_STRICT_SIGALTSTACK_SIZE static bool strict_sigaltstack_size __ro_after_init = true; #else static bool strict_sigaltstack_size __ro_after_init = false; #endif static int __init strict_sas_size(char *arg) { return kstrtobool(arg, &strict_sigaltstack_size) == 0; } __setup("strict_sas_size", strict_sas_size); /* * MINSIGSTKSZ is 2048 and can't be changed despite the fact that AVX512 * exceeds that size already. As such programs might never use the * sigaltstack they just continued to work. While always checking against * the real size would be correct, this might be considered a regression. * * Therefore avoid the sanity check, unless enforced by kernel * configuration or command line option. * * When dynamic FPU features are supported, the check is also enforced when * the task has permissions to use dynamic features. Tasks which have no * permission are checked against the size of the non-dynamic feature set * if strict checking is enabled. This avoids forcing all tasks on the * system to allocate large sigaltstacks even if they are never going * to use a dynamic feature. As this is serialized via sighand::siglock * any permission request for a dynamic feature either happened already * or will see the newly install sigaltstack size in the permission checks. */ bool sigaltstack_size_valid(size_t ss_size) { unsigned long fsize = max_frame_size - fpu_default_state_size; u64 mask; lockdep_assert_held(¤t->sighand->siglock); if (!fpu_state_size_dynamic() && !strict_sigaltstack_size) return true; fsize += current->group_leader->thread.fpu.perm.__user_state_size; if (likely(ss_size > fsize)) return true; if (strict_sigaltstack_size) return ss_size > fsize; mask = current->group_leader->thread.fpu.perm.__state_perm; if (mask & XFEATURE_MASK_USER_DYNAMIC) return ss_size > fsize; return true; } #endif /* CONFIG_DYNAMIC_SIGFRAME */ |
| 3 3 11 1009 1004 10 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #include <linux/skb_array.h> struct macvtap_dev { struct macvlan_dev vlan; struct tap_dev tap; }; /* * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; static const void *macvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class macvtap_class = { .name = "macvtap", .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; static struct cdev macvtap_cdev; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static void macvtap_count_tx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_dropped); } static void macvtap_count_rx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; macvlan_count_rx(vlan, 0, 0, 0); } static void macvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; vlan->set_features = features; netdev_update_features(vlan->dev); } static int macvtap_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; /* Register callbacks for rx/tx drops accounting and updating * net_device features */ vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped; vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped; vlantap->tap.update_features = macvtap_update_features; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = macvlan_common_newlink(dev, params, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return 0; } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { struct macvtap_dev *vlantap = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlantap->tap); macvlan_dellink(dev, head); } static void macvtap_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; } static struct net *macvtap_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, .get_link_net = macvtap_link_net, .priv_size = sizeof(struct macvtap_dev), }; static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &macvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(macvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); device_destroy(&macvtap_class, devt); tap_free_minor(macvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block macvtap_notifier_block __read_mostly = { .notifier_call = macvtap_device_event, }; static int __init macvtap_init(void) { int err; err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", THIS_MODULE); if (err) goto out1; err = class_register(&macvtap_class); if (err) goto out2; err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out3; err = macvlan_link_register(&macvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&macvtap_notifier_block); out3: class_unregister(&macvtap_class); out2: tap_destroy_cdev(macvtap_major, &macvtap_cdev); out1: return err; } module_init(macvtap_init); static void __exit macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(&macvtap_class); tap_destroy_cdev(macvtap_major, &macvtap_cdev); } module_exit(macvtap_exit); MODULE_ALIAS_RTNL_LINK("macvtap"); MODULE_DESCRIPTION("MAC-VLAN based tap driver"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); |
| 28 28 28 28 28 28 28 28 28 28 10 27 28 28 28 42 42 42 42 42 42 42 42 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH * Copyright 2018-2020, 2022-2024 Intel Corporation */ #include <crypto/utils.h> #include <linux/if_ether.h> #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/export.h> #include <net/mac80211.h> #include <linux/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "debugfs_key.h" #include "aes_ccm.h" #include "aes_cmac.h" #include "aes_gmac.h" #include "aes_gcm.h" /** * DOC: Key handling basics * * Key handling in mac80211 is done based on per-interface (sub_if_data) * keys and per-station keys. Since each station belongs to an interface, * each station key also belongs to that interface. * * Hardware acceleration is done on a best-effort basis for algorithms * that are implemented in software, for each key the hardware is asked * to enable that key for offloading but if it cannot do that the key is * simply kept for software encryption (unless it is for an algorithm * that isn't implemented in software). * There is currently no way of knowing whether a key is handled in SW * or HW except by looking into debugfs. * * All key management is internally protected by a mutex. Within all * other parts of mac80211, key references are, just as STA structure * references, protected by RCU. Note, however, that some things are * unprotected, namely the key->sta dereferences within the hardware * acceleration functions. This means that sta_info_destroy() must * remove the key which waits for an RCU grace period. */ static const u8 bcast_addr[ETH_ALEN] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; static void update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta) { struct ieee80211_sub_if_data *vlan; if (sdata->vif.type != NL80211_IFTYPE_AP) return; /* crypto_tx_tailroom_needed_cnt is protected by this */ lockdep_assert_wiphy(sdata->local->hw.wiphy); rcu_read_lock(); list_for_each_entry_rcu(vlan, &sdata->u.ap.vlans, u.vlan.list) vlan->crypto_tx_tailroom_needed_cnt += delta; rcu_read_unlock(); } static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) { /* * When this count is zero, SKB resizing for allocating tailroom * for IV or MMIC is skipped. But, this check has created two race * cases in xmit path while transiting from zero count to one: * * 1. SKB resize was skipped because no key was added but just before * the xmit key is added and SW encryption kicks off. * * 2. SKB resize was skipped because all the keys were hw planted but * just before xmit one of the key is deleted and SW encryption kicks * off. * * In both the above case SW encryption will find not enough space for * tailroom and exits with WARN_ON. (See WARN_ONs at wpa.c) * * Solution has been explained at * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net */ lockdep_assert_wiphy(sdata->local->hw.wiphy); update_vlan_tailroom_need_count(sdata, 1); if (!sdata->crypto_tx_tailroom_needed_cnt++) { /* * Flush all XMIT packets currently using HW encryption or no * encryption at all if the count transition is from 0 -> 1. */ synchronize_net(); } } static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta) { lockdep_assert_wiphy(sdata->local->hw.wiphy); WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta); update_vlan_tailroom_need_count(sdata, -delta); sdata->crypto_tx_tailroom_needed_cnt -= delta; } static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata = key->sdata; struct sta_info *sta; int ret = -EOPNOTSUPP; might_sleep(); lockdep_assert_wiphy(key->local->hw.wiphy); if (key->flags & KEY_FLAG_TAINTED) { /* If we get here, it's during resume and the key is * tainted so shouldn't be used/programmed any more. * However, its flags may still indicate that it was * programmed into the device (since we're in resume) * so clear that flag now to avoid trying to remove * it again later. */ if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(sdata); key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; return -EINVAL; } if (!key->local->ops->set_key) goto out_unsupported; sta = key->sta; /* * If this is a per-STA GTK, check if it * is supported; if not, return. */ if (sta && !(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE) && !ieee80211_hw_check(&key->local->hw, SUPPORTS_PER_STA_GTK)) goto out_unsupported; if (sta && !sta->uploaded) goto out_unsupported; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* * The driver doesn't know anything about VLAN interfaces. * Hence, don't send GTKs for VLAN interfaces to the driver. */ if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) { ret = 1; goto out_unsupported; } } if (key->conf.link_id >= 0 && sdata->vif.active_links && !(sdata->vif.active_links & BIT(key->conf.link_id))) return 0; ret = drv_set_key(key->local, SET_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); if (!ret) { key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; if (!(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) decrease_tailroom_need_count(sdata, 1); WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)); WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_MIC_SPACE) && (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)); return 0; } if (ret != -ENOSPC && ret != -EOPNOTSUPP && ret != 1) sdata_err(sdata, "failed to set key (%d, %pM) to hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); out_unsupported: switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: /* all of these we can do in software - if driver can */ if (ret == 1) return 0; if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) return -EINVAL; return 0; default: return -EINVAL; } } static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata; struct sta_info *sta; int ret; might_sleep(); if (!key || !key->local->ops->set_key) return; if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) return; sta = key->sta; sdata = key->sdata; lockdep_assert_wiphy(key->local->hw.wiphy); if (key->conf.link_id >= 0 && sdata->vif.active_links && !(sdata->vif.active_links & BIT(key->conf.link_id))) return; if (!(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(sdata); key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; ret = drv_set_key(key->local, DISABLE_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); if (ret) sdata_err(sdata, "failed to remove key (%d, %pM) from hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); } static int _ieee80211_set_tx_key(struct ieee80211_key *key, bool force) { struct sta_info *sta = key->sta; struct ieee80211_local *local = key->local; lockdep_assert_wiphy(local->hw.wiphy); set_sta_flag(sta, WLAN_STA_USES_ENCRYPTION); sta->ptk_idx = key->conf.keyidx; if (force || !ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) clear_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_check_fast_xmit(sta); return 0; } int ieee80211_set_tx_key(struct ieee80211_key *key) { return _ieee80211_set_tx_key(key, false); } static void ieee80211_pairwise_rekey(struct ieee80211_key *old, struct ieee80211_key *new) { struct ieee80211_local *local = new->local; struct sta_info *sta = new->sta; int i; lockdep_assert_wiphy(local->hw.wiphy); if (new->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX) { /* Extended Key ID key install, initial one or rekey */ if (sta->ptk_idx != INVALID_PTK_KEYIDX && !ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) { /* Aggregation Sessions with Extended Key ID must not * mix MPDUs with different keyIDs within one A-MPDU. * Tear down running Tx aggregation sessions and block * new Rx/Tx aggregation requests during rekey to * ensure there are no A-MPDUs when the driver is not * supporting A-MPDU key borders. (Blocking Tx only * would be sufficient but WLAN_STA_BLOCK_BA gets the * job done for the few ms we need it.) */ set_sta_flag(sta, WLAN_STA_BLOCK_BA); for (i = 0; i < IEEE80211_NUM_TIDS; i++) __ieee80211_stop_tx_ba_session(sta, i, AGG_STOP_LOCAL_REQUEST); } } else if (old) { /* Rekey without Extended Key ID. * Aggregation sessions are OK when running on SW crypto. * A broken remote STA may cause issues not observed with HW * crypto, though. */ if (!(old->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) return; /* Stop Tx till we are on the new key */ old->flags |= KEY_FLAG_TAINTED; ieee80211_clear_fast_xmit(sta); if (ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION)) { set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_LOCAL_REQUEST); } if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0)) { pr_warn_ratelimited("Rekeying PTK for STA %pM but driver can't safely do that.", sta->sta.addr); /* Flushing the driver queues *may* help prevent * the clear text leaks and freezes. */ ieee80211_flush_queues(local, old->sdata, false); } } } static void __ieee80211_set_default_key(struct ieee80211_link_data *link, int idx, bool uni, bool multi) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_key *key = NULL; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (idx >= 0 && idx < NUM_DEFAULT_KEYS) { key = wiphy_dereference(sdata->local->hw.wiphy, sdata->keys[idx]); if (!key) key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); } if (uni) { rcu_assign_pointer(sdata->default_unicast_key, key); ieee80211_check_fast_xmit_iface(sdata); if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN) drv_set_default_unicast_key(sdata->local, sdata, idx); } if (multi) rcu_assign_pointer(link->default_multicast_key, key); ieee80211_debugfs_key_update_default(sdata); } void ieee80211_set_default_key(struct ieee80211_link_data *link, int idx, bool uni, bool multi) { lockdep_assert_wiphy(link->sdata->local->hw.wiphy); __ieee80211_set_default_key(link, idx, uni, multi); } static void __ieee80211_set_default_mgmt_key(struct ieee80211_link_data *link, int idx) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_key *key = NULL; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (idx >= NUM_DEFAULT_KEYS && idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); rcu_assign_pointer(link->default_mgmt_key, key); ieee80211_debugfs_key_update_default(sdata); } void ieee80211_set_default_mgmt_key(struct ieee80211_link_data *link, int idx) { lockdep_assert_wiphy(link->sdata->local->hw.wiphy); __ieee80211_set_default_mgmt_key(link, idx); } static void __ieee80211_set_default_beacon_key(struct ieee80211_link_data *link, int idx) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_key *key = NULL; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS && idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS) key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); rcu_assign_pointer(link->default_beacon_key, key); ieee80211_debugfs_key_update_default(sdata); } void ieee80211_set_default_beacon_key(struct ieee80211_link_data *link, int idx) { lockdep_assert_wiphy(link->sdata->local->hw.wiphy); __ieee80211_set_default_beacon_key(link, idx); } static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, struct sta_info *sta, bool pairwise, struct ieee80211_key *old, struct ieee80211_key *new) { struct link_sta_info *link_sta = sta ? &sta->deflink : NULL; int link_id; int idx; int ret = 0; bool defunikey, defmultikey, defmgmtkey, defbeaconkey; bool is_wep; lockdep_assert_wiphy(sdata->local->hw.wiphy); /* caller must provide at least one old/new */ if (WARN_ON(!new && !old)) return 0; if (new) { idx = new->conf.keyidx; is_wep = new->conf.cipher == WLAN_CIPHER_SUITE_WEP40 || new->conf.cipher == WLAN_CIPHER_SUITE_WEP104; link_id = new->conf.link_id; } else { idx = old->conf.keyidx; is_wep = old->conf.cipher == WLAN_CIPHER_SUITE_WEP40 || old->conf.cipher == WLAN_CIPHER_SUITE_WEP104; link_id = old->conf.link_id; } if (WARN(old && old->conf.link_id != link_id, "old link ID %d doesn't match new link ID %d\n", old->conf.link_id, link_id)) return -EINVAL; if (link_id >= 0) { if (!link) { link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return -ENOLINK; } if (sta) { link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&sta->local->hw.wiphy->mtx)); if (!link_sta) return -ENOLINK; } } else { link = &sdata->deflink; } if ((is_wep || pairwise) && idx >= NUM_DEFAULT_KEYS) return -EINVAL; WARN_ON(new && old && new->conf.keyidx != old->conf.keyidx); if (new && sta && pairwise) { /* Unicast rekey needs special handling. With Extended Key ID * old is still NULL for the first rekey. */ ieee80211_pairwise_rekey(old, new); } if (old) { if (old->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) { ieee80211_key_disable_hw_accel(old); if (new) ret = ieee80211_key_enable_hw_accel(new); } } else { if (!new->local->wowlan) ret = ieee80211_key_enable_hw_accel(new); else new->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; } if (ret) return ret; if (new) list_add_tail_rcu(&new->list, &sdata->key_list); if (sta) { if (pairwise) { rcu_assign_pointer(sta->ptk[idx], new); if (new && !(new->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX)) _ieee80211_set_tx_key(new, true); } else { rcu_assign_pointer(link_sta->gtk[idx], new); } /* Only needed for transition from no key -> key. * Still triggers unnecessary when using Extended Key ID * and installing the second key ID the first time. */ if (new && !old) ieee80211_check_fast_rx(sta); } else { defunikey = old && old == wiphy_dereference(sdata->local->hw.wiphy, sdata->default_unicast_key); defmultikey = old && old == wiphy_dereference(sdata->local->hw.wiphy, link->default_multicast_key); defmgmtkey = old && old == wiphy_dereference(sdata->local->hw.wiphy, link->default_mgmt_key); defbeaconkey = old && old == wiphy_dereference(sdata->local->hw.wiphy, link->default_beacon_key); if (defunikey && !new) __ieee80211_set_default_key(link, -1, true, false); if (defmultikey && !new) __ieee80211_set_default_key(link, -1, false, true); if (defmgmtkey && !new) __ieee80211_set_default_mgmt_key(link, -1); if (defbeaconkey && !new) __ieee80211_set_default_beacon_key(link, -1); if (is_wep || pairwise) rcu_assign_pointer(sdata->keys[idx], new); else rcu_assign_pointer(link->gtk[idx], new); if (defunikey && new) __ieee80211_set_default_key(link, new->conf.keyidx, true, false); if (defmultikey && new) __ieee80211_set_default_key(link, new->conf.keyidx, false, true); if (defmgmtkey && new) __ieee80211_set_default_mgmt_key(link, new->conf.keyidx); if (defbeaconkey && new) __ieee80211_set_default_beacon_key(link, new->conf.keyidx); } if (old) list_del_rcu(&old->list); return 0; } struct ieee80211_key * ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, const u8 *key_data, size_t seq_len, const u8 *seq) { struct ieee80211_key *key; int i, j, err; if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS)) return ERR_PTR(-EINVAL); key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL); if (!key) return ERR_PTR(-ENOMEM); /* * Default to software encryption; we'll later upload the * key to the hardware if possible. */ key->conf.flags = 0; key->flags = 0; key->conf.link_id = -1; key->conf.cipher = cipher; key->conf.keyidx = idx; key->conf.keylen = key_len; switch (cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: key->conf.iv_len = IEEE80211_WEP_IV_LEN; key->conf.icv_len = IEEE80211_WEP_ICV_LEN; break; case WLAN_CIPHER_SUITE_TKIP: key->conf.iv_len = IEEE80211_TKIP_IV_LEN; key->conf.icv_len = IEEE80211_TKIP_ICV_LEN; if (seq) { for (i = 0; i < IEEE80211_NUM_TIDS; i++) { key->u.tkip.rx[i].iv32 = get_unaligned_le32(&seq[2]); key->u.tkip.rx[i].iv16 = get_unaligned_le16(seq); } } spin_lock_init(&key->u.tkip.txlock); break; case WLAN_CIPHER_SUITE_CCMP: key->conf.iv_len = IEEE80211_CCMP_HDR_LEN; key->conf.icv_len = IEEE80211_CCMP_MIC_LEN; if (seq) { for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) for (j = 0; j < IEEE80211_CCMP_PN_LEN; j++) key->u.ccmp.rx_pn[i][j] = seq[IEEE80211_CCMP_PN_LEN - j - 1]; } /* * Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt( key_data, key_len, IEEE80211_CCMP_MIC_LEN); if (IS_ERR(key->u.ccmp.tfm)) { err = PTR_ERR(key->u.ccmp.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_CCMP_256: key->conf.iv_len = IEEE80211_CCMP_256_HDR_LEN; key->conf.icv_len = IEEE80211_CCMP_256_MIC_LEN; for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++) for (j = 0; j < IEEE80211_CCMP_256_PN_LEN; j++) key->u.ccmp.rx_pn[i][j] = seq[IEEE80211_CCMP_256_PN_LEN - j - 1]; /* Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt( key_data, key_len, IEEE80211_CCMP_256_MIC_LEN); if (IS_ERR(key->u.ccmp.tfm)) { err = PTR_ERR(key->u.ccmp.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: key->conf.iv_len = 0; if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) key->conf.icv_len = sizeof(struct ieee80211_mmie); else key->conf.icv_len = sizeof(struct ieee80211_mmie_16); if (seq) for (j = 0; j < IEEE80211_CMAC_PN_LEN; j++) key->u.aes_cmac.rx_pn[j] = seq[IEEE80211_CMAC_PN_LEN - j - 1]; /* * Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.aes_cmac.tfm = ieee80211_aes_cmac_key_setup(key_data, key_len); if (IS_ERR(key->u.aes_cmac.tfm)) { err = PTR_ERR(key->u.aes_cmac.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: key->conf.iv_len = 0; key->conf.icv_len = sizeof(struct ieee80211_mmie_16); if (seq) for (j = 0; j < IEEE80211_GMAC_PN_LEN; j++) key->u.aes_gmac.rx_pn[j] = seq[IEEE80211_GMAC_PN_LEN - j - 1]; /* Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.aes_gmac.tfm = ieee80211_aes_gmac_key_setup(key_data, key_len); if (IS_ERR(key->u.aes_gmac.tfm)) { err = PTR_ERR(key->u.aes_gmac.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: key->conf.iv_len = IEEE80211_GCMP_HDR_LEN; key->conf.icv_len = IEEE80211_GCMP_MIC_LEN; for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++) for (j = 0; j < IEEE80211_GCMP_PN_LEN; j++) key->u.gcmp.rx_pn[i][j] = seq[IEEE80211_GCMP_PN_LEN - j - 1]; /* Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.gcmp.tfm = ieee80211_aes_gcm_key_setup_encrypt(key_data, key_len); if (IS_ERR(key->u.gcmp.tfm)) { err = PTR_ERR(key->u.gcmp.tfm); kfree(key); return ERR_PTR(err); } break; } memcpy(key->conf.key, key_data, key_len); INIT_LIST_HEAD(&key->list); return key; } static void ieee80211_key_free_common(struct ieee80211_key *key) { switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: ieee80211_aes_key_free(key->u.ccmp.tfm); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: ieee80211_aes_gmac_key_free(key->u.aes_gmac.tfm); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: ieee80211_aes_gcm_key_free(key->u.gcmp.tfm); break; } kfree_sensitive(key); } static void __ieee80211_key_destroy(struct ieee80211_key *key, bool delay_tailroom) { if (key->local) { struct ieee80211_sub_if_data *sdata = key->sdata; ieee80211_debugfs_key_remove(key); if (delay_tailroom) { /* see ieee80211_delayed_tailroom_dec */ sdata->crypto_tx_tailroom_pending_dec++; wiphy_delayed_work_queue(sdata->local->hw.wiphy, &sdata->dec_tailroom_needed_wk, HZ / 2); } else { decrease_tailroom_need_count(sdata, 1); } } ieee80211_key_free_common(key); } static void ieee80211_key_destroy(struct ieee80211_key *key, bool delay_tailroom) { if (!key) return; /* * Synchronize so the TX path and rcu key iterators * can no longer be using this key before we free/remove it. */ synchronize_net(); __ieee80211_key_destroy(key, delay_tailroom); } void ieee80211_key_free_unused(struct ieee80211_key *key) { if (!key) return; WARN_ON(key->sdata || key->local); ieee80211_key_free_common(key); } static bool ieee80211_key_identical(struct ieee80211_sub_if_data *sdata, struct ieee80211_key *old, struct ieee80211_key *new) { u8 tkip_old[WLAN_KEY_LEN_TKIP], tkip_new[WLAN_KEY_LEN_TKIP]; u8 *tk_old, *tk_new; if (!old || new->conf.keylen != old->conf.keylen) return false; tk_old = old->conf.key; tk_new = new->conf.key; /* * In station mode, don't compare the TX MIC key, as it's never used * and offloaded rekeying may not care to send it to the host. This * is the case in iwlwifi, for example. */ if (sdata->vif.type == NL80211_IFTYPE_STATION && new->conf.cipher == WLAN_CIPHER_SUITE_TKIP && new->conf.keylen == WLAN_KEY_LEN_TKIP && !(new->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) { memcpy(tkip_old, tk_old, WLAN_KEY_LEN_TKIP); memcpy(tkip_new, tk_new, WLAN_KEY_LEN_TKIP); memset(tkip_old + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8); memset(tkip_new + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8); tk_old = tkip_old; tk_new = tkip_new; } return !crypto_memneq(tk_old, tk_new, new->conf.keylen); } int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_link_data *link, struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = link->sdata; static atomic_t key_color = ATOMIC_INIT(0); struct ieee80211_key *old_key = NULL; int idx = key->conf.keyidx; bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; /* * We want to delay tailroom updates only for station - in that * case it helps roaming speed, but in other cases it hurts and * can cause warnings to appear. */ bool delay_tailroom = sdata->vif.type == NL80211_IFTYPE_STATION; int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (sta && pairwise) { struct ieee80211_key *alt_key; old_key = wiphy_dereference(sdata->local->hw.wiphy, sta->ptk[idx]); alt_key = wiphy_dereference(sdata->local->hw.wiphy, sta->ptk[idx ^ 1]); /* The rekey code assumes that the old and new key are using * the same cipher. Enforce the assumption for pairwise keys. */ if ((alt_key && alt_key->conf.cipher != key->conf.cipher) || (old_key && old_key->conf.cipher != key->conf.cipher)) { ret = -EOPNOTSUPP; goto out; } } else if (sta) { struct link_sta_info *link_sta = &sta->deflink; int link_id = key->conf.link_id; if (link_id >= 0) { link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&sta->local->hw.wiphy->mtx)); if (!link_sta) { ret = -ENOLINK; goto out; } } old_key = wiphy_dereference(sdata->local->hw.wiphy, link_sta->gtk[idx]); } else { if (idx < NUM_DEFAULT_KEYS) old_key = wiphy_dereference(sdata->local->hw.wiphy, sdata->keys[idx]); if (!old_key) old_key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); } /* Non-pairwise keys must also not switch the cipher on rekey */ if (!pairwise) { if (old_key && old_key->conf.cipher != key->conf.cipher) { ret = -EOPNOTSUPP; goto out; } } /* * Silently accept key re-installation without really installing the * new version of the key to avoid nonce reuse or replay issues. */ if (ieee80211_key_identical(sdata, old_key, key)) { ret = -EALREADY; goto out; } key->local = sdata->local; key->sdata = sdata; key->sta = sta; /* * Assign a unique ID to every key so we can easily prevent mixed * key and fragment cache attacks. */ key->color = atomic_inc_return(&key_color); /* keep this flag for easier access later */ if (sta && sta->sta.spp_amsdu) key->conf.flags |= IEEE80211_KEY_FLAG_SPP_AMSDU; increment_tailroom_need_count(sdata); ret = ieee80211_key_replace(sdata, link, sta, pairwise, old_key, key); if (!ret) { ieee80211_debugfs_key_add(key); ieee80211_key_destroy(old_key, delay_tailroom); } else { ieee80211_key_free(key, delay_tailroom); } key = NULL; out: ieee80211_key_free_unused(key); return ret; } void ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom) { if (!key) return; /* * Replace key with nothingness if it was ever used. */ if (key->sdata) ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); ieee80211_key_destroy(key, delay_tailroom); } void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata) { struct ieee80211_key *key; struct ieee80211_sub_if_data *vlan; lockdep_assert_wiphy(sdata->local->hw.wiphy); sdata->crypto_tx_tailroom_needed_cnt = 0; sdata->crypto_tx_tailroom_pending_dec = 0; if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { vlan->crypto_tx_tailroom_needed_cnt = 0; vlan->crypto_tx_tailroom_pending_dec = 0; } } if (ieee80211_sdata_running(sdata)) { list_for_each_entry(key, &sdata->key_list, list) { increment_tailroom_need_count(sdata); ieee80211_key_enable_hw_accel(key); } } } static void ieee80211_key_iter(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_key *key, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { /* skip keys of station in removal process */ if (key->sta && key->sta->removed) return; if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) return; iter(hw, vif, key->sta ? &key->sta->sta : NULL, &key->conf, iter_data); } void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_key *key, *tmp; struct ieee80211_sub_if_data *sdata; lockdep_assert_wiphy(hw->wiphy); if (vif) { sdata = vif_to_sdata(vif); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) ieee80211_key_iter(hw, vif, key, iter, iter_data); } else { list_for_each_entry(sdata, &local->interfaces, list) list_for_each_entry_safe(key, tmp, &sdata->key_list, list) ieee80211_key_iter(hw, &sdata->vif, key, iter, iter_data); } } EXPORT_SYMBOL(ieee80211_iter_keys); static void _ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, struct ieee80211_sub_if_data *sdata, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { struct ieee80211_key *key; list_for_each_entry_rcu(key, &sdata->key_list, list) ieee80211_key_iter(hw, &sdata->vif, key, iter, iter_data); } void ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; if (vif) { sdata = vif_to_sdata(vif); _ieee80211_iter_keys_rcu(hw, sdata, iter, iter_data); } else { list_for_each_entry_rcu(sdata, &local->interfaces, list) _ieee80211_iter_keys_rcu(hw, sdata, iter, iter_data); } } EXPORT_SYMBOL(ieee80211_iter_keys_rcu); static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, struct list_head *keys) { struct ieee80211_key *key, *tmp; decrease_tailroom_need_count(sdata, sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); ieee80211_debugfs_key_remove_beacon_default(sdata); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) { ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); list_add_tail(&key->list, keys); } ieee80211_debugfs_key_update_default(sdata); } void ieee80211_remove_link_keys(struct ieee80211_link_data *link, struct list_head *keys) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_key *key, *tmp; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) { if (key->conf.link_id != link->link_id) continue; ieee80211_key_replace(key->sdata, link, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); list_add_tail(&key->list, keys); } } void ieee80211_free_key_list(struct ieee80211_local *local, struct list_head *keys) { struct ieee80211_key *key, *tmp; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry_safe(key, tmp, keys, list) __ieee80211_key_destroy(key, false); } void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, bool force_synchronize) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *vlan; struct ieee80211_sub_if_data *master; struct ieee80211_key *key, *tmp; LIST_HEAD(keys); wiphy_delayed_work_cancel(local->hw.wiphy, &sdata->dec_tailroom_needed_wk); lockdep_assert_wiphy(local->hw.wiphy); ieee80211_free_keys_iface(sdata, &keys); if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) ieee80211_free_keys_iface(vlan, &keys); } if (!list_empty(&keys) || force_synchronize) synchronize_net(); list_for_each_entry_safe(key, tmp, &keys, list) __ieee80211_key_destroy(key, false); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { if (sdata->bss) { master = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt != master->crypto_tx_tailroom_needed_cnt); } } else { WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || sdata->crypto_tx_tailroom_pending_dec); } if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || vlan->crypto_tx_tailroom_pending_dec); } } void ieee80211_free_sta_keys(struct ieee80211_local *local, struct sta_info *sta) { struct ieee80211_key *key; int i; lockdep_assert_wiphy(local->hw.wiphy); for (i = 0; i < ARRAY_SIZE(sta->deflink.gtk); i++) { key = wiphy_dereference(local->hw.wiphy, sta->deflink.gtk[i]); if (!key) continue; ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); __ieee80211_key_destroy(key, key->sdata->vif.type == NL80211_IFTYPE_STATION); } for (i = 0; i < NUM_DEFAULT_KEYS; i++) { key = wiphy_dereference(local->hw.wiphy, sta->ptk[i]); if (!key) continue; ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); __ieee80211_key_destroy(key, key->sdata->vif.type == NL80211_IFTYPE_STATION); } } void ieee80211_delayed_tailroom_dec(struct wiphy *wiphy, struct wiphy_work *wk) { struct ieee80211_sub_if_data *sdata; sdata = container_of(wk, struct ieee80211_sub_if_data, dec_tailroom_needed_wk.work); /* * The reason for the delayed tailroom needed decrementing is to * make roaming faster: during roaming, all keys are first deleted * and then new keys are installed. The first new key causes the * crypto_tx_tailroom_needed_cnt to go from 0 to 1, which invokes * the cost of synchronize_net() (which can be slow). Avoid this * by deferring the crypto_tx_tailroom_needed_cnt decrementing on * key removal for a while, so if we roam the value is larger than * zero and no 0->1 transition happens. * * The cost is that if the AP switching was from an AP with keys * to one without, we still allocate tailroom while it would no * longer be needed. However, in the typical (fast) roaming case * within an ESS this usually won't happen. */ decrease_tailroom_need_count(sdata, sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; } void ieee80211_gtk_rekey_notify(struct ieee80211_vif *vif, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); trace_api_gtk_rekey_notify(sdata, bssid, replay_ctr); cfg80211_gtk_rekey_notify(sdata->dev, bssid, replay_ctr, gfp); } EXPORT_SYMBOL_GPL(ieee80211_gtk_rekey_notify); void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq) { struct ieee80211_key *key; const u8 *pn; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: if (WARN_ON(tid < 0 || tid >= IEEE80211_NUM_TIDS)) return; seq->tkip.iv32 = key->u.tkip.rx[tid].iv32; seq->tkip.iv16 = key->u.tkip.rx[tid].iv16; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.ccmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.ccmp.rx_pn[tid]; memcpy(seq->ccmp.pn, pn, IEEE80211_CCMP_PN_LEN); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_cmac.rx_pn; memcpy(seq->aes_cmac.pn, pn, IEEE80211_CMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_gmac.rx_pn; memcpy(seq->aes_gmac.pn, pn, IEEE80211_GMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.gcmp.rx_pn[tid]; memcpy(seq->gcmp.pn, pn, IEEE80211_GCMP_PN_LEN); break; } } EXPORT_SYMBOL(ieee80211_get_key_rx_seq); void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq) { struct ieee80211_key *key; u8 *pn; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: if (WARN_ON(tid < 0 || tid >= IEEE80211_NUM_TIDS)) return; key->u.tkip.rx[tid].iv32 = seq->tkip.iv32; key->u.tkip.rx[tid].iv16 = seq->tkip.iv16; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.ccmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.ccmp.rx_pn[tid]; memcpy(pn, seq->ccmp.pn, IEEE80211_CCMP_PN_LEN); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_cmac.rx_pn; memcpy(pn, seq->aes_cmac.pn, IEEE80211_CMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_gmac.rx_pn; memcpy(pn, seq->aes_gmac.pn, IEEE80211_GMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.gcmp.rx_pn[tid]; memcpy(pn, seq->gcmp.pn, IEEE80211_GCMP_PN_LEN); break; default: WARN_ON(1); break; } } EXPORT_SYMBOL_GPL(ieee80211_set_key_rx_seq); void ieee80211_remove_key(struct ieee80211_key_conf *keyconf) { struct ieee80211_key *key; key = container_of(keyconf, struct ieee80211_key, conf); lockdep_assert_wiphy(key->local->hw.wiphy); /* * if key was uploaded, we assume the driver will/has remove(d) * it, so adjust bookkeeping accordingly */ if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) { key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; if (!(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(key->sdata); } ieee80211_key_free(key, false); } EXPORT_SYMBOL_GPL(ieee80211_remove_key); struct ieee80211_key_conf * ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, struct ieee80211_key_conf *keyconf, int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; int err; struct ieee80211_link_data *link_data = link_id < 0 ? &sdata->deflink : sdata_dereference(sdata->link[link_id], sdata); if (WARN_ON(!link_data)) return ERR_PTR(-EINVAL); if (WARN_ON(!local->wowlan)) return ERR_PTR(-EINVAL); if (WARN_ON(vif->type != NL80211_IFTYPE_STATION)) return ERR_PTR(-EINVAL); key = ieee80211_key_alloc(keyconf->cipher, keyconf->keyidx, keyconf->keylen, keyconf->key, 0, NULL); if (IS_ERR(key)) return ERR_CAST(key); if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; key->conf.link_id = link_data->link_id; err = ieee80211_key_link(key, link_data, NULL); if (err) return ERR_PTR(err); return &key->conf; } EXPORT_SYMBOL_GPL(ieee80211_gtk_rekey_add); void ieee80211_key_mic_failure(struct ieee80211_key_conf *keyconf) { struct ieee80211_key *key; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: key->u.aes_cmac.icverrors++; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: key->u.aes_gmac.icverrors++; break; default: /* ignore the others for now, we don't keep counters now */ break; } } EXPORT_SYMBOL_GPL(ieee80211_key_mic_failure); void ieee80211_key_replay(struct ieee80211_key_conf *keyconf) { struct ieee80211_key *key; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: key->u.ccmp.replays++; break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: key->u.aes_cmac.replays++; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: key->u.aes_gmac.replays++; break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: key->u.gcmp.replays++; break; } } EXPORT_SYMBOL_GPL(ieee80211_key_replay); int ieee80211_key_switch_links(struct ieee80211_sub_if_data *sdata, unsigned long del_links_mask, unsigned long add_links_mask) { struct ieee80211_key *key; int ret; list_for_each_entry(key, &sdata->key_list, list) { if (key->conf.link_id < 0 || !(del_links_mask & BIT(key->conf.link_id))) continue; /* shouldn't happen for per-link keys */ WARN_ON(key->sta); ieee80211_key_disable_hw_accel(key); } list_for_each_entry(key, &sdata->key_list, list) { if (key->conf.link_id < 0 || !(add_links_mask & BIT(key->conf.link_id))) continue; /* shouldn't happen for per-link keys */ WARN_ON(key->sta); ret = ieee80211_key_enable_hw_accel(key); if (ret) return ret; } return 0; } |
| 108 223 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2005 Intel Corporation. All rights reserved. */ #ifndef IB_ADDR_H #define IB_ADDR_H #include <linux/ethtool.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <linux/if_vlan.h> #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/ip.h> #include <rdma/ib_verbs.h> #include <rdma/ib_pack.h> #include <net/net_namespace.h> /** * struct rdma_dev_addr - Contains resolved RDMA hardware addresses * @src_dev_addr: Source MAC address. * @dst_dev_addr: Destination MAC address. * @broadcast: Broadcast address of the device. * @dev_type: The interface hardware type of the device. * @bound_dev_if: An optional device interface index. * @transport: The transport type used. * @net: Network namespace containing the bound_dev_if net_dev. * @sgid_attr: GID attribute to use for identified SGID */ struct rdma_dev_addr { unsigned char src_dev_addr[MAX_ADDR_LEN]; unsigned char dst_dev_addr[MAX_ADDR_LEN]; unsigned char broadcast[MAX_ADDR_LEN]; unsigned short dev_type; int bound_dev_if; enum rdma_transport_type transport; struct net *net; const struct ib_gid_attr *sgid_attr; enum rdma_network_type network; int hoplimit; }; /** * rdma_translate_ip - Translate a local IP address to an RDMA hardware * address. * * The dev_addr->net field must be initialized. */ int rdma_translate_ip(const struct sockaddr *addr, struct rdma_dev_addr *dev_addr); /** * rdma_resolve_ip - Resolve source and destination IP addresses to * RDMA hardware addresses. * @src_addr: An optional source address to use in the resolution. If a * source address is not provided, a usable address will be returned via * the callback. * @dst_addr: The destination address to resolve. * @addr: A reference to a data location that will receive the resolved * addresses. The data location must remain valid until the callback has * been invoked. The net field of the addr struct must be valid. * @timeout_ms: Amount of time to wait for the address resolution to complete. * @callback: Call invoked once address resolution has completed, timed out, * or been canceled. A status of 0 indicates success. * @resolve_by_gid_attr: Resolve the ip based on the GID attribute from * rdma_dev_addr. * @context: User-specified context associated with the call. */ int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr, struct rdma_dev_addr *addr, unsigned long timeout_ms, void (*callback)(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context), bool resolve_by_gid_attr, void *context); void rdma_addr_cancel(struct rdma_dev_addr *addr); int rdma_addr_size(const struct sockaddr *addr); int rdma_addr_size_in6(struct sockaddr_in6 *addr); int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr); static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr) { return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9]; } static inline void ib_addr_set_pkey(struct rdma_dev_addr *dev_addr, u16 pkey) { dev_addr->broadcast[8] = pkey >> 8; dev_addr->broadcast[9] = (unsigned char) pkey; } static inline void ib_addr_get_mgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->broadcast + 4, sizeof *gid); } static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) { return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; } static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 0xffff; } static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid) { switch (addr->sa_family) { case AF_INET: ipv6_addr_set_v4mapped(((struct sockaddr_in *) addr)->sin_addr.s_addr, (struct in6_addr *)gid); break; case AF_INET6: *(struct in6_addr *)&gid->raw = ((struct sockaddr_in6 *)addr)->sin6_addr; break; default: return -EINVAL; } return 0; } /* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */ static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid) { if (ipv6_addr_v4mapped((struct in6_addr *)gid)) { struct sockaddr_in *out_in = (struct sockaddr_in *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin_family = AF_INET; memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4); } else { struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin6_family = AF_INET6; memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16); } } /* * rdma_get/set_sgid/dgid() APIs are applicable to IB, and iWarp. * They are not applicable to RoCE. * RoCE GIDs are derived from the IP addresses. */ static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(*gid)); } static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline void rdma_addr_get_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid); } static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline enum ib_mtu iboe_get_mtu(int mtu) { /* * Reduce IB headers from effective IBoE MTU. */ mtu = mtu - (IB_GRH_BYTES + IB_UDP_BYTES + IB_BTH_BYTES + IB_EXT_XRC_BYTES + IB_EXT_ATOMICETH_BYTES + IB_ICRC_BYTES); if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) return IB_MTU_4096; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048)) return IB_MTU_2048; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024)) return IB_MTU_1024; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512)) return IB_MTU_512; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256)) return IB_MTU_256; else return 0; } static inline int rdma_link_local_addr(struct in6_addr *addr) { if (addr->s6_addr32[0] == htonl(0xfe800000) && addr->s6_addr32[1] == 0) return 1; return 0; } static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) { memcpy(mac, &addr->s6_addr[8], 3); memcpy(mac + 3, &addr->s6_addr[13], 3); mac[0] ^= 2; } static inline int rdma_is_multicast_addr(struct in6_addr *addr) { __be32 ipv4_addr; if (addr->s6_addr[0] == 0xff) return 1; ipv4_addr = addr->s6_addr32[3]; return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr)); } static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) { int i; mac[0] = 0x33; mac[1] = 0x33; for (i = 2; i < 6; ++i) mac[i] = addr->s6_addr[i + 10]; } static inline u16 rdma_get_vlan_id(union ib_gid *dgid) { u16 vid; vid = dgid->raw[11] << 8 | dgid->raw[12]; return vid < 0x1000 ? vid : 0xffff; } static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : NULL; } #endif /* IB_ADDR_H */ |
| 5 3 18 888 888 2 17 17 16 17 11 1 5 16 16 2 14 16 10 7 3 3 3 6 6 6 6 6 2 2 30 30 28 2 30 4 36 26 4 4 4 4 2 14 4 10 19 19 19 25 14 19 43 13 30 43 66 23 43 43 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/file.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/rw_hint.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #include "internal.h" #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } /* * Allocate an file->f_owner struct if it doesn't exist, handling racing * allocations correctly. */ int file_f_owner_allocate(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) return 0; f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL); if (!f_owner) return -ENOMEM; rwlock_init(&f_owner->lock); f_owner->file = file; /* If someone else raced us, drop our allocation. */ if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner))) kfree(f_owner); return 0; } EXPORT_SYMBOL(file_f_owner_allocate); void file_f_owner_release(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) { put_pid(f_owner->pid); kfree(f_owner); } } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (WARN_ON_ONCE(!f_owner)) return; write_lock_irq(&f_owner->lock); if (force || !f_owner->pid) { put_pid(f_owner->pid); f_owner->pid = get_pid(pid); f_owner->pid_type = type; if (pid) { const struct cred *cred = current_cred(); security_file_set_fowner(filp); f_owner->uid = cred->uid; f_owner->euid = cred->euid; } } write_unlock_irq(&f_owner->lock); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, int who, int force) { enum pid_type type; struct pid *pid = NULL; int ret = 0; might_sleep(); type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { __f_setown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (!f_owner) return pid; read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) { pid = pid_vnr(f_owner->pid); if (f_owner->pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&f_owner->lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; struct fown_struct *f_owner; enum pid_type pid_type = PIDTYPE_PID; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) owner.pid = pid_vnr(f_owner->pid); rcu_read_unlock(); pid_type = f_owner->pid_type; } switch (pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } if (f_owner) read_unlock_irq(&f_owner->lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); struct fown_struct *f_owner; uid_t __user *dst = (void __user *)arg; uid_t src[2] = {0, 0}; int err; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); src[0] = from_kuid(user_ns, f_owner->uid); src[1] = from_kuid(user_ns, f_owner->euid); read_unlock_irq(&f_owner->lock); } err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET); BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE); BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT); BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM); BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG); BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME); switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_get_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint = READ_ONCE(inode->i_write_hint); if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; } static long fcntl_set_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; if (!inode_owner_or_capable(file_mnt_idmap(file), inode)) return -EPERM; if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; WRITE_ONCE(inode->i_write_hint, hint); /* * file->f_mapping->host may differ from inode. As an example, * blkdev_open() modifies file->f_mapping. */ if (file->f_mapping->host != inode) WRITE_ONCE(file->f_mapping->host->i_write_hint, hint); return 0; } /* Is the file descriptor a dup of the file? */ static long f_dupfd_query(int fd, struct file *filp) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return -EBADF; /* * We can do the 'fdput()' immediately, as the only thing that * matters is the pointer value which isn't changed by the fdput. * * Technically we didn't need a ref at all, and 'fdget()' was * overkill, but given our lockless file pointer lookup, the * alternatives are complicated. */ return fd_file(f) == filp; } /* Let the caller figure out whether a given file was just created. */ static long f_created_query(const struct file *filp) { return !!(filp->f_mode & FMODE_CREATED); } static int f_owner_sig(struct file *filp, int signum, bool setsig) { int ret = 0; struct fown_struct *f_owner; might_sleep(); if (setsig) { if (!valid_signal(signum)) return -EINVAL; ret = file_f_owner_allocate(filp); if (ret) return ret; } f_owner = file_f_owner(filp); if (setsig) f_owner->signum = signum; else if (f_owner) ret = f_owner->signum; return ret; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; int argi = (int)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_CREATED_QUERY: err = f_created_query(filp); break; case F_DUPFD: err = f_dupfd(argi, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; case F_DUPFD_QUERY: err = f_dupfd_query(argi, filp); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, argi & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, argi); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, argi, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = f_owner_sig(filp, 0, false); break; case F_SETSIG: err = f_owner_sig(filp, argi, true); break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, argi); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, argi); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, argi); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, argi); break; case F_GET_RW_HINT: err = fcntl_get_rw_hint(filp, cmd, arg); break; case F_SET_RW_HINT: err = fcntl_set_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_CREATED_QUERY: case F_DUPFD: case F_DUPFD_CLOEXEC: case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { CLASS(fd_raw, f)(fd); long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, fd_file(f)); return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; CLASS(fd_raw, f)(fd); struct flock64 flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(fd_file(f), cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, fd_file(f), cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { CLASS(fd_raw, f)(fd); struct flock flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct file *file) { struct fown_struct *fown; struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; fown = file_f_owner(file); if (!fown) return 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; kfree_rcu(fa, fa_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = file_f_owner(fa->fa_file); if (!fown) goto next; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } next: read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash algorithms. * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_HASH_H #define _CRYPTO_INTERNAL_HASH_H #include <crypto/algapi.h> #include <crypto/hash.h> struct ahash_request; struct ahash_instance { void (*free)(struct ahash_instance *inst); union { struct { char head[offsetof(struct ahash_alg, halg.base)]; struct crypto_instance base; } s; struct ahash_alg alg; }; }; struct shash_instance { void (*free)(struct shash_instance *inst); union { struct { char head[offsetof(struct shash_alg, base)]; struct crypto_instance base; } s; struct shash_alg alg; }; }; struct crypto_ahash_spawn { struct crypto_spawn base; }; struct crypto_shash_spawn { struct crypto_spawn base; }; int crypto_register_ahash(struct ahash_alg *alg); void crypto_unregister_ahash(struct ahash_alg *alg); int crypto_register_ahashes(struct ahash_alg *algs, int count); void crypto_unregister_ahashes(struct ahash_alg *algs, int count); int ahash_register_instance(struct crypto_template *tmpl, struct ahash_instance *inst); int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); static inline bool crypto_shash_alg_has_setkey(struct shash_alg *alg) { return alg->setkey != shash_no_setkey; } static inline bool crypto_shash_alg_needs_key(struct shash_alg *alg) { return crypto_shash_alg_has_setkey(alg) && !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY); } int crypto_grab_ahash(struct crypto_ahash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_ahash(struct crypto_ahash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct hash_alg_common *crypto_spawn_ahash_alg( struct crypto_ahash_spawn *spawn) { return __crypto_hash_alg_common(spawn->base.alg); } int crypto_register_shash(struct shash_alg *alg); void crypto_unregister_shash(struct shash_alg *alg); int crypto_register_shashes(struct shash_alg *algs, int count); void crypto_unregister_shashes(struct shash_alg *algs, int count); int shash_register_instance(struct crypto_template *tmpl, struct shash_instance *inst); void shash_free_singlespawn_instance(struct shash_instance *inst); int crypto_grab_shash(struct crypto_shash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_shash(struct crypto_shash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct shash_alg *crypto_spawn_shash_alg( struct crypto_shash_spawn *spawn) { return __crypto_shash_alg(spawn->base.alg); } int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc); static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm) { return crypto_tfm_ctx(crypto_ahash_tfm(tfm)); } static inline void *crypto_ahash_ctx_dma(struct crypto_ahash *tfm) { return crypto_tfm_ctx_dma(crypto_ahash_tfm(tfm)); } static inline struct ahash_alg *__crypto_ahash_alg(struct crypto_alg *alg) { return container_of(__crypto_hash_alg_common(alg), struct ahash_alg, halg); } static inline struct ahash_alg *crypto_ahash_alg(struct crypto_ahash *hash) { return container_of(crypto_hash_alg_common(hash), struct ahash_alg, halg); } static inline void crypto_ahash_set_statesize(struct crypto_ahash *tfm, unsigned int size) { tfm->statesize = size; } static inline void crypto_ahash_set_reqsize(struct crypto_ahash *tfm, unsigned int reqsize) { tfm->reqsize = reqsize; } static inline void crypto_ahash_set_reqsize_dma(struct crypto_ahash *ahash, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); ahash->reqsize = reqsize; } static inline struct crypto_instance *ahash_crypto_instance( struct ahash_instance *inst) { return &inst->s.base; } static inline struct ahash_instance *ahash_instance( struct crypto_instance *inst) { return container_of(inst, struct ahash_instance, s.base); } static inline struct ahash_instance *ahash_alg_instance( struct crypto_ahash *ahash) { return ahash_instance(crypto_tfm_alg_instance(&ahash->base)); } static inline void *ahash_instance_ctx(struct ahash_instance *inst) { return crypto_instance_ctx(ahash_crypto_instance(inst)); } static inline void *ahash_request_ctx_dma(struct ahash_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(ahash_request_ctx(req), align); } static inline void ahash_request_complete(struct ahash_request *req, int err) { crypto_request_complete(&req->base, err); } static inline u32 ahash_request_flags(struct ahash_request *req) { return req->base.flags; } static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline int ahash_enqueue_request(struct crypto_queue *queue, struct ahash_request *request) { return crypto_enqueue_request(queue, &request->base); } static inline struct ahash_request *ahash_dequeue_request( struct crypto_queue *queue) { return ahash_request_cast(crypto_dequeue_request(queue)); } static inline void *crypto_shash_ctx(struct crypto_shash *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline struct crypto_instance *shash_crypto_instance( struct shash_instance *inst) { return &inst->s.base; } static inline struct shash_instance *shash_instance( struct crypto_instance *inst) { return container_of(inst, struct shash_instance, s.base); } static inline struct shash_instance *shash_alg_instance( struct crypto_shash *shash) { return shash_instance(crypto_tfm_alg_instance(&shash->base)); } static inline void *shash_instance_ctx(struct shash_instance *inst) { return crypto_instance_ctx(shash_crypto_instance(inst)); } static inline struct crypto_shash *crypto_spawn_shash( struct crypto_shash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline struct crypto_shash *__crypto_shash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_shash, base); } static inline bool ahash_request_chained(struct ahash_request *req) { return false; } static inline bool ahash_request_isvirt(struct ahash_request *req) { return req->base.flags & CRYPTO_AHASH_REQ_VIRT; } static inline bool crypto_ahash_req_chain(struct crypto_ahash *tfm) { return crypto_tfm_req_chain(&tfm->base); } #endif /* _CRYPTO_INTERNAL_HASH_H */ |
| 1176 698 17 2 2 807 808 809 366 360 1 10 1983 9 1983 424 2 422 564 15 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * * Avoid unnecessary multiplications/divisions in the * two most common HZ cases. * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value * * Return: microseconds value */ unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; # else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; # endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); /** * mktime64 - Converts date to seconds. * @year0: year to convert * @mon0: month to convert * @day: day to convert * @hour: hour to convert * @min: minute to convert * @sec: second to convert * * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. * * Return: seconds since the epoch time for the given input date */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC. * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Return: the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h * * Return: jiffies value */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); /** * __usecs_to_jiffies: - convert microseconds to jiffies * @u: time in milliseconds * * Return: jiffies value */ unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /** * timespec64_to_jiffies - convert a timespec64 value to jiffies * @value: pointer to &struct timespec64 * * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundaries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. * * Return: jiffies value */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); /** * jiffies_to_timespec64 - convert jiffies value to &struct timespec64 * @jiffies: jiffies value * @value: pointer to &struct timespec64 */ void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ /** * jiffies_to_clock_t - Convert jiffies to clock_t * @x: jiffies value * * Return: jiffies converted to clock_t (CLOCKS_PER_SEC) */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); /** * clock_t_to_jiffies - Convert clock_t to jiffies * @x: clock_t value * * Return: clock_t value converted to jiffies */ unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); /** * jiffies_64_to_clock_t - Convert jiffies_64 to clock_t * @x: jiffies_64 value * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); /** * nsec_to_clock_t - Convert nsec value to clock_t * @x: nsec value * * Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } /** * jiffies64_to_nsecs - Convert jiffies64 to nanoseconds * @j: jiffies64 value * * Return: nanoseconds value */ u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); /** * jiffies64_to_msecs - Convert jiffies64 to milliseconds * @j: jiffies64 value * * Return: milliseconds value */ u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies64 value */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies value */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /** * timespec64_add_safe - Add two timespec64 values and do a safety check * for overflow. * @lhs: first (left) timespec64 to add * @rhs: second (right) timespec64 to add * * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. * * Return: sum of @lhs + @rhs */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } /** * get_timespec64 - get user's time value into kernel space * @ts: destination &struct timespec64 * @uts: user's time value as &struct __kernel_timespec * * Handles compat or 32-bit modes. * * Return: 0 on success or negative errno on error */ int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); /** * put_timespec64 - convert timespec64 value to __kernel_timespec format and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct __kernel_timespec * * Return: 0 on success or negative errno on error */ int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } /** * get_old_timespec32 - get user's old-format time value into kernel space * @ts: destination &struct timespec64 * @uts: user's old-format time value (&struct old_timespec32) * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); /** * put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct old_timespec32 * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); /** * get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space * @it: destination &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(get_itimerspec64); /** * put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format * and copy the latter to userspace * @it: input &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) { int ret; ret = put_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = put_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); /** * get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space * @its: destination &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) { if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(get_old_itimerspec32); /** * put_old_itimerspec32 - convert &struct itimerspec64 to &struct * old_itimerspec32 and copy the latter to userspace * @its: input &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) { if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(put_old_itimerspec32); |
| 11 11 11 11 11 11 11 11 11 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <linux/crc32c.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ __be32 s_head; /* blocknr of head of log, only uptodate * while the filesystem is clean */ /* 0x005C */ __u32 s_padding[40]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. * (Locking Documentation improved by LockDoc) */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock, no locks needed fo * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for * one at all times. [j_list_lock, no locks needed for jbd2 * thread] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested [j_state_lock] */ unsigned long t_requested; /* * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock, * no lock for quick racy checks] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock, * no lock for quick racy checks] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock, no lock for quick racy checks] [caller holding * open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_shrinker: * * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: * * Record next transaction will shrink on the checkpoint list. * [j_list_lock] */ transaction_t *j_shrink_transaction; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_fs_dev_wb_err: * * Records the errseq of the client fs's backing block device. */ errseq_t j_fs_dev_wb_err; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_transaction_overhead_buffers: * * Number of blocks each transaction needs for its own bookkeeping */ int j_transaction_overhead_buffers; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); /** * @j_bmap: * * Bmap function that should be used instead of the generic * VFS bmap function. */ int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* * We can support any known requested features iff the * superblock is not in version 1. Otherwise we fail to support any * extended sb features. */ static inline bool jbd2_format_support_feature(journal_t *j) { return j->j_superblock->s_header.h_blocktype != cpu_to_be32(JBD2_SUPERBLOCK_V1); } /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* Journal high priority write IO operation flags */ #define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on * clean and empty filesystem * logging area */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ #define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 #define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); void jbd2_journal_wait_updates(journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_handle(_gfp_flags) \ ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_inode(_gfp_flags) \ ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size); void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern void jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); void jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which * could be used to detect the client fs's metadata async write error. */ errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); } static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { return jbd2_has_feature_csum2(journal) || jbd2_has_feature_csum3(journal); } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { return crc32c(crc, address, length); } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_H */ |
| 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Syscall interface to knfsd. * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */ #include <linux/slab.h> #include <linux/namei.h> #include <linux/ctype.h> #include <linux/fs_context.h> #include <linux/sunrpc/svcsock.h> #include <linux/lockd/lockd.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/gss_api.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/svc.h> #include <linux/module.h> #include <linux/fsnotify.h> #include <linux/nfslocalio.h> #include "idmap.h" #include "nfsd.h" #include "cache.h" #include "state.h" #include "netns.h" #include "pnfs.h" #include "filecache.h" #include "trace.h" #include "netlink.h" /* * We have a single directory with several nodes in it. */ enum { NFSD_Root = 1, NFSD_List, NFSD_Export_Stats, NFSD_Export_features, NFSD_Fh, NFSD_FO_UnlockIP, NFSD_FO_UnlockFS, NFSD_Threads, NFSD_Pool_Threads, NFSD_Pool_Stats, NFSD_Reply_Cache_Stats, NFSD_Versions, NFSD_Ports, NFSD_MaxBlkSize, NFSD_Filecache, NFSD_Leasetime, NFSD_Gracetime, NFSD_RecoveryDir, NFSD_V4EndGrace, NFSD_MaxReserved }; /* * write() for these nodes. */ static ssize_t write_filehandle(struct file *file, char *buf, size_t size); static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size); static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size); static ssize_t write_threads(struct file *file, char *buf, size_t size); static ssize_t write_pool_threads(struct file *file, char *buf, size_t size); static ssize_t write_versions(struct file *file, char *buf, size_t size); static ssize_t write_ports(struct file *file, char *buf, size_t size); static ssize_t write_maxblksize(struct file *file, char *buf, size_t size); #ifdef CONFIG_NFSD_V4 static ssize_t write_leasetime(struct file *file, char *buf, size_t size); static ssize_t write_gracetime(struct file *file, char *buf, size_t size); #ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING static ssize_t write_recoverydir(struct file *file, char *buf, size_t size); #endif static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size); #endif static ssize_t (*const write_op[])(struct file *, char *, size_t) = { [NFSD_Fh] = write_filehandle, [NFSD_FO_UnlockIP] = write_unlock_ip, [NFSD_FO_UnlockFS] = write_unlock_fs, [NFSD_Threads] = write_threads, [NFSD_Pool_Threads] = write_pool_threads, [NFSD_Versions] = write_versions, [NFSD_Ports] = write_ports, [NFSD_MaxBlkSize] = write_maxblksize, #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = write_leasetime, [NFSD_Gracetime] = write_gracetime, #ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING [NFSD_RecoveryDir] = write_recoverydir, #endif [NFSD_V4EndGrace] = write_v4_end_grace, #endif }; static ssize_t nfsctl_transaction_write(struct file *file, const char __user *buf, size_t size, loff_t *pos) { ino_t ino = file_inode(file)->i_ino; char *data; ssize_t rv; if (ino >= ARRAY_SIZE(write_op) || !write_op[ino]) return -EINVAL; data = simple_transaction_get(file, buf, size); if (IS_ERR(data)) return PTR_ERR(data); rv = write_op[ino](file, data, size); if (rv < 0) return rv; simple_transaction_set(file, rv); return size; } static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) { if (! file->private_data) { /* An attempt to read a transaction file without writing * causes a 0-byte write so that the file can return * state information */ ssize_t rv = nfsctl_transaction_write(file, buf, 0, pos); if (rv < 0) return rv; } return simple_transaction_read(file, buf, size, pos); } static const struct file_operations transaction_ops = { .write = nfsctl_transaction_write, .read = nfsctl_transaction_read, .release = simple_transaction_release, .llseek = default_llseek, }; static int exports_net_open(struct net *net, struct file *file) { int err; struct seq_file *seq; struct nfsd_net *nn = net_generic(net, nfsd_net_id); err = seq_open(file, &nfs_exports_op); if (err) return err; seq = file->private_data; seq->private = nn->svc_export_cache; return 0; } static int exports_nfsd_open(struct inode *inode, struct file *file) { return exports_net_open(inode->i_sb->s_fs_info, file); } static const struct file_operations exports_nfsd_operations = { .open = exports_nfsd_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static int export_features_show(struct seq_file *m, void *v) { seq_printf(m, "0x%x 0x%x\n", NFSEXP_ALLFLAGS, NFSEXP_SECINFO_FLAGS); return 0; } DEFINE_SHOW_ATTRIBUTE(export_features); static int nfsd_pool_stats_open(struct inode *inode, struct file *file) { struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id); return svc_pool_stats_open(&nn->nfsd_info, file); } static const struct file_operations pool_stats_operations = { .open = nfsd_pool_stats_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats); DEFINE_SHOW_ATTRIBUTE(nfsd_file_cache_stats); /*----------------------------------------------------------------------------*/ /* * payload - write methods */ static inline struct net *netns(struct file *file) { return file_inode(file)->i_sb->s_fs_info; } /* * write_unlock_ip - Release all locks used by a client * * Experimental. * * Input: * buf: '\n'-terminated C string containing a * presentation format IP address * size: length of C string in @buf * Output: * On success: returns zero if all specified locks were released; * returns one if one or more locks were not released * On error: return code is negative errno value */ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) { struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; size_t salen = sizeof(address); char *fo_path; struct net *net = netns(file); /* sanity check */ if (size == 0) return -EINVAL; if (buf[size-1] != '\n') return -EINVAL; fo_path = buf; if (qword_get(&buf, fo_path, size) < 0) return -EINVAL; if (rpc_pton(net, fo_path, size, sap, salen) == 0) return -EINVAL; trace_nfsd_ctl_unlock_ip(net, buf); return nlmsvc_unlock_all_by_ip(sap); } /* * write_unlock_fs - Release all locks on a local file system * * Experimental. * * Input: * buf: '\n'-terminated C string containing the * absolute pathname of a local file system * size: length of C string in @buf * Output: * On success: returns zero if all specified locks were released; * returns one if one or more locks were not released * On error: return code is negative errno value */ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) { struct path path; char *fo_path; int error; /* sanity check */ if (size == 0) return -EINVAL; if (buf[size-1] != '\n') return -EINVAL; fo_path = buf; if (qword_get(&buf, fo_path, size) < 0) return -EINVAL; trace_nfsd_ctl_unlock_fs(netns(file), fo_path); error = kern_path(fo_path, 0, &path); if (error) return error; /* * XXX: Needs better sanity checking. Otherwise we could end up * releasing locks on the wrong file system. * * For example: * 1. Does the path refer to a directory? * 2. Is that directory a mount point, or * 3. Is that directory the root of an exported file system? */ error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); nfsd4_revoke_states(netns(file), path.dentry->d_sb); path_put(&path); return error; } /* * write_filehandle - Get a variable-length NFS file handle by path * * On input, the buffer contains a '\n'-terminated C string comprised of * three alphanumeric words separated by whitespace. The string may * contain escape sequences. * * Input: * buf: * domain: client domain name * path: export pathname * maxsize: numeric maximum size of * @buf * size: length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C * string containing a ASCII hex text version * of the NFS file handle; * return code is the size in bytes of the string * On error: return code is negative errno value */ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) { char *dname, *path; int maxsize; char *mesg = buf; int len; struct auth_domain *dom; struct knfsd_fh fh; if (size == 0) return -EINVAL; if (buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; dname = mesg; len = qword_get(&mesg, dname, size); if (len <= 0) return -EINVAL; path = dname+len+1; len = qword_get(&mesg, path, size); if (len <= 0) return -EINVAL; len = get_int(&mesg, &maxsize); if (len) return len; if (maxsize < NFS_FHSIZE) return -EINVAL; maxsize = min(maxsize, NFS3_FHSIZE); if (qword_get(&mesg, mesg, size) > 0) return -EINVAL; trace_nfsd_ctl_filehandle(netns(file), dname, path, maxsize); /* we have all the words, they are in buf.. */ dom = unix_domain_find(dname); if (!dom) return -ENOMEM; len = exp_rootfh(netns(file), dom, path, &fh, maxsize); auth_domain_put(dom); if (len) return len; mesg = buf; len = SIMPLE_TRANSACTION_LIMIT; qword_addhex(&mesg, &len, fh.fh_raw, fh.fh_size); mesg[-1] = '\n'; return mesg - buf; } /* * write_threads - Start NFSD, or report the current number of running threads * * Input: * buf: ignored * size: zero * Output: * On success: passed-in buffer filled with '\n'-terminated C * string numeric value representing the number of * running NFSD threads; * return code is the size in bytes of the string * On error: return code is zero * * OR * * Input: * buf: C string containing an unsigned * integer value representing the * number of NFSD threads to start * size: non-zero length of C string in @buf * Output: * On success: NFS service is started; * passed-in buffer filled with '\n'-terminated C * string numeric value representing the number of * running NFSD threads; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ static ssize_t write_threads(struct file *file, char *buf, size_t size) { char *mesg = buf; int rv; struct net *net = netns(file); if (size > 0) { int newthreads; rv = get_int(&mesg, &newthreads); if (rv) return rv; if (newthreads < 0) return -EINVAL; trace_nfsd_ctl_threads(net, newthreads); mutex_lock(&nfsd_mutex); rv = nfsd_svc(1, &newthreads, net, file->f_cred, NULL); mutex_unlock(&nfsd_mutex); if (rv < 0) return rv; } else rv = nfsd_nrthreads(net); return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv); } /* * write_pool_threads - Set or report the current number of threads per pool * * Input: * buf: ignored * size: zero * * OR * * Input: * buf: C string containing whitespace- * separated unsigned integer values * representing the number of NFSD * threads to start in each pool * size: non-zero length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C * string containing integer values representing the * number of NFSD threads in each pool; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) { /* if size > 0, look for an array of number of threads per node * and apply them then write out number of threads per node as reply */ char *mesg = buf; int i; int rv; int len; int npools; int *nthreads; struct net *net = netns(file); mutex_lock(&nfsd_mutex); npools = nfsd_nrpools(net); if (npools == 0) { /* * NFS is shut down. The admin can start it by * writing to the threads file but NOT the pool_threads * file, sorry. Report zero threads. */ mutex_unlock(&nfsd_mutex); strcpy(buf, "0\n"); return strlen(buf); } nthreads = kcalloc(npools, sizeof(int), GFP_KERNEL); rv = -ENOMEM; if (nthreads == NULL) goto out_free; if (size > 0) { for (i = 0; i < npools; i++) { rv = get_int(&mesg, &nthreads[i]); if (rv == -ENOENT) break; /* fewer numbers than pools */ if (rv) goto out_free; /* syntax error */ rv = -EINVAL; if (nthreads[i] < 0) goto out_free; trace_nfsd_ctl_pool_threads(net, i, nthreads[i]); } /* * There must always be a thread in pool 0; the admin * can't shut down NFS completely using pool_threads. */ if (nthreads[0] == 0) nthreads[0] = 1; rv = nfsd_set_nrthreads(i, nthreads, net); if (rv) goto out_free; } rv = nfsd_get_nrthreads(npools, nthreads, net); if (rv) goto out_free; mesg = buf; size = SIMPLE_TRANSACTION_LIMIT; for (i = 0; i < npools && size > 0; i++) { snprintf(mesg, size, "%d%c", nthreads[i], (i == npools-1 ? '\n' : ' ')); len = strlen(mesg); size -= len; mesg += len; } rv = mesg - buf; out_free: kfree(nthreads); mutex_unlock(&nfsd_mutex); return rv; } static ssize_t nfsd_print_version_support(struct nfsd_net *nn, char *buf, int remaining, const char *sep, unsigned vers, int minor) { const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u"; bool supported = !!nfsd_vers(nn, vers, NFSD_TEST); if (vers == 4 && minor >= 0 && !nfsd_minorversion(nn, minor, NFSD_TEST)) supported = false; if (minor == 0 && supported) /* * special case for backward compatability. * +4.0 is never reported, it is implied by * +4, unless -4.0 is present. */ return 0; return snprintf(buf, remaining, format, sep, supported ? '+' : '-', vers, minor); } static ssize_t __write_versions(struct file *file, char *buf, size_t size) { char *mesg = buf; char *vers, *minorp, sign; int len, num, remaining; ssize_t tlen = 0; char *sep; struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); if (size > 0) { if (nn->nfsd_serv) /* Cannot change versions without updating * nn->nfsd_serv->sv_xdrsize, and reallocing * rq_argp and rq_resp */ return -EBUSY; if (buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; trace_nfsd_ctl_version(netns(file), buf); vers = mesg; len = qword_get(&mesg, vers, size); if (len <= 0) return -EINVAL; do { enum vers_op cmd; unsigned minor; sign = *vers; if (sign == '+' || sign == '-') num = simple_strtol((vers+1), &minorp, 0); else num = simple_strtol(vers, &minorp, 0); if (*minorp == '.') { if (num != 4) return -EINVAL; if (kstrtouint(minorp+1, 0, &minor) < 0) return -EINVAL; } cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET; switch(num) { #ifdef CONFIG_NFSD_V2 case 2: #endif case 3: nfsd_vers(nn, num, cmd); break; case 4: if (*minorp == '.') { if (nfsd_minorversion(nn, minor, cmd) < 0) return -EINVAL; } else if ((cmd == NFSD_SET) != nfsd_vers(nn, num, NFSD_TEST)) { /* * Either we have +4 and no minors are enabled, * or we have -4 and at least one minor is enabled. * In either case, propagate 'cmd' to all minors. */ minor = 0; while (nfsd_minorversion(nn, minor, cmd) >= 0) minor++; } break; default: /* Ignore requests to disable non-existent versions */ if (cmd == NFSD_SET) return -EINVAL; } vers += len + 1; } while ((len = qword_get(&mesg, vers, size)) > 0); /* If all get turned off, turn them back on, as * having no versions is BAD */ nfsd_reset_versions(nn); } /* Now write current state into reply buffer */ sep = ""; remaining = SIMPLE_TRANSACTION_LIMIT; for (num=2 ; num <= 4 ; num++) { int minor; if (!nfsd_vers(nn, num, NFSD_AVAIL)) continue; minor = -1; do { len = nfsd_print_version_support(nn, buf, remaining, sep, num, minor); if (len >= remaining) goto out; remaining -= len; buf += len; tlen += len; minor++; if (len) sep = " "; } while (num == 4 && minor <= NFSD_SUPPORTED_MINOR_VERSION); } out: len = snprintf(buf, remaining, "\n"); if (len >= remaining) return -EINVAL; return tlen + len; } /* * write_versions - Set or report the available NFS protocol versions * * Input: * buf: ignored * size: zero * Output: * On success: passed-in buffer filled with '\n'-terminated C * string containing positive or negative integer * values representing the current status of each * protocol version; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value * * OR * * Input: * buf: C string containing whitespace- * separated positive or negative * integer values representing NFS * protocol versions to enable ("+n") * or disable ("-n") * size: non-zero length of C string in @buf * Output: * On success: status of zero or more protocol versions has * been updated; passed-in buffer filled with * '\n'-terminated C string containing positive * or negative integer values representing the * current status of each protocol version; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ static ssize_t write_versions(struct file *file, char *buf, size_t size) { ssize_t rv; mutex_lock(&nfsd_mutex); rv = __write_versions(file, buf, size); mutex_unlock(&nfsd_mutex); return rv; } /* * Zero-length write. Return a list of NFSD's current listener * transports. */ static ssize_t __write_ports_names(char *buf, struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (nn->nfsd_serv == NULL) return 0; return svc_xprt_names(nn->nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT); } /* * A single 'fd' number was written, in which case it must be for * a socket of a supported family/protocol, and we use it as an * nfsd listener. */ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred *cred) { char *mesg = buf; int fd, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; err = get_int(&mesg, &fd); if (err != 0 || fd < 0) return -EINVAL; trace_nfsd_ctl_ports_addfd(net, fd); err = nfsd_create_serv(net); if (err != 0) return err; serv = nn->nfsd_serv; err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks)) nfsd_destroy_serv(net); return err; } /* * A transport listener is added by writing its transport name and * a port number. */ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cred *cred) { char transport[16]; struct svc_xprt *xprt; int port, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; if (sscanf(buf, "%15s %5u", transport, &port) != 2) return -EINVAL; if (port < 1 || port > USHRT_MAX) return -EINVAL; trace_nfsd_ctl_ports_addxprt(net, transport, port); err = nfsd_create_serv(net); if (err != 0) return err; serv = nn->nfsd_serv; err = svc_xprt_create(serv, transport, net, PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; err = svc_xprt_create(serv, transport, net, PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; return 0; out_close: xprt = svc_find_xprt(serv, transport, net, PF_INET, port); if (xprt != NULL) { svc_xprt_close(xprt); svc_xprt_put(xprt); } out_err: if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks)) nfsd_destroy_serv(net); return err; } static ssize_t __write_ports(struct file *file, char *buf, size_t size, struct net *net) { if (size == 0) return __write_ports_names(buf, net); if (isdigit(buf[0])) return __write_ports_addfd(buf, net, file->f_cred); if (isalpha(buf[0])) return __write_ports_addxprt(buf, net, file->f_cred); return -EINVAL; } /* * write_ports - Pass a socket file descriptor or transport name to listen on * * Input: * buf: ignored * size: zero * Output: * On success: passed-in buffer filled with a '\n'-terminated C * string containing a whitespace-separated list of * named NFSD listeners; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value * * OR * * Input: * buf: C string containing an unsigned * integer value representing a bound * but unconnected socket that is to be * used as an NFSD listener; listen(3) * must be called for a SOCK_STREAM * socket, otherwise it is ignored * size: non-zero length of C string in @buf * Output: * On success: NFS service is started; * passed-in buffer filled with a '\n'-terminated C * string containing a unique alphanumeric name of * the listener; * return code is the size in bytes of the string * On error: return code is a negative errno value * * OR * * Input: * buf: C string containing a transport * name and an unsigned integer value * representing the port to listen on, * separated by whitespace * size: non-zero length of C string in @buf * Output: * On success: returns zero; NFS service is started * On error: return code is a negative errno value */ static ssize_t write_ports(struct file *file, char *buf, size_t size) { ssize_t rv; mutex_lock(&nfsd_mutex); rv = __write_ports(file, buf, size, netns(file)); mutex_unlock(&nfsd_mutex); return rv; } int nfsd_max_blksize; /* * write_maxblksize - Set or report the current NFS blksize * * Input: * buf: ignored * size: zero * * OR * * Input: * buf: C string containing an unsigned * integer value representing the new * NFS blksize * size: non-zero length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C string * containing numeric value of the current NFS blksize * setting; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) { char *mesg = buf; struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); if (size > 0) { int bsize; int rv = get_int(&mesg, &bsize); if (rv) return rv; trace_nfsd_ctl_maxblksize(netns(file), bsize); /* force bsize into allowed range and * required alignment. */ bsize = max_t(int, bsize, 1024); bsize = min_t(int, bsize, NFSSVC_MAXBLKSIZE); bsize &= ~(1024-1); mutex_lock(&nfsd_mutex); if (nn->nfsd_serv) { mutex_unlock(&nfsd_mutex); return -EBUSY; } nfsd_max_blksize = bsize; mutex_unlock(&nfsd_mutex); } return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", nfsd_max_blksize); } #ifdef CONFIG_NFSD_V4 static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, time64_t *time, struct nfsd_net *nn) { struct dentry *dentry = file_dentry(file); char *mesg = buf; int rv, i; if (size > 0) { if (nn->nfsd_serv) return -EBUSY; rv = get_int(&mesg, &i); if (rv) return rv; trace_nfsd_ctl_time(netns(file), dentry->d_name.name, dentry->d_name.len, i); /* * Some sanity checking. We don't have a reason for * these particular numbers, but problems with the * extremes are: * - Too short: the briefest network outage may * cause clients to lose all their locks. Also, * the frequent polling may be wasteful. * - Too long: do you really want reboot recovery * to take more than an hour? Or to make other * clients wait an hour before being able to * revoke a dead client's locks? */ if (i < 10 || i > 3600) return -EINVAL; *time = i; } return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%lld\n", *time); } static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, time64_t *time, struct nfsd_net *nn) { ssize_t rv; mutex_lock(&nfsd_mutex); rv = __nfsd4_write_time(file, buf, size, time, nn); mutex_unlock(&nfsd_mutex); return rv; } /* * write_leasetime - Set or report the current NFSv4 lease time * * Input: * buf: ignored * size: zero * * OR * * Input: * buf: C string containing an unsigned * integer value representing the new * NFSv4 lease expiry time * size: non-zero length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C * string containing unsigned integer value of the * current lease expiry time; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) { struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn); } /* * write_gracetime - Set or report current NFSv4 grace period time * * As above, but sets the time of the NFSv4 grace period. * * Note this should never be set to less than the *previous* * lease-period time, but we don't try to enforce this. (In the common * case (a new boot), we don't know what the previous lease time was * anyway.) */ static ssize_t write_gracetime(struct file *file, char *buf, size_t size) { struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn); } #ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, struct nfsd_net *nn) { char *mesg = buf; char *recdir; int len, status; if (size > 0) { if (nn->nfsd_serv) return -EBUSY; if (size > PATH_MAX || buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; recdir = mesg; len = qword_get(&mesg, recdir, size); if (len <= 0) return -EINVAL; trace_nfsd_ctl_recoverydir(netns(file), recdir); status = nfs4_reset_recoverydir(recdir); if (status) return status; } return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%s\n", nfs4_recoverydir()); } /* * write_recoverydir - Set or report the pathname of the recovery directory * * Input: * buf: ignored * size: zero * * OR * * Input: * buf: C string containing the pathname * of the directory on a local file * system containing permanent NFSv4 * recovery data * size: non-zero length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C string * containing the current recovery pathname setting; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) { ssize_t rv; struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); mutex_lock(&nfsd_mutex); rv = __write_recoverydir(file, buf, size, nn); mutex_unlock(&nfsd_mutex); return rv; } #endif /* * write_v4_end_grace - release grace period for nfsd's v4.x lock manager * * Input: * buf: ignored * size: zero * OR * * Input: * buf: any value * size: non-zero length of C string in @buf * Output: * passed-in buffer filled with "Y" or "N" with a newline * and NULL-terminated C string. This indicates whether * the grace period has ended in the current net * namespace. Return code is the size in bytes of the * string. Writing a string that starts with 'Y', 'y', or * '1' to the file will end the grace period for nfsd's v4 * lock manager. */ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) { struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); if (size > 0) { switch(buf[0]) { case 'Y': case 'y': case '1': if (!nn->nfsd_serv) return -EBUSY; trace_nfsd_end_grace(netns(file)); nfsd4_end_grace(nn); break; default: return -EINVAL; } } return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%c\n", nn->grace_ended ? 'Y' : 'N'); } #endif /*----------------------------------------------------------------------------*/ /* * populating the filesystem. */ /* Basically copying rpc_get_inode. */ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (!inode) return NULL; /* Following advice from simple_fill_super documentation: */ inode->i_ino = iunique(sb, NFSD_MaxReserved); inode->i_mode = mode; simple_inode_init_ts(inode); switch (mode & S_IFMT) { case S_IFDIR: inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); break; case S_IFLNK: inode->i_op = &simple_symlink_inode_operations; break; default: break; } return inode; } static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, struct nfsdfs_client *ncl) { struct inode *inode; inode = nfsd_get_inode(dir->i_sb, mode); if (!inode) return -ENOMEM; if (ncl) { inode->i_private = ncl; kref_get(&ncl->cl_ref); } d_add(dentry, inode); inc_nlink(dir); fsnotify_mkdir(dir, dentry); return 0; } static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *ncl, char *name) { struct inode *dir = parent->d_inode; struct dentry *dentry; int ret = -ENOMEM; inode_lock(dir); dentry = d_alloc_name(parent, name); if (!dentry) goto out_err; ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600, ncl); if (ret) goto out_err; out: inode_unlock(dir); return dentry; out_err: dput(dentry); dentry = ERR_PTR(ret); goto out; } #if IS_ENABLED(CONFIG_SUNRPC_GSS) static int __nfsd_symlink(struct inode *dir, struct dentry *dentry, umode_t mode, const char *content) { struct inode *inode; inode = nfsd_get_inode(dir->i_sb, mode); if (!inode) return -ENOMEM; inode->i_link = (char *)content; inode->i_size = strlen(content); d_add(dentry, inode); inc_nlink(dir); fsnotify_create(dir, dentry); return 0; } /* * @content is assumed to be a NUL-terminated string that lives * longer than the symlink itself. */ static void _nfsd_symlink(struct dentry *parent, const char *name, const char *content) { struct inode *dir = parent->d_inode; struct dentry *dentry; int ret; inode_lock(dir); dentry = d_alloc_name(parent, name); if (!dentry) goto out; ret = __nfsd_symlink(d_inode(parent), dentry, S_IFLNK | 0777, content); if (ret) dput(dentry); out: inode_unlock(dir); } #else static inline void _nfsd_symlink(struct dentry *parent, const char *name, const char *content) { } #endif static void clear_ncl(struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct nfsdfs_client *ncl = inode->i_private; spin_lock(&inode->i_lock); inode->i_private = NULL; spin_unlock(&inode->i_lock); kref_put(&ncl->cl_ref, ncl->cl_release); } struct nfsdfs_client *get_nfsdfs_client(struct inode *inode) { struct nfsdfs_client *nc; spin_lock(&inode->i_lock); nc = inode->i_private; if (nc) kref_get(&nc->cl_ref); spin_unlock(&inode->i_lock); return nc; } /* XXX: cut'n'paste from simple_fill_super; figure out if we could share * code instead. */ static int nfsdfs_create_files(struct dentry *root, const struct tree_descr *files, struct nfsdfs_client *ncl, struct dentry **fdentries) { struct inode *dir = d_inode(root); struct inode *inode; struct dentry *dentry; int i; inode_lock(dir); for (i = 0; files->name && files->name[0]; i++, files++) { dentry = d_alloc_name(root, files->name); if (!dentry) goto out; inode = nfsd_get_inode(d_inode(root)->i_sb, S_IFREG | files->mode); if (!inode) { dput(dentry); goto out; } kref_get(&ncl->cl_ref); inode->i_fop = files->ops; inode->i_private = ncl; d_add(dentry, inode); fsnotify_create(dir, dentry); if (fdentries) fdentries[i] = dentry; } inode_unlock(dir); return 0; out: inode_unlock(dir); return -ENOMEM; } /* on success, returns positive number unique to that client. */ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, struct nfsdfs_client *ncl, u32 id, const struct tree_descr *files, struct dentry **fdentries) { struct dentry *dentry; char name[11]; int ret; sprintf(name, "%u", id); dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name); if (IS_ERR(dentry)) /* XXX: tossing errors? */ return NULL; ret = nfsdfs_create_files(dentry, files, ncl, fdentries); if (ret) { nfsd_client_rmdir(dentry); return NULL; } return dentry; } /* Taken from __rpc_rmdir: */ void nfsd_client_rmdir(struct dentry *dentry) { simple_recursive_removal(dentry, clear_ncl); } static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) { struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, nfsd_net_id); struct dentry *dentry; int ret; static const struct tree_descr nfsd_files[] = { [NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO}, /* Per-export io stats use same ops as exports file */ [NFSD_Export_Stats] = {"export_stats", &exports_nfsd_operations, S_IRUGO}, [NFSD_Export_features] = {"export_features", &export_features_fops, S_IRUGO}, [NFSD_FO_UnlockIP] = {"unlock_ip", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_FO_UnlockFS] = {"unlock_filesystem", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Fh] = {"filehandle", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO}, [NFSD_Reply_Cache_Stats] = {"reply_cache_stats", &nfsd_reply_cache_stats_fops, S_IRUGO}, [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO}, #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR}, #ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING [NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR}, #endif [NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO}, #endif /* last one */ {""} }; ret = simple_fill_super(sb, 0x6e667364, nfsd_files); if (ret) return ret; _nfsd_symlink(sb->s_root, "supported_krb5_enctypes", "/proc/net/rpc/gss_krb5_enctypes"); dentry = nfsd_mkdir(sb->s_root, NULL, "clients"); if (IS_ERR(dentry)) return PTR_ERR(dentry); nn->nfsd_client_dir = dentry; return 0; } static int nfsd_fs_get_tree(struct fs_context *fc) { return get_tree_keyed(fc, nfsd_fill_super, get_net(fc->net_ns)); } static void nfsd_fs_free_fc(struct fs_context *fc) { if (fc->s_fs_info) put_net(fc->s_fs_info); } static const struct fs_context_operations nfsd_fs_context_ops = { .free = nfsd_fs_free_fc, .get_tree = nfsd_fs_get_tree, }; static int nfsd_init_fs_context(struct fs_context *fc) { put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(fc->net_ns->user_ns); fc->ops = &nfsd_fs_context_ops; return 0; } static void nfsd_umount(struct super_block *sb) { struct net *net = sb->s_fs_info; nfsd_shutdown_threads(net); kill_litter_super(sb); put_net(net); } static struct file_system_type nfsd_fs_type = { .owner = THIS_MODULE, .name = "nfsd", .init_fs_context = nfsd_init_fs_context, .kill_sb = nfsd_umount, }; MODULE_ALIAS_FS("nfsd"); #ifdef CONFIG_PROC_FS static int exports_proc_open(struct inode *inode, struct file *file) { return exports_net_open(current->nsproxy->net_ns, file); } static const struct proc_ops exports_proc_ops = { .proc_open = exports_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, }; static int create_proc_exports_entry(void) { struct proc_dir_entry *entry; entry = proc_mkdir("fs/nfs", NULL); if (!entry) return -ENOMEM; entry = proc_create("exports", 0, entry, &exports_proc_ops); if (!entry) { remove_proc_entry("fs/nfs", NULL); return -ENOMEM; } return 0; } #else /* CONFIG_PROC_FS */ static int create_proc_exports_entry(void) { return 0; } #endif unsigned int nfsd_net_id; static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, struct netlink_callback *cb, struct nfsd_genl_rqstp *rqstp) { void *hdr; u32 i; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &nfsd_nl_family, 0, NFSD_CMD_RPC_STATUS_GET); if (!hdr) return -ENOBUFS; if (nla_put_be32(skb, NFSD_A_RPC_STATUS_XID, rqstp->rq_xid) || nla_put_u32(skb, NFSD_A_RPC_STATUS_FLAGS, rqstp->rq_flags) || nla_put_u32(skb, NFSD_A_RPC_STATUS_PROG, rqstp->rq_prog) || nla_put_u32(skb, NFSD_A_RPC_STATUS_PROC, rqstp->rq_proc) || nla_put_u8(skb, NFSD_A_RPC_STATUS_VERSION, rqstp->rq_vers) || nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME, ktime_to_us(rqstp->rq_stime), NFSD_A_RPC_STATUS_PAD)) return -ENOBUFS; switch (rqstp->rq_saddr.sa_family) { case AF_INET: { const struct sockaddr_in *s_in, *d_in; s_in = (const struct sockaddr_in *)&rqstp->rq_saddr; d_in = (const struct sockaddr_in *)&rqstp->rq_daddr; if (nla_put_in_addr(skb, NFSD_A_RPC_STATUS_SADDR4, s_in->sin_addr.s_addr) || nla_put_in_addr(skb, NFSD_A_RPC_STATUS_DADDR4, d_in->sin_addr.s_addr) || nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT, s_in->sin_port) || nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, d_in->sin_port)) return -ENOBUFS; break; } case AF_INET6: { const struct sockaddr_in6 *s_in, *d_in; s_in = (const struct sockaddr_in6 *)&rqstp->rq_saddr; d_in = (const struct sockaddr_in6 *)&rqstp->rq_daddr; if (nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_SADDR6, &s_in->sin6_addr) || nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_DADDR6, &d_in->sin6_addr) || nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT, s_in->sin6_port) || nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, d_in->sin6_port)) return -ENOBUFS; break; } } for (i = 0; i < rqstp->rq_opcnt; i++) if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS, rqstp->rq_opnum[i])) return -ENOBUFS; genlmsg_end(skb, hdr); return 0; } /** * nfsd_nl_rpc_status_get_dumpit - Handle rpc_status_get dumpit * @skb: reply buffer * @cb: netlink metadata and command arguments * * Returns the size of the reply or a negative errno. */ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { int i, ret, rqstp_index = 0; struct nfsd_net *nn; mutex_lock(&nfsd_mutex); nn = net_generic(sock_net(skb->sk), nfsd_net_id); if (!nn->nfsd_serv) { ret = -ENODEV; goto out_unlock; } rcu_read_lock(); for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) { struct svc_rqst *rqstp; if (i < cb->args[0]) /* already consumed */ continue; rqstp_index = 0; list_for_each_entry_rcu(rqstp, &nn->nfsd_serv->sv_pools[i].sp_all_threads, rq_all) { struct nfsd_genl_rqstp genl_rqstp; unsigned int status_counter; if (rqstp_index++ < cb->args[1]) /* already consumed */ continue; /* * Acquire rq_status_counter before parsing the rqst * fields. rq_status_counter is set to an odd value in * order to notify the consumers the rqstp fields are * meaningful. */ status_counter = smp_load_acquire(&rqstp->rq_status_counter); if (!(status_counter & 1)) continue; genl_rqstp.rq_xid = rqstp->rq_xid; genl_rqstp.rq_flags = rqstp->rq_flags; genl_rqstp.rq_vers = rqstp->rq_vers; genl_rqstp.rq_prog = rqstp->rq_prog; genl_rqstp.rq_proc = rqstp->rq_proc; genl_rqstp.rq_stime = rqstp->rq_stime; genl_rqstp.rq_opcnt = 0; memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp), sizeof(struct sockaddr)); memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp), sizeof(struct sockaddr)); #ifdef CONFIG_NFSD_V4 if (rqstp->rq_vers == NFS4_VERSION && rqstp->rq_proc == NFSPROC4_COMPOUND) { /* NFSv4 compound */ struct nfsd4_compoundargs *args; int j; args = rqstp->rq_argp; genl_rqstp.rq_opcnt = args->opcnt; for (j = 0; j < genl_rqstp.rq_opcnt; j++) genl_rqstp.rq_opnum[j] = args->ops[j].opnum; } #endif /* CONFIG_NFSD_V4 */ /* * Acquire rq_status_counter before reporting the rqst * fields to the user. */ if (smp_load_acquire(&rqstp->rq_status_counter) != status_counter) continue; ret = nfsd_genl_rpc_status_compose_msg(skb, cb, &genl_rqstp); if (ret) goto out; } } cb->args[0] = i; cb->args[1] = rqstp_index; ret = skb->len; out: rcu_read_unlock(); out_unlock: mutex_unlock(&nfsd_mutex); return ret; } /** * nfsd_nl_threads_set_doit - set the number of running threads * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info) { int *nthreads, count = 0, nrpools, i, ret = -EOPNOTSUPP, rem; struct net *net = genl_info_net(info); struct nfsd_net *nn = net_generic(net, nfsd_net_id); const struct nlattr *attr; const char *scope = NULL; if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_THREADS)) return -EINVAL; /* count number of SERVER_THREADS values */ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { if (nla_type(attr) == NFSD_A_SERVER_THREADS) count++; } mutex_lock(&nfsd_mutex); nrpools = max(count, nfsd_nrpools(net)); nthreads = kcalloc(nrpools, sizeof(int), GFP_KERNEL); if (!nthreads) { ret = -ENOMEM; goto out_unlock; } i = 0; nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { if (nla_type(attr) == NFSD_A_SERVER_THREADS) { nthreads[i++] = nla_get_u32(attr); if (i >= nrpools) break; } } if (info->attrs[NFSD_A_SERVER_GRACETIME] || info->attrs[NFSD_A_SERVER_LEASETIME] || info->attrs[NFSD_A_SERVER_SCOPE]) { ret = -EBUSY; if (nn->nfsd_serv && nn->nfsd_serv->sv_nrthreads) goto out_unlock; ret = -EINVAL; attr = info->attrs[NFSD_A_SERVER_GRACETIME]; if (attr) { u32 gracetime = nla_get_u32(attr); if (gracetime < 10 || gracetime > 3600) goto out_unlock; nn->nfsd4_grace = gracetime; } attr = info->attrs[NFSD_A_SERVER_LEASETIME]; if (attr) { u32 leasetime = nla_get_u32(attr); if (leasetime < 10 || leasetime > 3600) goto out_unlock; nn->nfsd4_lease = leasetime; } attr = info->attrs[NFSD_A_SERVER_SCOPE]; if (attr) scope = nla_data(attr); } ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope); if (ret > 0) ret = 0; out_unlock: mutex_unlock(&nfsd_mutex); kfree(nthreads); return ret; } /** * nfsd_nl_threads_get_doit - get the number of running threads * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct nfsd_net *nn = net_generic(net, nfsd_net_id); void *hdr; int err; skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; hdr = genlmsg_iput(skb, info); if (!hdr) { err = -EMSGSIZE; goto err_free_msg; } mutex_lock(&nfsd_mutex); err = nla_put_u32(skb, NFSD_A_SERVER_GRACETIME, nn->nfsd4_grace) || nla_put_u32(skb, NFSD_A_SERVER_LEASETIME, nn->nfsd4_lease) || nla_put_string(skb, NFSD_A_SERVER_SCOPE, nn->nfsd_name); if (err) goto err_unlock; if (nn->nfsd_serv) { int i; for (i = 0; i < nfsd_nrpools(net); ++i) { struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i]; err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, sp->sp_nrthreads); if (err) goto err_unlock; } } else { err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, 0); if (err) goto err_unlock; } mutex_unlock(&nfsd_mutex); genlmsg_end(skb, hdr); return genlmsg_reply(skb, info); err_unlock: mutex_unlock(&nfsd_mutex); err_free_msg: nlmsg_free(skb); return err; } /** * nfsd_nl_version_set_doit - set the nfs enabled versions * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info) { const struct nlattr *attr; struct nfsd_net *nn; int i, rem; if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_PROTO_VERSION)) return -EINVAL; mutex_lock(&nfsd_mutex); nn = net_generic(genl_info_net(info), nfsd_net_id); if (nn->nfsd_serv) { mutex_unlock(&nfsd_mutex); return -EBUSY; } /* clear current supported versions. */ nfsd_vers(nn, 2, NFSD_CLEAR); nfsd_vers(nn, 3, NFSD_CLEAR); for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) nfsd_minorversion(nn, i, NFSD_CLEAR); nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { struct nlattr *tb[NFSD_A_VERSION_MAX + 1]; u32 major, minor = 0; bool enabled; if (nla_type(attr) != NFSD_A_SERVER_PROTO_VERSION) continue; if (nla_parse_nested(tb, NFSD_A_VERSION_MAX, attr, nfsd_version_nl_policy, info->extack) < 0) continue; if (!tb[NFSD_A_VERSION_MAJOR]) continue; major = nla_get_u32(tb[NFSD_A_VERSION_MAJOR]); if (tb[NFSD_A_VERSION_MINOR]) minor = nla_get_u32(tb[NFSD_A_VERSION_MINOR]); enabled = nla_get_flag(tb[NFSD_A_VERSION_ENABLED]); switch (major) { case 4: nfsd_minorversion(nn, minor, enabled ? NFSD_SET : NFSD_CLEAR); break; case 3: case 2: if (!minor) nfsd_vers(nn, major, enabled ? NFSD_SET : NFSD_CLEAR); break; default: break; } } mutex_unlock(&nfsd_mutex); return 0; } /** * nfsd_nl_version_get_doit - get the enabled status for all supported nfs versions * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info) { struct nfsd_net *nn; int i, err; void *hdr; skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; hdr = genlmsg_iput(skb, info); if (!hdr) { err = -EMSGSIZE; goto err_free_msg; } mutex_lock(&nfsd_mutex); nn = net_generic(genl_info_net(info), nfsd_net_id); for (i = 2; i <= 4; i++) { int j; for (j = 0; j <= NFSD_SUPPORTED_MINOR_VERSION; j++) { struct nlattr *attr; /* Don't record any versions the kernel doesn't have * compiled in */ if (!nfsd_support_version(i)) continue; /* NFSv{2,3} does not support minor numbers */ if (i < 4 && j) continue; attr = nla_nest_start(skb, NFSD_A_SERVER_PROTO_VERSION); if (!attr) { err = -EINVAL; goto err_nfsd_unlock; } if (nla_put_u32(skb, NFSD_A_VERSION_MAJOR, i) || nla_put_u32(skb, NFSD_A_VERSION_MINOR, j)) { err = -EINVAL; goto err_nfsd_unlock; } /* Set the enabled flag if the version is enabled */ if (nfsd_vers(nn, i, NFSD_TEST) && (i < 4 || nfsd_minorversion(nn, j, NFSD_TEST)) && nla_put_flag(skb, NFSD_A_VERSION_ENABLED)) { err = -EINVAL; goto err_nfsd_unlock; } nla_nest_end(skb, attr); } } mutex_unlock(&nfsd_mutex); genlmsg_end(skb, hdr); return genlmsg_reply(skb, info); err_nfsd_unlock: mutex_unlock(&nfsd_mutex); err_free_msg: nlmsg_free(skb); return err; } /** * nfsd_nl_listener_set_doit - set the nfs running sockets * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct svc_xprt *xprt, *tmp; const struct nlattr *attr; struct svc_serv *serv; LIST_HEAD(permsocks); struct nfsd_net *nn; bool delete = false; int err, rem; mutex_lock(&nfsd_mutex); err = nfsd_create_serv(net); if (err) { mutex_unlock(&nfsd_mutex); return err; } nn = net_generic(net, nfsd_net_id); serv = nn->nfsd_serv; spin_lock_bh(&serv->sv_lock); /* Move all of the old listener sockets to a temp list */ list_splice_init(&serv->sv_permsocks, &permsocks); /* * Walk the list of server_socks from userland and move any that match * back to sv_permsocks */ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; const char *xcl_name; struct sockaddr *sa; if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR) continue; if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) continue; if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) continue; xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); sa = nla_data(tb[NFSD_A_SOCK_ADDR]); /* Put back any matching sockets */ list_for_each_entry_safe(xprt, tmp, &permsocks, xpt_list) { /* This shouldn't be possible */ if (WARN_ON_ONCE(xprt->xpt_net != net)) { list_move(&xprt->xpt_list, &serv->sv_permsocks); continue; } /* If everything matches, put it back */ if (!strcmp(xprt->xpt_class->xcl_name, xcl_name) && rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local)) { list_move(&xprt->xpt_list, &serv->sv_permsocks); break; } } } /* * If there are listener transports remaining on the permsocks list, * it means we were asked to remove a listener. */ if (!list_empty(&permsocks)) { list_splice_init(&permsocks, &serv->sv_permsocks); delete = true; } spin_unlock_bh(&serv->sv_lock); /* Do not remove listeners while there are active threads. */ if (serv->sv_nrthreads) { err = -EBUSY; goto out_unlock_mtx; } /* * Since we can't delete an arbitrary llist entry, destroy the * remaining listeners and recreate the list. */ if (delete) svc_xprt_destroy_all(serv, net); /* walk list of addrs again, open any that still don't exist */ nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) { struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; const char *xcl_name; struct sockaddr *sa; int ret; if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR) continue; if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) continue; if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) continue; xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); sa = nla_data(tb[NFSD_A_SOCK_ADDR]); xprt = svc_find_listener(serv, xcl_name, net, sa); if (xprt) { if (delete) WARN_ONCE(1, "Transport type=%s already exists\n", xcl_name); svc_xprt_put(xprt); continue; } ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0, get_current_cred()); /* always save the latest error */ if (ret < 0) err = ret; } if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks)) nfsd_destroy_serv(net); out_unlock_mtx: mutex_unlock(&nfsd_mutex); return err; } /** * nfsd_nl_listener_get_doit - get the nfs running listeners * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info) { struct svc_xprt *xprt; struct svc_serv *serv; struct nfsd_net *nn; void *hdr; int err; skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; hdr = genlmsg_iput(skb, info); if (!hdr) { err = -EMSGSIZE; goto err_free_msg; } mutex_lock(&nfsd_mutex); nn = net_generic(genl_info_net(info), nfsd_net_id); /* no nfs server? Just send empty socket list */ if (!nn->nfsd_serv) goto out_unlock_mtx; serv = nn->nfsd_serv; spin_lock_bh(&serv->sv_lock); list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) { struct nlattr *attr; attr = nla_nest_start(skb, NFSD_A_SERVER_SOCK_ADDR); if (!attr) { err = -EINVAL; goto err_serv_unlock; } if (nla_put_string(skb, NFSD_A_SOCK_TRANSPORT_NAME, xprt->xpt_class->xcl_name) || nla_put(skb, NFSD_A_SOCK_ADDR, sizeof(struct sockaddr_storage), &xprt->xpt_local)) { err = -EINVAL; goto err_serv_unlock; } nla_nest_end(skb, attr); } spin_unlock_bh(&serv->sv_lock); out_unlock_mtx: mutex_unlock(&nfsd_mutex); genlmsg_end(skb, hdr); return genlmsg_reply(skb, info); err_serv_unlock: spin_unlock_bh(&serv->sv_lock); mutex_unlock(&nfsd_mutex); err_free_msg: nlmsg_free(skb); return err; } /** * nfsd_nl_pool_mode_set_doit - set the number of running threads * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info) { const struct nlattr *attr; if (GENL_REQ_ATTR_CHECK(info, NFSD_A_POOL_MODE_MODE)) return -EINVAL; attr = info->attrs[NFSD_A_POOL_MODE_MODE]; return sunrpc_set_pool_mode(nla_data(attr)); } /** * nfsd_nl_pool_mode_get_doit - get info about pool_mode * @skb: reply buffer * @info: netlink metadata and command arguments * * Return 0 on success or a negative errno. */ int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); char buf[16]; void *hdr; int err; if (sunrpc_get_pool_mode(buf, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) return -ERANGE; skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; err = -EMSGSIZE; hdr = genlmsg_iput(skb, info); if (!hdr) goto err_free_msg; err = nla_put_string(skb, NFSD_A_POOL_MODE_MODE, buf) | nla_put_u32(skb, NFSD_A_POOL_MODE_NPOOLS, nfsd_nrpools(net)); if (err) goto err_free_msg; genlmsg_end(skb, hdr); return genlmsg_reply(skb, info); err_free_msg: nlmsg_free(skb); return err; } /** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace * * This information stays around as long as the network namespace is * alive whether or not there is an NFSD instance running in the * namespace. * * Returns zero on success, or a negative errno otherwise. */ static __net_init int nfsd_net_init(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int retval; int i; retval = nfsd_export_init(net); if (retval) goto out_export_error; retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; retval = percpu_counter_init_many(nn->counter, 0, GFP_KERNEL, NFSD_STATS_COUNTERS_NUM); if (retval) goto out_repcache_error; memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats)); nn->nfsd_svcstats.program = &nfsd_programs[0]; if (!nfsd_proc_stat_init(net)) { retval = -ENOMEM; goto out_proc_error; } for (i = 0; i < sizeof(nn->nfsd_versions); i++) nn->nfsd_versions[i] = nfsd_support_version(i); for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++) nn->nfsd4_minorversions[i] = nfsd_support_version(4); nn->nfsd_info.mutex = &nfsd_mutex; nn->nfsd_serv = NULL; nfsd4_init_leases_net(nn); get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); #if IS_ENABLED(CONFIG_NFS_LOCALIO) spin_lock_init(&nn->local_clients_lock); INIT_LIST_HEAD(&nn->local_clients); #endif return 0; out_proc_error: percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM); out_repcache_error: nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); out_export_error: return retval; } #if IS_ENABLED(CONFIG_NFS_LOCALIO) /** * nfsd_net_pre_exit - Disconnect localio clients from net namespace * @net: a network namespace that is about to be destroyed * * This invalidates ->net pointers held by localio clients * while they can still safely access nn->counter. */ static __net_exit void nfsd_net_pre_exit(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); nfs_localio_invalidate_clients(&nn->local_clients, &nn->local_clients_lock); } #endif /** * nfsd_net_exit - Release the nfsd_net portion of a net namespace * @net: a network namespace that is about to be destroyed * */ static __net_exit void nfsd_net_exit(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); nfsd_proc_stat_shutdown(net); percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); } static struct pernet_operations nfsd_net_ops = { .init = nfsd_net_init, #if IS_ENABLED(CONFIG_NFS_LOCALIO) .pre_exit = nfsd_net_pre_exit, #endif .exit = nfsd_net_exit, .id = &nfsd_net_id, .size = sizeof(struct nfsd_net), }; static int __init init_nfsd(void) { int retval; retval = nfsd4_init_slabs(); if (retval) return retval; retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; retval = nfsd_drc_slab_create(); if (retval) goto out_free_pnfs; nfsd_lockd_init(); /* lockd->nfsd callbacks */ retval = create_proc_exports_entry(); if (retval) goto out_free_lockd; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) goto out_free_exports; retval = register_cld_notifier(); if (retval) goto out_free_subsys; retval = nfsd4_create_laundry_wq(); if (retval) goto out_free_cld; retval = register_filesystem(&nfsd_fs_type); if (retval) goto out_free_all; retval = genl_register_family(&nfsd_nl_family); if (retval) goto out_free_all; nfsd_localio_ops_init(); return 0; out_free_all: nfsd4_destroy_laundry_wq(); out_free_cld: unregister_cld_notifier(); out_free_subsys: unregister_pernet_subsys(&nfsd_net_ops); out_free_exports: remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); out_free_lockd: nfsd_lockd_shutdown(); nfsd_drc_slab_free(); out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); return retval; } static void __exit exit_nfsd(void) { genl_unregister_family(&nfsd_nl_family); unregister_filesystem(&nfsd_fs_type); nfsd4_destroy_laundry_wq(); unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); nfsd_lockd_shutdown(); nfsd4_free_slabs(); nfsd4_exit_pnfs(); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); MODULE_DESCRIPTION("In-kernel NFS server"); MODULE_LICENSE("GPL"); module_init(init_nfsd) module_exit(exit_nfsd) |
| 2 2 1 1 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* GTP according to GSM TS 09.60 / 3GPP TS 29.060 * * (C) 2012-2014 by sysmocom - s.f.m.c. GmbH * (C) 2016 by Pablo Neira Ayuso <pablo@netfilter.org> * * Author: Harald Welte <hwelte@sysmocom.de> * Pablo Neira Ayuso <pablo@netfilter.org> * Andreas Schultz <aschultz@travelping.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/udp.h> #include <linux/rculist.h> #include <linux/jhash.h> #include <linux/if_tunnel.h> #include <linux/net.h> #include <linux/file.h> #include <linux/gtp.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/inet_dscp.h> #include <net/inet_sock.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/genetlink.h> #include <net/netns/generic.h> #include <net/gtp.h> /* An active session for the subscriber. */ struct pdp_ctx { struct hlist_node hlist_tid; struct hlist_node hlist_addr; union { struct { u64 tid; u16 flow; } v0; struct { u32 i_tei; u32 o_tei; } v1; } u; u8 gtp_version; u16 af; union { struct in_addr addr; struct in6_addr addr6; } ms; union { struct in_addr addr; struct in6_addr addr6; } peer; struct sock *sk; struct net_device *dev; atomic_t tx_seq; struct rcu_head rcu_head; }; /* One instance of the GTP device. */ struct gtp_dev { struct list_head list; struct sock *sk0; struct sock *sk1u; u8 sk_created; struct net_device *dev; struct net *net; unsigned int role; unsigned int hash_size; struct hlist_head *tid_hash; struct hlist_head *addr_hash; u8 restart_count; }; struct echo_info { u16 af; u8 gtp_version; union { struct in_addr addr; } ms; union { struct in_addr addr; } peer; }; static unsigned int gtp_net_id __read_mostly; struct gtp_net { struct list_head gtp_dev_list; }; static u32 gtp_h_initval; static struct genl_family gtp_genl_family; enum gtp_multicast_groups { GTP_GENL_MCGRP, }; static const struct genl_multicast_group gtp_genl_mcgrps[] = { [GTP_GENL_MCGRP] = { .name = GTP_GENL_MCGRP_NAME }, }; static void pdp_context_delete(struct pdp_ctx *pctx); static inline u32 gtp0_hashfn(u64 tid) { u32 *tid32 = (u32 *) &tid; return jhash_2words(tid32[0], tid32[1], gtp_h_initval); } static inline u32 gtp1u_hashfn(u32 tid) { return jhash_1word(tid, gtp_h_initval); } static inline u32 ipv4_hashfn(__be32 ip) { return jhash_1word((__force u32)ip, gtp_h_initval); } static u32 ipv6_hashfn(const struct in6_addr *ip6) { return jhash_2words((__force u32)ip6->s6_addr32[0], (__force u32)ip6->s6_addr32[1], gtp_h_initval); } /* Resolve a PDP context structure based on the 64bit TID. */ static struct pdp_ctx *gtp0_pdp_find(struct gtp_dev *gtp, u64 tid, u16 family) { struct hlist_head *head; struct pdp_ctx *pdp; head = >p->tid_hash[gtp0_hashfn(tid) % gtp->hash_size]; hlist_for_each_entry_rcu(pdp, head, hlist_tid) { if (pdp->af == family && pdp->gtp_version == GTP_V0 && pdp->u.v0.tid == tid) return pdp; } return NULL; } /* Resolve a PDP context structure based on the 32bit TEI. */ static struct pdp_ctx *gtp1_pdp_find(struct gtp_dev *gtp, u32 tid, u16 family) { struct hlist_head *head; struct pdp_ctx *pdp; head = >p->tid_hash[gtp1u_hashfn(tid) % gtp->hash_size]; hlist_for_each_entry_rcu(pdp, head, hlist_tid) { if (pdp->af == family && pdp->gtp_version == GTP_V1 && pdp->u.v1.i_tei == tid) return pdp; } return NULL; } /* Resolve a PDP context based on IPv4 address of MS. */ static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr) { struct hlist_head *head; struct pdp_ctx *pdp; head = >p->addr_hash[ipv4_hashfn(ms_addr) % gtp->hash_size]; hlist_for_each_entry_rcu(pdp, head, hlist_addr) { if (pdp->af == AF_INET && pdp->ms.addr.s_addr == ms_addr) return pdp; } return NULL; } /* 3GPP TS 29.060: PDN Connection: the association between a MS represented by * [...] one IPv6 *prefix* and a PDN represented by an APN. * * Then, 3GPP TS 29.061, Section 11.2.1.3 says: The size of the prefix shall be * according to the maximum prefix length for a global IPv6 address as * specified in the IPv6 Addressing Architecture, see RFC 4291. * * Finally, RFC 4291 section 2.5.4 states: All Global Unicast addresses other * than those that start with binary 000 have a 64-bit interface ID field * (i.e., n + m = 64). */ static bool ipv6_pdp_addr_equal(const struct in6_addr *a, const struct in6_addr *b) { return a->s6_addr32[0] == b->s6_addr32[0] && a->s6_addr32[1] == b->s6_addr32[1]; } static struct pdp_ctx *ipv6_pdp_find(struct gtp_dev *gtp, const struct in6_addr *ms_addr) { struct hlist_head *head; struct pdp_ctx *pdp; head = >p->addr_hash[ipv6_hashfn(ms_addr) % gtp->hash_size]; hlist_for_each_entry_rcu(pdp, head, hlist_addr) { if (pdp->af == AF_INET6 && ipv6_pdp_addr_equal(&pdp->ms.addr6, ms_addr)) return pdp; } return NULL; } static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx, unsigned int hdrlen, unsigned int role) { struct iphdr *iph; if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr))) return false; iph = (struct iphdr *)(skb->data + hdrlen); if (role == GTP_ROLE_SGSN) return iph->daddr == pctx->ms.addr.s_addr; else return iph->saddr == pctx->ms.addr.s_addr; } static bool gtp_check_ms_ipv6(struct sk_buff *skb, struct pdp_ctx *pctx, unsigned int hdrlen, unsigned int role) { struct ipv6hdr *ip6h; int ret; if (!pskb_may_pull(skb, hdrlen + sizeof(struct ipv6hdr))) return false; ip6h = (struct ipv6hdr *)(skb->data + hdrlen); if ((ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL) || (ipv6_addr_type(&ip6h->daddr) & IPV6_ADDR_LINKLOCAL)) return false; if (role == GTP_ROLE_SGSN) { ret = ipv6_pdp_addr_equal(&ip6h->daddr, &pctx->ms.addr6); } else { ret = ipv6_pdp_addr_equal(&ip6h->saddr, &pctx->ms.addr6); } return ret; } /* Check if the inner IP address in this packet is assigned to any * existing mobile subscriber. */ static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx, unsigned int hdrlen, unsigned int role, __u16 inner_proto) { switch (inner_proto) { case ETH_P_IP: return gtp_check_ms_ipv4(skb, pctx, hdrlen, role); case ETH_P_IPV6: return gtp_check_ms_ipv6(skb, pctx, hdrlen, role); } return false; } static int gtp_inner_proto(struct sk_buff *skb, unsigned int hdrlen, __u16 *inner_proto) { __u8 *ip_version, _ip_version; ip_version = skb_header_pointer(skb, hdrlen, sizeof(*ip_version), &_ip_version); if (!ip_version) return -1; switch (*ip_version & 0xf0) { case 0x40: *inner_proto = ETH_P_IP; break; case 0x60: *inner_proto = ETH_P_IPV6; break; default: return -1; } return 0; } static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen, unsigned int role, __u16 inner_proto) { if (!gtp_check_ms(skb, pctx, hdrlen, role, inner_proto)) { netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); return 1; } /* Get rid of the GTP + UDP headers. */ if (iptunnel_pull_header(skb, hdrlen, htons(inner_proto), !net_eq(sock_net(pctx->sk), dev_net(pctx->dev)))) { pctx->dev->stats.rx_length_errors++; goto err; } netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n"); /* Now that the UDP and the GTP header have been removed, set up the * new network header. This is required by the upper layer to * calculate the transport header. */ skb_reset_network_header(skb); skb_reset_mac_header(skb); skb->dev = pctx->dev; dev_sw_netstats_rx_add(pctx->dev, skb->len); __netif_rx(skb); return 0; err: pctx->dev->stats.rx_dropped++; return -1; } static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, const struct sock *sk, __be32 daddr, __be32 saddr) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = sk->sk_bound_dev_if; fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = inet_dscp_to_dsfield(inet_sk_dscp(inet_sk(sk))); fl4->flowi4_scope = ip_sock_rt_scope(sk); fl4->flowi4_proto = sk->sk_protocol; return ip_route_output_key(sock_net(sk), fl4); } static struct rt6_info *ip6_route_output_gtp(struct net *net, struct flowi6 *fl6, const struct sock *sk, const struct in6_addr *daddr, struct in6_addr *saddr) { struct dst_entry *dst; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_oif = sk->sk_bound_dev_if; fl6->daddr = *daddr; fl6->saddr = *saddr; fl6->flowi6_proto = sk->sk_protocol; dst = ipv6_stub->ipv6_dst_lookup_flow(net, sk, fl6, NULL); if (IS_ERR(dst)) return ERR_PTR(-ENETUNREACH); return (struct rt6_info *)dst; } /* GSM TS 09.60. 7.3 * In all Path Management messages: * - TID: is not used and shall be set to 0. * - Flow Label is not used and shall be set to 0 * In signalling messages: * - number: this field is not yet used in signalling messages. * It shall be set to 255 by the sender and shall be ignored * by the receiver * Returns true if the echo req was correct, false otherwise. */ static bool gtp0_validate_echo_hdr(struct gtp0_header *gtp0) { return !(gtp0->tid || (gtp0->flags ^ 0x1e) || gtp0->number != 0xff || gtp0->flow); } /* msg_type has to be GTP_ECHO_REQ or GTP_ECHO_RSP */ static void gtp0_build_echo_msg(struct gtp0_header *hdr, __u8 msg_type) { int len_pkt, len_hdr; hdr->flags = 0x1e; /* v0, GTP-non-prime. */ hdr->type = msg_type; /* GSM TS 09.60. 7.3 In all Path Management Flow Label and TID * are not used and shall be set to 0. */ hdr->flow = 0; hdr->tid = 0; hdr->number = 0xff; hdr->spare[0] = 0xff; hdr->spare[1] = 0xff; hdr->spare[2] = 0xff; len_pkt = sizeof(struct gtp0_packet); len_hdr = sizeof(struct gtp0_header); if (msg_type == GTP_ECHO_RSP) hdr->length = htons(len_pkt - len_hdr); else hdr->length = 0; } static int gtp0_send_echo_resp_ip(struct gtp_dev *gtp, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4; struct rtable *rt; /* find route to the sender, * src address becomes dst address and vice versa. */ rt = ip4_route_output_gtp(&fl4, gtp->sk0, iph->saddr, iph->daddr); if (IS_ERR(rt)) { netdev_dbg(gtp->dev, "no route for echo response from %pI4\n", &iph->saddr); return -1; } udp_tunnel_xmit_skb(rt, gtp->sk0, skb, fl4.saddr, fl4.daddr, iph->tos, ip4_dst_hoplimit(&rt->dst), 0, htons(GTP0_PORT), htons(GTP0_PORT), !net_eq(sock_net(gtp->sk1u), dev_net(gtp->dev)), false); return 0; } static int gtp0_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) { struct gtp0_packet *gtp_pkt; struct gtp0_header *gtp0; __be16 seq; gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr)); if (!gtp0_validate_echo_hdr(gtp0)) return -1; seq = gtp0->seq; /* pull GTP and UDP headers */ skb_pull_data(skb, sizeof(struct gtp0_header) + sizeof(struct udphdr)); gtp_pkt = skb_push(skb, sizeof(struct gtp0_packet)); memset(gtp_pkt, 0, sizeof(struct gtp0_packet)); gtp0_build_echo_msg(>p_pkt->gtp0_h, GTP_ECHO_RSP); /* GSM TS 09.60. 7.3 The Sequence Number in a signalling response * message shall be copied from the signalling request message * that the GSN is replying to. */ gtp_pkt->gtp0_h.seq = seq; gtp_pkt->ie.tag = GTPIE_RECOVERY; gtp_pkt->ie.val = gtp->restart_count; switch (gtp->sk0->sk_family) { case AF_INET: if (gtp0_send_echo_resp_ip(gtp, skb) < 0) return -1; break; case AF_INET6: return -1; } return 0; } static int gtp_genl_fill_echo(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, int flags, u32 type, struct echo_info echo) { void *genlh; genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, flags, type); if (!genlh) goto failure; if (nla_put_u32(skb, GTPA_VERSION, echo.gtp_version) || nla_put_be32(skb, GTPA_PEER_ADDRESS, echo.peer.addr.s_addr) || nla_put_be32(skb, GTPA_MS_ADDRESS, echo.ms.addr.s_addr)) goto failure; genlmsg_end(skb, genlh); return 0; failure: genlmsg_cancel(skb, genlh); return -EMSGSIZE; } static void gtp0_handle_echo_resp_ip(struct sk_buff *skb, struct echo_info *echo) { struct iphdr *iph = ip_hdr(skb); echo->ms.addr.s_addr = iph->daddr; echo->peer.addr.s_addr = iph->saddr; echo->gtp_version = GTP_V0; } static int gtp0_handle_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) { struct gtp0_header *gtp0; struct echo_info echo; struct sk_buff *msg; int ret; gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr)); if (!gtp0_validate_echo_hdr(gtp0)) return -1; switch (gtp->sk0->sk_family) { case AF_INET: gtp0_handle_echo_resp_ip(skb, &echo); break; case AF_INET6: return -1; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; ret = gtp_genl_fill_echo(msg, 0, 0, 0, GTP_CMD_ECHOREQ, echo); if (ret < 0) { nlmsg_free(msg); return ret; } return genlmsg_multicast_netns(>p_genl_family, dev_net(gtp->dev), msg, 0, GTP_GENL_MCGRP, GFP_ATOMIC); } static int gtp_proto_to_family(__u16 proto) { switch (proto) { case ETH_P_IP: return AF_INET; case ETH_P_IPV6: return AF_INET6; default: WARN_ON_ONCE(1); break; } return AF_UNSPEC; } /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp0_header); struct gtp0_header *gtp0; struct pdp_ctx *pctx; __u16 inner_proto; if (!pskb_may_pull(skb, hdrlen)) return -1; gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr)); if ((gtp0->flags >> 5) != GTP_V0) return 1; /* If the sockets were created in kernel, it means that * there is no daemon running in userspace which would * handle echo request. */ if (gtp0->type == GTP_ECHO_REQ && gtp->sk_created) return gtp0_send_echo_resp(gtp, skb); if (gtp0->type == GTP_ECHO_RSP && gtp->sk_created) return gtp0_handle_echo_resp(gtp, skb); if (gtp0->type != GTP_TPDU) return 1; if (gtp_inner_proto(skb, hdrlen, &inner_proto) < 0) { netdev_dbg(gtp->dev, "GTP packet does not encapsulate an IP packet\n"); return -1; } pctx = gtp0_pdp_find(gtp, be64_to_cpu(gtp0->tid), gtp_proto_to_family(inner_proto)); if (!pctx) { netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); return 1; } return gtp_rx(pctx, skb, hdrlen, gtp->role, inner_proto); } /* msg_type has to be GTP_ECHO_REQ or GTP_ECHO_RSP */ static void gtp1u_build_echo_msg(struct gtp1_header_long *hdr, __u8 msg_type) { int len_pkt, len_hdr; /* S flag must be set to 1 */ hdr->flags = 0x32; /* v1, GTP-non-prime. */ hdr->type = msg_type; /* 3GPP TS 29.281 5.1 - TEID has to be set to 0 */ hdr->tid = 0; /* seq, npdu and next should be counted to the length of the GTP packet * that's why szie of gtp1_header should be subtracted, * not size of gtp1_header_long. */ len_hdr = sizeof(struct gtp1_header); if (msg_type == GTP_ECHO_RSP) { len_pkt = sizeof(struct gtp1u_packet); hdr->length = htons(len_pkt - len_hdr); } else { /* GTP_ECHO_REQ does not carry GTP Information Element, * the why gtp1_header_long is used here. */ len_pkt = sizeof(struct gtp1_header_long); hdr->length = htons(len_pkt - len_hdr); } } static int gtp1u_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) { struct gtp1_header_long *gtp1u; struct gtp1u_packet *gtp_pkt; struct rtable *rt; struct flowi4 fl4; struct iphdr *iph; gtp1u = (struct gtp1_header_long *)(skb->data + sizeof(struct udphdr)); /* 3GPP TS 29.281 5.1 - For the Echo Request, Echo Response, * Error Indication and Supported Extension Headers Notification * messages, the S flag shall be set to 1 and TEID shall be set to 0. */ if (!(gtp1u->flags & GTP1_F_SEQ) || gtp1u->tid) return -1; /* pull GTP and UDP headers */ skb_pull_data(skb, sizeof(struct gtp1_header_long) + sizeof(struct udphdr)); gtp_pkt = skb_push(skb, sizeof(struct gtp1u_packet)); memset(gtp_pkt, 0, sizeof(struct gtp1u_packet)); gtp1u_build_echo_msg(>p_pkt->gtp1u_h, GTP_ECHO_RSP); /* 3GPP TS 29.281 7.7.2 - The Restart Counter value in the * Recovery information element shall not be used, i.e. it shall * be set to zero by the sender and shall be ignored by the receiver. * The Recovery information element is mandatory due to backwards * compatibility reasons. */ gtp_pkt->ie.tag = GTPIE_RECOVERY; gtp_pkt->ie.val = 0; iph = ip_hdr(skb); /* find route to the sender, * src address becomes dst address and vice versa. */ rt = ip4_route_output_gtp(&fl4, gtp->sk1u, iph->saddr, iph->daddr); if (IS_ERR(rt)) { netdev_dbg(gtp->dev, "no route for echo response from %pI4\n", &iph->saddr); return -1; } udp_tunnel_xmit_skb(rt, gtp->sk1u, skb, fl4.saddr, fl4.daddr, iph->tos, ip4_dst_hoplimit(&rt->dst), 0, htons(GTP1U_PORT), htons(GTP1U_PORT), !net_eq(sock_net(gtp->sk1u), dev_net(gtp->dev)), false); return 0; } static int gtp1u_handle_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) { struct gtp1_header_long *gtp1u; struct echo_info echo; struct sk_buff *msg; struct iphdr *iph; int ret; gtp1u = (struct gtp1_header_long *)(skb->data + sizeof(struct udphdr)); /* 3GPP TS 29.281 5.1 - For the Echo Request, Echo Response, * Error Indication and Supported Extension Headers Notification * messages, the S flag shall be set to 1 and TEID shall be set to 0. */ if (!(gtp1u->flags & GTP1_F_SEQ) || gtp1u->tid) return -1; iph = ip_hdr(skb); echo.ms.addr.s_addr = iph->daddr; echo.peer.addr.s_addr = iph->saddr; echo.gtp_version = GTP_V1; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; ret = gtp_genl_fill_echo(msg, 0, 0, 0, GTP_CMD_ECHOREQ, echo); if (ret < 0) { nlmsg_free(msg); return ret; } return genlmsg_multicast_netns(>p_genl_family, dev_net(gtp->dev), msg, 0, GTP_GENL_MCGRP, GFP_ATOMIC); } static int gtp_parse_exthdrs(struct sk_buff *skb, unsigned int *hdrlen) { struct gtp_ext_hdr *gtp_exthdr, _gtp_exthdr; unsigned int offset = *hdrlen; __u8 *next_type, _next_type; /* From 29.060: "The Extension Header Length field specifies the length * of the particular Extension header in 4 octets units." * * This length field includes length field size itself (1 byte), * payload (variable length) and next type (1 byte). The extension * header is aligned to to 4 bytes. */ do { gtp_exthdr = skb_header_pointer(skb, offset, sizeof(*gtp_exthdr), &_gtp_exthdr); if (!gtp_exthdr || !gtp_exthdr->len) return -1; offset += gtp_exthdr->len * 4; /* From 29.060: "If no such Header follows, then the value of * the Next Extension Header Type shall be 0." */ next_type = skb_header_pointer(skb, offset - 1, sizeof(_next_type), &_next_type); if (!next_type) return -1; } while (*next_type != 0); *hdrlen = offset; return 0; } static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp1_header); struct gtp1_header *gtp1; struct pdp_ctx *pctx; __u16 inner_proto; if (!pskb_may_pull(skb, hdrlen)) return -1; gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); if ((gtp1->flags >> 5) != GTP_V1) return 1; /* If the sockets were created in kernel, it means that * there is no daemon running in userspace which would * handle echo request. */ if (gtp1->type == GTP_ECHO_REQ && gtp->sk_created) return gtp1u_send_echo_resp(gtp, skb); if (gtp1->type == GTP_ECHO_RSP && gtp->sk_created) return gtp1u_handle_echo_resp(gtp, skb); if (gtp1->type != GTP_TPDU) return 1; /* From 29.060: "This field shall be present if and only if any one or * more of the S, PN and E flags are set.". * * If any of the bit is set, then the remaining ones also have to be * set. */ if (gtp1->flags & GTP1_F_MASK) hdrlen += 4; /* Make sure the header is larger enough, including extensions. */ if (!pskb_may_pull(skb, hdrlen)) return -1; if (gtp_inner_proto(skb, hdrlen, &inner_proto) < 0) { netdev_dbg(gtp->dev, "GTP packet does not encapsulate an IP packet\n"); return -1; } gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid), gtp_proto_to_family(inner_proto)); if (!pctx) { netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); return 1; } if (gtp1->flags & GTP1_F_EXTHDR && gtp_parse_exthdrs(skb, &hdrlen) < 0) return -1; return gtp_rx(pctx, skb, hdrlen, gtp->role, inner_proto); } static void __gtp_encap_destroy(struct sock *sk) { struct gtp_dev *gtp; lock_sock(sk); gtp = sk->sk_user_data; if (gtp) { if (gtp->sk0 == sk) gtp->sk0 = NULL; else gtp->sk1u = NULL; WRITE_ONCE(udp_sk(sk)->encap_type, 0); rcu_assign_sk_user_data(sk, NULL); release_sock(sk); sock_put(sk); return; } release_sock(sk); } static void gtp_encap_destroy(struct sock *sk) { rtnl_lock(); __gtp_encap_destroy(sk); rtnl_unlock(); } static void gtp_encap_disable_sock(struct sock *sk) { if (!sk) return; __gtp_encap_destroy(sk); } static void gtp_encap_disable(struct gtp_dev *gtp) { if (gtp->sk_created) { udp_tunnel_sock_release(gtp->sk0->sk_socket); udp_tunnel_sock_release(gtp->sk1u->sk_socket); gtp->sk_created = false; gtp->sk0 = NULL; gtp->sk1u = NULL; } else { gtp_encap_disable_sock(gtp->sk0); gtp_encap_disable_sock(gtp->sk1u); } } /* UDP encapsulation receive handler. See net/ipv4/udp.c. * Return codes: 0: success, <0: error, >0: pass up to userspace UDP socket. */ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct gtp_dev *gtp; int ret = 0; gtp = rcu_dereference_sk_user_data(sk); if (!gtp) return 1; netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); switch (READ_ONCE(udp_sk(sk)->encap_type)) { case UDP_ENCAP_GTP0: netdev_dbg(gtp->dev, "received GTP0 packet\n"); ret = gtp0_udp_encap_recv(gtp, skb); break; case UDP_ENCAP_GTP1U: netdev_dbg(gtp->dev, "received GTP1U packet\n"); ret = gtp1u_udp_encap_recv(gtp, skb); break; default: ret = -1; /* Shouldn't happen. */ } switch (ret) { case 1: netdev_dbg(gtp->dev, "pass up to the process\n"); break; case 0: break; case -1: netdev_dbg(gtp->dev, "GTP packet has been dropped\n"); kfree_skb(skb); ret = 0; break; } return ret; } static void gtp_dev_uninit(struct net_device *dev) { struct gtp_dev *gtp = netdev_priv(dev); gtp_encap_disable(gtp); } static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) { int payload_len = skb->len; struct gtp0_header *gtp0; gtp0 = skb_push(skb, sizeof(*gtp0)); gtp0->flags = 0x1e; /* v0, GTP-non-prime. */ gtp0->type = GTP_TPDU; gtp0->length = htons(payload_len); gtp0->seq = htons((atomic_inc_return(&pctx->tx_seq) - 1) % 0xffff); gtp0->flow = htons(pctx->u.v0.flow); gtp0->number = 0xff; gtp0->spare[0] = gtp0->spare[1] = gtp0->spare[2] = 0xff; gtp0->tid = cpu_to_be64(pctx->u.v0.tid); } static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) { int payload_len = skb->len; struct gtp1_header *gtp1; gtp1 = skb_push(skb, sizeof(*gtp1)); /* Bits 8 7 6 5 4 3 2 1 * +--+--+--+--+--+--+--+--+ * |version |PT| 0| E| S|PN| * +--+--+--+--+--+--+--+--+ * 0 0 1 1 1 0 0 0 */ gtp1->flags = 0x30; /* v1, GTP-non-prime. */ gtp1->type = GTP_TPDU; gtp1->length = htons(payload_len); gtp1->tid = htonl(pctx->u.v1.o_tei); /* TODO: Support for extension header, sequence number and N-PDU. * Update the length field if any of them is available. */ } struct gtp_pktinfo { struct sock *sk; union { struct flowi4 fl4; struct flowi6 fl6; }; union { struct rtable *rt; struct rt6_info *rt6; }; struct pdp_ctx *pctx; struct net_device *dev; __u8 tos; __be16 gtph_port; }; static void gtp_push_header(struct sk_buff *skb, struct gtp_pktinfo *pktinfo) { switch (pktinfo->pctx->gtp_version) { case GTP_V0: pktinfo->gtph_port = htons(GTP0_PORT); gtp0_push_header(skb, pktinfo->pctx); break; case GTP_V1: pktinfo->gtph_port = htons(GTP1U_PORT); gtp1_push_header(skb, pktinfo->pctx); break; } } static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo, struct sock *sk, __u8 tos, struct pdp_ctx *pctx, struct rtable *rt, struct flowi4 *fl4, struct net_device *dev) { pktinfo->sk = sk; pktinfo->tos = tos; pktinfo->pctx = pctx; pktinfo->rt = rt; pktinfo->fl4 = *fl4; pktinfo->dev = dev; } static void gtp_set_pktinfo_ipv6(struct gtp_pktinfo *pktinfo, struct sock *sk, __u8 tos, struct pdp_ctx *pctx, struct rt6_info *rt6, struct flowi6 *fl6, struct net_device *dev) { pktinfo->sk = sk; pktinfo->tos = tos; pktinfo->pctx = pctx; pktinfo->rt6 = rt6; pktinfo->fl6 = *fl6; pktinfo->dev = dev; } static int gtp_build_skb_outer_ip4(struct sk_buff *skb, struct net_device *dev, struct gtp_pktinfo *pktinfo, struct pdp_ctx *pctx, __u8 tos, __be16 frag_off) { struct rtable *rt; struct flowi4 fl4; __be16 df; int mtu; rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer.addr.s_addr, inet_sk(pctx->sk)->inet_saddr); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to SSGN %pI4\n", &pctx->peer.addr.s_addr); dev->stats.tx_carrier_errors++; goto err; } if (rt->dst.dev == dev) { netdev_dbg(dev, "circular route to SSGN %pI4\n", &pctx->peer.addr.s_addr); dev->stats.collisions++; goto err_rt; } /* This is similar to tnl_update_pmtu(). */ df = frag_off; if (df) { mtu = dst_mtu(&rt->dst) - dev->hard_header_len - sizeof(struct iphdr) - sizeof(struct udphdr); switch (pctx->gtp_version) { case GTP_V0: mtu -= sizeof(struct gtp0_header); break; case GTP_V1: mtu -= sizeof(struct gtp1_header); break; } } else { mtu = dst_mtu(&rt->dst); } skb_dst_update_pmtu_no_confirm(skb, mtu); if (frag_off & htons(IP_DF) && ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu)))) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto err_rt; } gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, tos, pctx, rt, &fl4, dev); gtp_push_header(skb, pktinfo); return 0; err_rt: ip_rt_put(rt); err: return -EBADMSG; } static int gtp_build_skb_outer_ip6(struct net *net, struct sk_buff *skb, struct net_device *dev, struct gtp_pktinfo *pktinfo, struct pdp_ctx *pctx, __u8 tos) { struct dst_entry *dst; struct rt6_info *rt; struct flowi6 fl6; int mtu; rt = ip6_route_output_gtp(net, &fl6, pctx->sk, &pctx->peer.addr6, &inet6_sk(pctx->sk)->saddr); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to SSGN %pI6\n", &pctx->peer.addr6); dev->stats.tx_carrier_errors++; goto err; } dst = &rt->dst; if (rt->dst.dev == dev) { netdev_dbg(dev, "circular route to SSGN %pI6\n", &pctx->peer.addr6); dev->stats.collisions++; goto err_rt; } mtu = dst_mtu(&rt->dst) - dev->hard_header_len - sizeof(struct ipv6hdr) - sizeof(struct udphdr); switch (pctx->gtp_version) { case GTP_V0: mtu -= sizeof(struct gtp0_header); break; case GTP_V1: mtu -= sizeof(struct gtp1_header); break; } skb_dst_update_pmtu_no_confirm(skb, mtu); if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); goto err_rt; } gtp_set_pktinfo_ipv6(pktinfo, pctx->sk, tos, pctx, rt, &fl6, dev); gtp_push_header(skb, pktinfo); return 0; err_rt: dst_release(dst); err: return -EBADMSG; } static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, struct gtp_pktinfo *pktinfo) { struct gtp_dev *gtp = netdev_priv(dev); struct net *net = gtp->net; struct pdp_ctx *pctx; struct iphdr *iph; int ret; /* Read the IP destination address and resolve the PDP context. * Prepend PDP header with TEI/TID from PDP ctx. */ iph = ip_hdr(skb); if (gtp->role == GTP_ROLE_SGSN) pctx = ipv4_pdp_find(gtp, iph->saddr); else pctx = ipv4_pdp_find(gtp, iph->daddr); if (!pctx) { netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n", &iph->daddr); return -ENOENT; } netdev_dbg(dev, "found PDP context %p\n", pctx); switch (pctx->sk->sk_family) { case AF_INET: ret = gtp_build_skb_outer_ip4(skb, dev, pktinfo, pctx, iph->tos, iph->frag_off); break; case AF_INET6: ret = gtp_build_skb_outer_ip6(net, skb, dev, pktinfo, pctx, iph->tos); break; default: ret = -1; WARN_ON_ONCE(1); break; } if (ret < 0) return ret; netdev_dbg(dev, "gtp -> IP src: %pI4 dst: %pI4\n", &iph->saddr, &iph->daddr); return 0; } static int gtp_build_skb_ip6(struct sk_buff *skb, struct net_device *dev, struct gtp_pktinfo *pktinfo) { struct gtp_dev *gtp = netdev_priv(dev); struct net *net = gtp->net; struct pdp_ctx *pctx; struct ipv6hdr *ip6h; __u8 tos; int ret; /* Read the IP destination address and resolve the PDP context. * Prepend PDP header with TEI/TID from PDP ctx. */ ip6h = ipv6_hdr(skb); if (gtp->role == GTP_ROLE_SGSN) pctx = ipv6_pdp_find(gtp, &ip6h->saddr); else pctx = ipv6_pdp_find(gtp, &ip6h->daddr); if (!pctx) { netdev_dbg(dev, "no PDP ctx found for %pI6, skip\n", &ip6h->daddr); return -ENOENT; } netdev_dbg(dev, "found PDP context %p\n", pctx); tos = ipv6_get_dsfield(ip6h); switch (pctx->sk->sk_family) { case AF_INET: ret = gtp_build_skb_outer_ip4(skb, dev, pktinfo, pctx, tos, 0); break; case AF_INET6: ret = gtp_build_skb_outer_ip6(net, skb, dev, pktinfo, pctx, tos); break; default: ret = -1; WARN_ON_ONCE(1); break; } if (ret < 0) return ret; netdev_dbg(dev, "gtp -> IP src: %pI6 dst: %pI6\n", &ip6h->saddr, &ip6h->daddr); return 0; } static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned int proto = ntohs(skb->protocol); struct gtp_pktinfo pktinfo; int err; /* Ensure there is sufficient headroom. */ if (skb_cow_head(skb, dev->needed_headroom)) goto tx_err; if (!pskb_inet_may_pull(skb)) goto tx_err; skb_reset_inner_headers(skb); /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */ rcu_read_lock(); switch (proto) { case ETH_P_IP: err = gtp_build_skb_ip4(skb, dev, &pktinfo); break; case ETH_P_IPV6: err = gtp_build_skb_ip6(skb, dev, &pktinfo); break; default: err = -EOPNOTSUPP; break; } rcu_read_unlock(); if (err < 0) goto tx_err; switch (pktinfo.pctx->sk->sk_family) { case AF_INET: udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb, pktinfo.fl4.saddr, pktinfo.fl4.daddr, pktinfo.tos, ip4_dst_hoplimit(&pktinfo.rt->dst), 0, pktinfo.gtph_port, pktinfo.gtph_port, !net_eq(sock_net(pktinfo.pctx->sk), dev_net(dev)), false); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) udp_tunnel6_xmit_skb(&pktinfo.rt6->dst, pktinfo.sk, skb, dev, &pktinfo.fl6.saddr, &pktinfo.fl6.daddr, pktinfo.tos, ip6_dst_hoplimit(&pktinfo.rt->dst), 0, pktinfo.gtph_port, pktinfo.gtph_port, false); #else goto tx_err; #endif break; } return NETDEV_TX_OK; tx_err: dev->stats.tx_errors++; dev_kfree_skb(skb); return NETDEV_TX_OK; } static const struct net_device_ops gtp_netdev_ops = { .ndo_uninit = gtp_dev_uninit, .ndo_start_xmit = gtp_dev_xmit, }; static const struct device_type gtp_type = { .name = "gtp", }; #define GTP_TH_MAXLEN (sizeof(struct udphdr) + sizeof(struct gtp0_header)) #define GTP_IPV4_MAXLEN (sizeof(struct iphdr) + GTP_TH_MAXLEN) static void gtp_link_setup(struct net_device *dev) { struct gtp_dev *gtp = netdev_priv(dev); dev->netdev_ops = >p_netdev_ops; dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, >p_type); dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = ETH_DATA_LEN - GTP_IPV4_MAXLEN; /* Zero header length. */ dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; netif_keep_dst(dev); dev->needed_headroom = LL_MAX_HEADER + GTP_IPV4_MAXLEN; gtp->dev = dev; } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); static void gtp_destructor(struct net_device *dev) { struct gtp_dev *gtp = netdev_priv(dev); kfree(gtp->addr_hash); kfree(gtp->tid_hash); } static int gtp_sock_udp_config(struct udp_port_cfg *udp_conf, const struct nlattr *nla, int family) { udp_conf->family = family; switch (udp_conf->family) { case AF_INET: udp_conf->local_ip.s_addr = nla_get_be32(nla); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: udp_conf->local_ip6 = nla_get_in6_addr(nla); break; #endif default: return -EOPNOTSUPP; } return 0; } static struct sock *gtp_create_sock(int type, struct gtp_dev *gtp, const struct nlattr *nla, int family) { struct udp_tunnel_sock_cfg tuncfg = {}; struct udp_port_cfg udp_conf = {}; struct net *net = gtp->net; struct socket *sock; int err; if (nla) { err = gtp_sock_udp_config(&udp_conf, nla, family); if (err < 0) return ERR_PTR(err); } else { udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.family = AF_INET; } if (type == UDP_ENCAP_GTP0) udp_conf.local_udp_port = htons(GTP0_PORT); else if (type == UDP_ENCAP_GTP1U) udp_conf.local_udp_port = htons(GTP1U_PORT); else return ERR_PTR(-EINVAL); err = udp_sock_create(net, &udp_conf, &sock); if (err) return ERR_PTR(err); tuncfg.sk_user_data = gtp; tuncfg.encap_type = type; tuncfg.encap_rcv = gtp_encap_recv; tuncfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sock, &tuncfg); return sock->sk; } static int gtp_create_sockets(struct gtp_dev *gtp, const struct nlattr *nla, int family) { struct sock *sk1u; struct sock *sk0; sk0 = gtp_create_sock(UDP_ENCAP_GTP0, gtp, nla, family); if (IS_ERR(sk0)) return PTR_ERR(sk0); sk1u = gtp_create_sock(UDP_ENCAP_GTP1U, gtp, nla, family); if (IS_ERR(sk1u)) { udp_tunnel_sock_release(sk0->sk_socket); return PTR_ERR(sk1u); } gtp->sk_created = true; gtp->sk0 = sk0; gtp->sk1u = sk1u; return 0; } #define GTP_TH_MAXLEN (sizeof(struct udphdr) + sizeof(struct gtp0_header)) #define GTP_IPV6_MAXLEN (sizeof(struct ipv6hdr) + GTP_TH_MAXLEN) static int gtp_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; unsigned int role = GTP_ROLE_GGSN; struct gtp_dev *gtp; struct gtp_net *gn; int hashsize, err; #if !IS_ENABLED(CONFIG_IPV6) if (data[IFLA_GTP_LOCAL6]) return -EAFNOSUPPORT; #endif gtp = netdev_priv(dev); if (!data[IFLA_GTP_PDP_HASHSIZE]) { hashsize = 1024; } else { hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]); if (!hashsize) hashsize = 1024; } if (data[IFLA_GTP_ROLE]) { role = nla_get_u32(data[IFLA_GTP_ROLE]); if (role > GTP_ROLE_SGSN) return -EINVAL; } gtp->role = role; gtp->restart_count = nla_get_u8_default(data[IFLA_GTP_RESTART_COUNT], 0); gtp->net = link_net; err = gtp_hashtable_new(gtp, hashsize); if (err < 0) return err; if (data[IFLA_GTP_CREATE_SOCKETS]) { if (data[IFLA_GTP_LOCAL6]) err = gtp_create_sockets(gtp, data[IFLA_GTP_LOCAL6], AF_INET6); else err = gtp_create_sockets(gtp, data[IFLA_GTP_LOCAL], AF_INET); } else { err = gtp_encap_enable(gtp, data); } if (err < 0) goto out_hashtable; if ((gtp->sk0 && gtp->sk0->sk_family == AF_INET6) || (gtp->sk1u && gtp->sk1u->sk_family == AF_INET6)) { dev->mtu = ETH_DATA_LEN - GTP_IPV6_MAXLEN; dev->needed_headroom = LL_MAX_HEADER + GTP_IPV6_MAXLEN; } err = register_netdevice(dev); if (err < 0) { netdev_dbg(dev, "failed to register new netdev %d\n", err); goto out_encap; } gn = net_generic(link_net, gtp_net_id); list_add(>p->list, &gn->gtp_dev_list); dev->priv_destructor = gtp_destructor; netdev_dbg(dev, "registered new GTP interface\n"); return 0; out_encap: gtp_encap_disable(gtp); out_hashtable: kfree(gtp->addr_hash); kfree(gtp->tid_hash); return err; } static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); struct hlist_node *next; struct pdp_ctx *pctx; int i; for (i = 0; i < gtp->hash_size; i++) hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); list_del(>p->list); unregister_netdevice_queue(dev, head); } static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = { [IFLA_GTP_FD0] = { .type = NLA_U32 }, [IFLA_GTP_FD1] = { .type = NLA_U32 }, [IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 }, [IFLA_GTP_ROLE] = { .type = NLA_U32 }, [IFLA_GTP_CREATE_SOCKETS] = { .type = NLA_U8 }, [IFLA_GTP_RESTART_COUNT] = { .type = NLA_U8 }, [IFLA_GTP_LOCAL] = { .type = NLA_U32 }, [IFLA_GTP_LOCAL6] = { .len = sizeof(struct in6_addr) }, }; static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return -EINVAL; return 0; } static size_t gtp_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GTP_PDP_HASHSIZE */ nla_total_size(sizeof(__u32)) + /* IFLA_GTP_ROLE */ nla_total_size(sizeof(__u8)); /* IFLA_GTP_RESTART_COUNT */ } static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct gtp_dev *gtp = netdev_priv(dev); if (nla_put_u32(skb, IFLA_GTP_PDP_HASHSIZE, gtp->hash_size)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_GTP_ROLE, gtp->role)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GTP_RESTART_COUNT, gtp->restart_count)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops gtp_link_ops __read_mostly = { .kind = "gtp", .maxtype = IFLA_GTP_MAX, .policy = gtp_policy, .priv_size = sizeof(struct gtp_dev), .setup = gtp_link_setup, .validate = gtp_validate, .newlink = gtp_newlink, .dellink = gtp_dellink, .get_size = gtp_get_size, .fill_info = gtp_fill_info, }; static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize) { int i; gtp->addr_hash = kmalloc_array(hsize, sizeof(struct hlist_head), GFP_KERNEL | __GFP_NOWARN); if (gtp->addr_hash == NULL) return -ENOMEM; gtp->tid_hash = kmalloc_array(hsize, sizeof(struct hlist_head), GFP_KERNEL | __GFP_NOWARN); if (gtp->tid_hash == NULL) goto err1; gtp->hash_size = hsize; for (i = 0; i < hsize; i++) { INIT_HLIST_HEAD(>p->addr_hash[i]); INIT_HLIST_HEAD(>p->tid_hash[i]); } return 0; err1: kfree(gtp->addr_hash); return -ENOMEM; } static struct sock *gtp_encap_enable_socket(int fd, int type, struct gtp_dev *gtp) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; struct socket *sock; struct sock *sk; int err; pr_debug("enable gtp on %d, %d\n", fd, type); sock = sockfd_lookup(fd, &err); if (!sock) { pr_debug("gtp socket fd=%d not found\n", fd); return ERR_PTR(err); } sk = sock->sk; if (sk->sk_protocol != IPPROTO_UDP || sk->sk_type != SOCK_DGRAM || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { pr_debug("socket fd=%d not UDP\n", fd); sk = ERR_PTR(-EINVAL); goto out_sock; } if (sk->sk_family == AF_INET6 && !sk->sk_ipv6only) { sk = ERR_PTR(-EADDRNOTAVAIL); goto out_sock; } lock_sock(sk); if (sk->sk_user_data) { sk = ERR_PTR(-EBUSY); goto out_rel_sock; } sock_hold(sk); tuncfg.sk_user_data = gtp; tuncfg.encap_type = type; tuncfg.encap_rcv = gtp_encap_recv; tuncfg.encap_destroy = gtp_encap_destroy; setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg); out_rel_sock: release_sock(sock->sk); out_sock: sockfd_put(sock); return sk; } static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) { struct sock *sk1u = NULL; struct sock *sk0 = NULL; if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1]) return -EINVAL; if (data[IFLA_GTP_FD0]) { int fd0 = nla_get_u32(data[IFLA_GTP_FD0]); if (fd0 >= 0) { sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp); if (IS_ERR(sk0)) return PTR_ERR(sk0); } } if (data[IFLA_GTP_FD1]) { int fd1 = nla_get_u32(data[IFLA_GTP_FD1]); if (fd1 >= 0) { sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp); if (IS_ERR(sk1u)) { gtp_encap_disable_sock(sk0); return PTR_ERR(sk1u); } } } gtp->sk0 = sk0; gtp->sk1u = sk1u; if (sk0 && sk1u && sk0->sk_family != sk1u->sk_family) { gtp_encap_disable_sock(sk0); gtp_encap_disable_sock(sk1u); return -EINVAL; } return 0; } static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[]) { struct gtp_dev *gtp = NULL; struct net_device *dev; struct net *net; /* Examine the link attributes and figure out which network namespace * we are talking about. */ if (nla[GTPA_NET_NS_FD]) net = get_net_ns_by_fd(nla_get_u32(nla[GTPA_NET_NS_FD])); else net = get_net(src_net); if (IS_ERR(net)) return NULL; /* Check if there's an existing gtpX device to configure */ dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK])); if (dev && dev->netdev_ops == >p_netdev_ops) gtp = netdev_priv(dev); put_net(net); return gtp; } static void gtp_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) { pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]); switch (pctx->gtp_version) { case GTP_V0: /* According to TS 09.60, sections 7.5.1 and 7.5.2, the flow * label needs to be the same for uplink and downlink packets, * so let's annotate this. */ pctx->u.v0.tid = nla_get_u64(info->attrs[GTPA_TID]); pctx->u.v0.flow = nla_get_u16(info->attrs[GTPA_FLOW]); break; case GTP_V1: pctx->u.v1.i_tei = nla_get_u32(info->attrs[GTPA_I_TEI]); pctx->u.v1.o_tei = nla_get_u32(info->attrs[GTPA_O_TEI]); break; default: break; } } static void ip_pdp_peer_fill(struct pdp_ctx *pctx, struct genl_info *info) { if (info->attrs[GTPA_PEER_ADDRESS]) { pctx->peer.addr.s_addr = nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]); } else if (info->attrs[GTPA_PEER_ADDR6]) { pctx->peer.addr6 = nla_get_in6_addr(info->attrs[GTPA_PEER_ADDR6]); } } static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) { ip_pdp_peer_fill(pctx, info); pctx->ms.addr.s_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); gtp_pdp_fill(pctx, info); } static bool ipv6_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) { ip_pdp_peer_fill(pctx, info); pctx->ms.addr6 = nla_get_in6_addr(info->attrs[GTPA_MS_ADDR6]); if (pctx->ms.addr6.s6_addr32[2] || pctx->ms.addr6.s6_addr32[3]) return false; gtp_pdp_fill(pctx, info); return true; } static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, struct genl_info *info) { struct pdp_ctx *pctx, *pctx_tid = NULL; struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; struct in6_addr ms_addr6; unsigned int version; bool found = false; __be32 ms_addr; int family; version = nla_get_u32(info->attrs[GTPA_VERSION]); family = nla_get_u8_default(info->attrs[GTPA_FAMILY], AF_INET); #if !IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) return ERR_PTR(-EAFNOSUPPORT); #endif if (!info->attrs[GTPA_PEER_ADDRESS] && !info->attrs[GTPA_PEER_ADDR6]) return ERR_PTR(-EINVAL); if ((info->attrs[GTPA_PEER_ADDRESS] && sk->sk_family == AF_INET6) || (info->attrs[GTPA_PEER_ADDR6] && sk->sk_family == AF_INET)) return ERR_PTR(-EAFNOSUPPORT); switch (family) { case AF_INET: if (!info->attrs[GTPA_MS_ADDRESS] || info->attrs[GTPA_MS_ADDR6]) return ERR_PTR(-EINVAL); ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size; pctx = ipv4_pdp_find(gtp, ms_addr); break; case AF_INET6: if (!info->attrs[GTPA_MS_ADDR6] || info->attrs[GTPA_MS_ADDRESS]) return ERR_PTR(-EINVAL); ms_addr6 = nla_get_in6_addr(info->attrs[GTPA_MS_ADDR6]); hash_ms = ipv6_hashfn(&ms_addr6) % gtp->hash_size; pctx = ipv6_pdp_find(gtp, &ms_addr6); break; default: return ERR_PTR(-EAFNOSUPPORT); } if (pctx) found = true; if (version == GTP_V0) pctx_tid = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID]), family); else if (version == GTP_V1) pctx_tid = gtp1_pdp_find(gtp, nla_get_u32(info->attrs[GTPA_I_TEI]), family); if (pctx_tid) found = true; if (found) { if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) return ERR_PTR(-EEXIST); if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE) return ERR_PTR(-EOPNOTSUPP); if (pctx && pctx_tid) return ERR_PTR(-EEXIST); if (!pctx) pctx = pctx_tid; switch (pctx->af) { case AF_INET: ipv4_pdp_fill(pctx, info); break; case AF_INET6: if (!ipv6_pdp_fill(pctx, info)) return ERR_PTR(-EADDRNOTAVAIL); break; } if (pctx->gtp_version == GTP_V0) netdev_dbg(dev, "GTPv0-U: update tunnel id = %llx (pdp %p)\n", pctx->u.v0.tid, pctx); else if (pctx->gtp_version == GTP_V1) netdev_dbg(dev, "GTPv1-U: update tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); return pctx; } pctx = kmalloc(sizeof(*pctx), GFP_ATOMIC); if (pctx == NULL) return ERR_PTR(-ENOMEM); sock_hold(sk); pctx->sk = sk; pctx->dev = gtp->dev; pctx->af = family; switch (pctx->af) { case AF_INET: if (!info->attrs[GTPA_MS_ADDRESS]) { sock_put(sk); kfree(pctx); return ERR_PTR(-EINVAL); } ipv4_pdp_fill(pctx, info); break; case AF_INET6: if (!info->attrs[GTPA_MS_ADDR6]) { sock_put(sk); kfree(pctx); return ERR_PTR(-EINVAL); } if (!ipv6_pdp_fill(pctx, info)) { sock_put(sk); kfree(pctx); return ERR_PTR(-EADDRNOTAVAIL); } break; } atomic_set(&pctx->tx_seq, 0); switch (pctx->gtp_version) { case GTP_V0: /* TS 09.60: "The flow label identifies unambiguously a GTP * flow.". We use the tid for this instead, I cannot find a * situation in which this doesn't unambiguosly identify the * PDP context. */ hash_tid = gtp0_hashfn(pctx->u.v0.tid) % gtp->hash_size; break; case GTP_V1: hash_tid = gtp1u_hashfn(pctx->u.v1.i_tei) % gtp->hash_size; break; } hlist_add_head_rcu(&pctx->hlist_addr, >p->addr_hash[hash_ms]); hlist_add_head_rcu(&pctx->hlist_tid, >p->tid_hash[hash_tid]); switch (pctx->gtp_version) { case GTP_V0: netdev_dbg(dev, "GTPv0-U: new PDP ctx id=%llx ssgn=%pI4 ms=%pI4 (pdp=%p)\n", pctx->u.v0.tid, &pctx->peer.addr, &pctx->ms.addr, pctx); break; case GTP_V1: netdev_dbg(dev, "GTPv1-U: new PDP ctx id=%x/%x ssgn=%pI4 ms=%pI4 (pdp=%p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, &pctx->peer.addr, &pctx->ms.addr, pctx); break; } return pctx; } static void pdp_context_free(struct rcu_head *head) { struct pdp_ctx *pctx = container_of(head, struct pdp_ctx, rcu_head); sock_put(pctx->sk); kfree(pctx); } static void pdp_context_delete(struct pdp_ctx *pctx) { hlist_del_rcu(&pctx->hlist_tid); hlist_del_rcu(&pctx->hlist_addr); call_rcu(&pctx->rcu_head, pdp_context_free); } static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd, gfp_t allocation); static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) { unsigned int version; struct pdp_ctx *pctx; struct gtp_dev *gtp; struct sock *sk; int err; if (!info->attrs[GTPA_VERSION] || !info->attrs[GTPA_LINK]) return -EINVAL; version = nla_get_u32(info->attrs[GTPA_VERSION]); switch (version) { case GTP_V0: if (!info->attrs[GTPA_TID] || !info->attrs[GTPA_FLOW]) return -EINVAL; break; case GTP_V1: if (!info->attrs[GTPA_I_TEI] || !info->attrs[GTPA_O_TEI]) return -EINVAL; break; default: return -EINVAL; } rtnl_lock(); gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); if (!gtp) { err = -ENODEV; goto out_unlock; } if (version == GTP_V0) sk = gtp->sk0; else if (version == GTP_V1) sk = gtp->sk1u; else sk = NULL; if (!sk) { err = -ENODEV; goto out_unlock; } pctx = gtp_pdp_add(gtp, sk, info); if (IS_ERR(pctx)) { err = PTR_ERR(pctx); } else { gtp_tunnel_notify(pctx, GTP_CMD_NEWPDP, GFP_KERNEL); err = 0; } out_unlock: rtnl_unlock(); return err; } static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net, struct nlattr *nla[]) { struct gtp_dev *gtp; int family; family = nla_get_u8_default(nla[GTPA_FAMILY], AF_INET); gtp = gtp_find_dev(net, nla); if (!gtp) return ERR_PTR(-ENODEV); if (nla[GTPA_MS_ADDRESS]) { __be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]); if (family != AF_INET) return ERR_PTR(-EINVAL); return ipv4_pdp_find(gtp, ip); } else if (nla[GTPA_MS_ADDR6]) { struct in6_addr addr = nla_get_in6_addr(nla[GTPA_MS_ADDR6]); if (family != AF_INET6) return ERR_PTR(-EINVAL); if (addr.s6_addr32[2] || addr.s6_addr32[3]) return ERR_PTR(-EADDRNOTAVAIL); return ipv6_pdp_find(gtp, &addr); } else if (nla[GTPA_VERSION]) { u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]); if (gtp_version == GTP_V0 && nla[GTPA_TID]) { return gtp0_pdp_find(gtp, nla_get_u64(nla[GTPA_TID]), family); } else if (gtp_version == GTP_V1 && nla[GTPA_I_TEI]) { return gtp1_pdp_find(gtp, nla_get_u32(nla[GTPA_I_TEI]), family); } } return ERR_PTR(-EINVAL); } static struct pdp_ctx *gtp_find_pdp(struct net *net, struct nlattr *nla[]) { struct pdp_ctx *pctx; if (nla[GTPA_LINK]) pctx = gtp_find_pdp_by_link(net, nla); else pctx = ERR_PTR(-EINVAL); if (!pctx) pctx = ERR_PTR(-ENOENT); return pctx; } static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx; int err = 0; if (!info->attrs[GTPA_VERSION]) return -EINVAL; rcu_read_lock(); pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs); if (IS_ERR(pctx)) { err = PTR_ERR(pctx); goto out_unlock; } if (pctx->gtp_version == GTP_V0) netdev_dbg(pctx->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n", pctx->u.v0.tid, pctx); else if (pctx->gtp_version == GTP_V1) netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); gtp_tunnel_notify(pctx, GTP_CMD_DELPDP, GFP_ATOMIC); pdp_context_delete(pctx); out_unlock: rcu_read_unlock(); return err; } static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, int flags, u32 type, struct pdp_ctx *pctx) { void *genlh; genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, flags, type); if (genlh == NULL) goto nlmsg_failure; if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) || nla_put_u32(skb, GTPA_LINK, pctx->dev->ifindex) || nla_put_u8(skb, GTPA_FAMILY, pctx->af)) goto nla_put_failure; switch (pctx->af) { case AF_INET: if (nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms.addr.s_addr)) goto nla_put_failure; break; case AF_INET6: if (nla_put_in6_addr(skb, GTPA_MS_ADDR6, &pctx->ms.addr6)) goto nla_put_failure; break; } switch (pctx->sk->sk_family) { case AF_INET: if (nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer.addr.s_addr)) goto nla_put_failure; break; case AF_INET6: if (nla_put_in6_addr(skb, GTPA_PEER_ADDR6, &pctx->peer.addr6)) goto nla_put_failure; break; } switch (pctx->gtp_version) { case GTP_V0: if (nla_put_u64_64bit(skb, GTPA_TID, pctx->u.v0.tid, GTPA_PAD) || nla_put_u16(skb, GTPA_FLOW, pctx->u.v0.flow)) goto nla_put_failure; break; case GTP_V1: if (nla_put_u32(skb, GTPA_I_TEI, pctx->u.v1.i_tei) || nla_put_u32(skb, GTPA_O_TEI, pctx->u.v1.o_tei)) goto nla_put_failure; break; } genlmsg_end(skb, genlh); return 0; nlmsg_failure: nla_put_failure: genlmsg_cancel(skb, genlh); return -EMSGSIZE; } static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd, gfp_t allocation) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, allocation); if (!msg) return -ENOMEM; ret = gtp_genl_fill_info(msg, 0, 0, 0, cmd, pctx); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_multicast_netns(>p_genl_family, dev_net(pctx->dev), msg, 0, GTP_GENL_MCGRP, GFP_ATOMIC); return ret; } static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx = NULL; struct sk_buff *skb2; int err; if (!info->attrs[GTPA_VERSION]) return -EINVAL; rcu_read_lock(); pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs); if (IS_ERR(pctx)) { err = PTR_ERR(pctx); goto err_unlock; } skb2 = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb2 == NULL) { err = -ENOMEM; goto err_unlock; } err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, info->snd_seq, 0, info->nlhdr->nlmsg_type, pctx); if (err < 0) goto err_unlock_free; rcu_read_unlock(); return genlmsg_unicast(genl_info_net(info), skb2, info->snd_portid); err_unlock_free: kfree_skb(skb2); err_unlock: rcu_read_unlock(); return err; } static int gtp_genl_dump_pdp(struct sk_buff *skb, struct netlink_callback *cb) { struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp; int i, j, bucket = cb->args[0], skip = cb->args[1]; struct net *net = sock_net(skb->sk); struct net_device *dev; struct pdp_ctx *pctx; if (cb->args[4]) return 0; rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (dev->rtnl_link_ops != >p_link_ops) continue; gtp = netdev_priv(dev); if (last_gtp && last_gtp != gtp) continue; else last_gtp = NULL; for (i = bucket; i < gtp->hash_size; i++) { j = 0; hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) { if (j >= skip && gtp_genl_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh->nlmsg_type, pctx)) { cb->args[0] = i; cb->args[1] = j; cb->args[2] = (unsigned long)gtp; goto out; } j++; } skip = 0; } bucket = 0; } cb->args[4] = 1; out: rcu_read_unlock(); return skb->len; } static int gtp_genl_send_echo_req(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *skb_to_send; __be32 src_ip, dst_ip; unsigned int version; struct gtp_dev *gtp; struct flowi4 fl4; struct rtable *rt; struct sock *sk; __be16 port; int len; if (!info->attrs[GTPA_VERSION] || !info->attrs[GTPA_LINK] || !info->attrs[GTPA_PEER_ADDRESS] || !info->attrs[GTPA_MS_ADDRESS]) return -EINVAL; version = nla_get_u32(info->attrs[GTPA_VERSION]); dst_ip = nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]); src_ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); if (!gtp) return -ENODEV; if (!gtp->sk_created) return -EOPNOTSUPP; if (!(gtp->dev->flags & IFF_UP)) return -ENETDOWN; if (version == GTP_V0) { struct gtp0_header *gtp0_h; len = LL_RESERVED_SPACE(gtp->dev) + sizeof(struct gtp0_header) + sizeof(struct iphdr) + sizeof(struct udphdr); skb_to_send = netdev_alloc_skb_ip_align(gtp->dev, len); if (!skb_to_send) return -ENOMEM; sk = gtp->sk0; port = htons(GTP0_PORT); gtp0_h = skb_push(skb_to_send, sizeof(struct gtp0_header)); memset(gtp0_h, 0, sizeof(struct gtp0_header)); gtp0_build_echo_msg(gtp0_h, GTP_ECHO_REQ); } else if (version == GTP_V1) { struct gtp1_header_long *gtp1u_h; len = LL_RESERVED_SPACE(gtp->dev) + sizeof(struct gtp1_header_long) + sizeof(struct iphdr) + sizeof(struct udphdr); skb_to_send = netdev_alloc_skb_ip_align(gtp->dev, len); if (!skb_to_send) return -ENOMEM; sk = gtp->sk1u; port = htons(GTP1U_PORT); gtp1u_h = skb_push(skb_to_send, sizeof(struct gtp1_header_long)); memset(gtp1u_h, 0, sizeof(struct gtp1_header_long)); gtp1u_build_echo_msg(gtp1u_h, GTP_ECHO_REQ); } else { return -ENODEV; } rt = ip4_route_output_gtp(&fl4, sk, dst_ip, src_ip); if (IS_ERR(rt)) { netdev_dbg(gtp->dev, "no route for echo request to %pI4\n", &dst_ip); kfree_skb(skb_to_send); return -ENODEV; } udp_tunnel_xmit_skb(rt, sk, skb_to_send, fl4.saddr, fl4.daddr, fl4.flowi4_tos, ip4_dst_hoplimit(&rt->dst), 0, port, port, !net_eq(sock_net(sk), dev_net(gtp->dev)), false); return 0; } static const struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = { [GTPA_LINK] = { .type = NLA_U32, }, [GTPA_VERSION] = { .type = NLA_U32, }, [GTPA_TID] = { .type = NLA_U64, }, [GTPA_PEER_ADDRESS] = { .type = NLA_U32, }, [GTPA_MS_ADDRESS] = { .type = NLA_U32, }, [GTPA_FLOW] = { .type = NLA_U16, }, [GTPA_NET_NS_FD] = { .type = NLA_U32, }, [GTPA_I_TEI] = { .type = NLA_U32, }, [GTPA_O_TEI] = { .type = NLA_U32, }, [GTPA_PEER_ADDR6] = { .len = sizeof(struct in6_addr), }, [GTPA_MS_ADDR6] = { .len = sizeof(struct in6_addr), }, [GTPA_FAMILY] = { .type = NLA_U8, }, }; static const struct genl_small_ops gtp_genl_ops[] = { { .cmd = GTP_CMD_NEWPDP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = gtp_genl_new_pdp, .flags = GENL_ADMIN_PERM, }, { .cmd = GTP_CMD_DELPDP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = gtp_genl_del_pdp, .flags = GENL_ADMIN_PERM, }, { .cmd = GTP_CMD_GETPDP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = gtp_genl_get_pdp, .dumpit = gtp_genl_dump_pdp, .flags = GENL_ADMIN_PERM, }, { .cmd = GTP_CMD_ECHOREQ, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = gtp_genl_send_echo_req, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family gtp_genl_family __ro_after_init = { .name = "gtp", .version = 0, .hdrsize = 0, .maxattr = GTPA_MAX, .policy = gtp_genl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = gtp_genl_ops, .n_small_ops = ARRAY_SIZE(gtp_genl_ops), .resv_start_op = GTP_CMD_ECHOREQ + 1, .mcgrps = gtp_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(gtp_genl_mcgrps), }; static int __net_init gtp_net_init(struct net *net) { struct gtp_net *gn = net_generic(net, gtp_net_id); INIT_LIST_HEAD(&gn->gtp_dev_list); return 0; } static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; list_for_each_entry(net, net_list, exit_list) { struct gtp_net *gn = net_generic(net, gtp_net_id); struct gtp_dev *gtp, *gtp_next; list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list) gtp_dellink(gtp->dev, dev_to_kill); } } static struct pernet_operations gtp_net_ops = { .init = gtp_net_init, .exit_batch_rtnl = gtp_net_exit_batch_rtnl, .id = >p_net_id, .size = sizeof(struct gtp_net), }; static int __init gtp_init(void) { int err; get_random_bytes(>p_h_initval, sizeof(gtp_h_initval)); err = register_pernet_subsys(>p_net_ops); if (err < 0) goto error_out; err = rtnl_link_register(>p_link_ops); if (err < 0) goto unreg_pernet_subsys; err = genl_register_family(>p_genl_family); if (err < 0) goto unreg_rtnl_link; pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0; unreg_rtnl_link: rtnl_link_unregister(>p_link_ops); unreg_pernet_subsys: unregister_pernet_subsys(>p_net_ops); error_out: pr_err("error loading GTP module loaded\n"); return err; } late_initcall(gtp_init); static void __exit gtp_fini(void) { genl_unregister_family(>p_genl_family); rtnl_link_unregister(>p_link_ops); unregister_pernet_subsys(>p_net_ops); pr_info("GTP module unloaded\n"); } module_exit(gtp_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <hwelte@sysmocom.de>"); MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("gtp"); MODULE_ALIAS_GENL_FAMILY("gtp"); |
| 2 2 2 2 2 2 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" struct fec_req_info { struct ethnl_req_info base; }; struct fec_reply_data { struct ethnl_reply_data base; __ETHTOOL_DECLARE_LINK_MODE_MASK(fec_link_modes); u32 active_fec; u8 fec_auto; struct fec_stat_grp { u64 stats[1 + ETHTOOL_MAX_LANES]; u8 cnt; } corr, uncorr, corr_bits; }; #define FEC_REPDATA(__reply_base) \ container_of(__reply_base, struct fec_reply_data, base) #define ETHTOOL_FEC_MASK ((ETHTOOL_FEC_LLRS << 1) - 1) const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1] = { [ETHTOOL_A_FEC_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static void ethtool_fec_to_link_modes(u32 fec, unsigned long *link_modes, u8 *fec_auto) { if (fec_auto) *fec_auto = !!(fec & ETHTOOL_FEC_AUTO); if (fec & ETHTOOL_FEC_OFF) __set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, link_modes); if (fec & ETHTOOL_FEC_RS) __set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, link_modes); if (fec & ETHTOOL_FEC_BASER) __set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, link_modes); if (fec & ETHTOOL_FEC_LLRS) __set_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, link_modes); } static int ethtool_link_modes_to_fecparam(struct ethtool_fecparam *fec, unsigned long *link_modes, u8 fec_auto) { memset(fec, 0, sizeof(*fec)); if (fec_auto) fec->fec |= ETHTOOL_FEC_AUTO; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_OFF; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_RS; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_BASER; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_LLRS; if (!bitmap_empty(link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS)) return -EINVAL; return 0; } static void fec_stats_recalc(struct fec_stat_grp *grp, struct ethtool_fec_stat *stats) { int i; if (stats->lanes[0] == ETHTOOL_STAT_NOT_SET) { grp->stats[0] = stats->total; grp->cnt = stats->total != ETHTOOL_STAT_NOT_SET; return; } grp->cnt = 1; grp->stats[0] = 0; for (i = 0; i < ETHTOOL_MAX_LANES; i++) { if (stats->lanes[i] == ETHTOOL_STAT_NOT_SET) break; grp->stats[0] += stats->lanes[i]; grp->stats[grp->cnt++] = stats->lanes[i]; } } static int fec_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { __ETHTOOL_DECLARE_LINK_MODE_MASK(active_fec_modes) = {}; struct fec_reply_data *data = FEC_REPDATA(reply_base); struct net_device *dev = reply_base->dev; struct ethtool_fecparam fec = {}; int ret; if (!dev->ethtool_ops->get_fecparam) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = dev->ethtool_ops->get_fecparam(dev, &fec); if (ret) goto out_complete; if (req_base->flags & ETHTOOL_FLAG_STATS && dev->ethtool_ops->get_fec_stats) { struct ethtool_fec_stats stats; ethtool_stats_init((u64 *)&stats, sizeof(stats) / 8); dev->ethtool_ops->get_fec_stats(dev, &stats); fec_stats_recalc(&data->corr, &stats.corrected_blocks); fec_stats_recalc(&data->uncorr, &stats.uncorrectable_blocks); fec_stats_recalc(&data->corr_bits, &stats.corrected_bits); } WARN_ON_ONCE(fec.reserved); ethtool_fec_to_link_modes(fec.fec, data->fec_link_modes, &data->fec_auto); ethtool_fec_to_link_modes(fec.active_fec, active_fec_modes, NULL); data->active_fec = find_first_bit(active_fec_modes, __ETHTOOL_LINK_MODE_MASK_NBITS); /* Don't report attr if no FEC mode set. Note that * ethtool_fecparam_to_link_modes() ignores NONE and AUTO. */ if (data->active_fec == __ETHTOOL_LINK_MODE_MASK_NBITS) data->active_fec = 0; out_complete: ethnl_ops_complete(dev); return ret; } static int fec_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct fec_reply_data *data = FEC_REPDATA(reply_base); int len = 0; int ret; ret = ethnl_bitset_size(data->fec_link_modes, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; len += nla_total_size(sizeof(u8)) + /* _FEC_AUTO */ nla_total_size(sizeof(u32)); /* _FEC_ACTIVE */ if (req_base->flags & ETHTOOL_FLAG_STATS) len += 3 * nla_total_size_64bit(sizeof(u64) * (1 + ETHTOOL_MAX_LANES)); return len; } static int fec_put_stats(struct sk_buff *skb, const struct fec_reply_data *data) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_FEC_STATS); if (!nest) return -EMSGSIZE; if (nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_CORRECTED, sizeof(u64) * data->corr.cnt, data->corr.stats, ETHTOOL_A_FEC_STAT_PAD) || nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_UNCORR, sizeof(u64) * data->uncorr.cnt, data->uncorr.stats, ETHTOOL_A_FEC_STAT_PAD) || nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_CORR_BITS, sizeof(u64) * data->corr_bits.cnt, data->corr_bits.stats, ETHTOOL_A_FEC_STAT_PAD)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int fec_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct fec_reply_data *data = FEC_REPDATA(reply_base); int ret; ret = ethnl_put_bitset(skb, ETHTOOL_A_FEC_MODES, data->fec_link_modes, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; if (nla_put_u8(skb, ETHTOOL_A_FEC_AUTO, data->fec_auto) || (data->active_fec && nla_put_u32(skb, ETHTOOL_A_FEC_ACTIVE, data->active_fec))) return -EMSGSIZE; if (req_base->flags & ETHTOOL_FLAG_STATS && fec_put_stats(skb, data)) return -EMSGSIZE; return 0; } /* FEC_SET */ const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1] = { [ETHTOOL_A_FEC_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_FEC_MODES] = { .type = NLA_NESTED }, [ETHTOOL_A_FEC_AUTO] = NLA_POLICY_MAX(NLA_U8, 1), }; static int ethnl_set_fec_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_fecparam && ops->set_fecparam ? 1 : -EOPNOTSUPP; } static int ethnl_set_fec(struct ethnl_req_info *req_info, struct genl_info *info) { __ETHTOOL_DECLARE_LINK_MODE_MASK(fec_link_modes) = {}; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; struct ethtool_fecparam fec = {}; bool mod = false; u8 fec_auto; int ret; ret = dev->ethtool_ops->get_fecparam(dev, &fec); if (ret < 0) return ret; ethtool_fec_to_link_modes(fec.fec, fec_link_modes, &fec_auto); ret = ethnl_update_bitset(fec_link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS, tb[ETHTOOL_A_FEC_MODES], link_mode_names, info->extack, &mod); if (ret < 0) return ret; ethnl_update_u8(&fec_auto, tb[ETHTOOL_A_FEC_AUTO], &mod); if (!mod) return 0; ret = ethtool_link_modes_to_fecparam(&fec, fec_link_modes, fec_auto); if (ret) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_FEC_MODES], "invalid FEC modes requested"); return ret; } if (!fec.fec) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_FEC_MODES], "no FEC modes set"); return -EINVAL; } ret = dev->ethtool_ops->set_fecparam(dev, &fec); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_fec_request_ops = { .request_cmd = ETHTOOL_MSG_FEC_GET, .reply_cmd = ETHTOOL_MSG_FEC_GET_REPLY, .hdr_attr = ETHTOOL_A_FEC_HEADER, .req_info_size = sizeof(struct fec_req_info), .reply_data_size = sizeof(struct fec_reply_data), .prepare_data = fec_prepare_data, .reply_size = fec_reply_size, .fill_reply = fec_fill_reply, .set_validate = ethnl_set_fec_validate, .set = ethnl_set_fec, .set_ntf_cmd = ETHTOOL_MSG_FEC_NTF, }; |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright(c) 1999 - 2004 Intel Corporation. All rights reserved. */ #include <linux/skbuff.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/if_bonding.h> #include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/bonding.h> #include <net/bond_3ad.h> #include <net/netlink.h> /* General definitions */ #define AD_SHORT_TIMEOUT 1 #define AD_LONG_TIMEOUT 0 #define AD_STANDBY 0x2 #define AD_MAX_TX_IN_SECOND 3 #define AD_COLLECTOR_MAX_DELAY 0 /* Timer definitions (43.4.4 in the 802.3ad standard) */ #define AD_FAST_PERIODIC_TIME 1 #define AD_SLOW_PERIODIC_TIME 30 #define AD_SHORT_TIMEOUT_TIME (3*AD_FAST_PERIODIC_TIME) #define AD_LONG_TIMEOUT_TIME (3*AD_SLOW_PERIODIC_TIME) #define AD_CHURN_DETECTION_TIME 60 #define AD_AGGREGATE_WAIT_TIME 2 /* Port Variables definitions used by the State Machines (43.4.7 in the * 802.3ad standard) */ #define AD_PORT_BEGIN 0x1 #define AD_PORT_LACP_ENABLED 0x2 #define AD_PORT_ACTOR_CHURN 0x4 #define AD_PORT_PARTNER_CHURN 0x8 #define AD_PORT_READY 0x10 #define AD_PORT_READY_N 0x20 #define AD_PORT_MATCHED 0x40 #define AD_PORT_STANDBY 0x80 #define AD_PORT_SELECTED 0x100 #define AD_PORT_MOVED 0x200 #define AD_PORT_CHURNED (AD_PORT_ACTOR_CHURN | AD_PORT_PARTNER_CHURN) /* Port Key definitions * key is determined according to the link speed, duplex and * user key (which is yet not supported) * -------------------------------------------------------------- * Port key | User key (10 bits) | Speed (5 bits) | Duplex| * -------------------------------------------------------------- * |15 6|5 1|0 */ #define AD_DUPLEX_KEY_MASKS 0x1 #define AD_SPEED_KEY_MASKS 0x3E #define AD_USER_KEY_MASKS 0xFFC0 enum ad_link_speed_type { AD_LINK_SPEED_1MBPS = 1, AD_LINK_SPEED_10MBPS, AD_LINK_SPEED_100MBPS, AD_LINK_SPEED_1000MBPS, AD_LINK_SPEED_2500MBPS, AD_LINK_SPEED_5000MBPS, AD_LINK_SPEED_10000MBPS, AD_LINK_SPEED_14000MBPS, AD_LINK_SPEED_20000MBPS, AD_LINK_SPEED_25000MBPS, AD_LINK_SPEED_40000MBPS, AD_LINK_SPEED_50000MBPS, AD_LINK_SPEED_56000MBPS, AD_LINK_SPEED_100000MBPS, AD_LINK_SPEED_200000MBPS, AD_LINK_SPEED_400000MBPS, AD_LINK_SPEED_800000MBPS, }; /* compare MAC addresses */ #define MAC_ADDRESS_EQUAL(A, B) \ ether_addr_equal_64bits((const u8 *)A, (const u8 *)B) static const u16 ad_ticks_per_sec = 1000 / AD_TIMER_INTERVAL; static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = { 0x01, 0x80, 0xC2, 0x00, 0x00, 0x02 }; /* ================= main 802.3ad protocol functions ================== */ static int ad_lacpdu_send(struct port *port); static int ad_marker_send(struct port *port, struct bond_marker *marker); static void ad_mux_machine(struct port *port, bool *update_slave_arr); static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port); static void ad_tx_machine(struct port *port); static void ad_periodic_machine(struct port *port, struct bond_params *bond_params); static void ad_port_selection_logic(struct port *port, bool *update_slave_arr); static void ad_agg_selection_logic(struct aggregator *aggregator, bool *update_slave_arr); static void ad_clear_agg(struct aggregator *aggregator); static void ad_initialize_agg(struct aggregator *aggregator); static void ad_initialize_port(struct port *port, int lacp_fast); static void ad_enable_collecting(struct port *port); static void ad_disable_distributing(struct port *port, bool *update_slave_arr); static void ad_enable_collecting_distributing(struct port *port, bool *update_slave_arr); static void ad_disable_collecting_distributing(struct port *port, bool *update_slave_arr); static void ad_marker_info_received(struct bond_marker *marker_info, struct port *port); static void ad_marker_response_received(struct bond_marker *marker, struct port *port); static void ad_update_actor_keys(struct port *port, bool reset); /* ================= api to bonding and kernel code ================== */ /** * __get_bond_by_port - get the port's bonding struct * @port: the port we're looking at * * Return @port's bonding struct, or %NULL if it can't be found. */ static inline struct bonding *__get_bond_by_port(struct port *port) { if (port->slave == NULL) return NULL; return bond_get_bond_by_slave(port->slave); } /** * __get_first_agg - get the first aggregator in the bond * @port: the port we're looking at * * Return the aggregator of the first slave in @bond, or %NULL if it can't be * found. * The caller must hold RCU or RTNL lock. */ static inline struct aggregator *__get_first_agg(struct port *port) { struct bonding *bond = __get_bond_by_port(port); struct slave *first_slave; struct aggregator *agg; /* If there's no bond for this port, or bond has no slaves */ if (bond == NULL) return NULL; rcu_read_lock(); first_slave = bond_first_slave_rcu(bond); agg = first_slave ? &(SLAVE_AD_INFO(first_slave)->aggregator) : NULL; rcu_read_unlock(); return agg; } /** * __agg_has_partner - see if we have a partner * @agg: the agregator we're looking at * * Return nonzero if aggregator has a partner (denoted by a non-zero ether * address for the partner). Return 0 if not. */ static inline int __agg_has_partner(struct aggregator *agg) { return !is_zero_ether_addr(agg->partner_system.mac_addr_value); } /** * __disable_distributing_port - disable the port's slave for distributing. * Port will still be able to collect. * @port: the port we're looking at * * This will disable only distributing on the port's slave. */ static void __disable_distributing_port(struct port *port) { bond_set_slave_tx_disabled_flags(port->slave, BOND_SLAVE_NOTIFY_LATER); } /** * __enable_collecting_port - enable the port's slave for collecting, * if it's up * @port: the port we're looking at * * This will enable only collecting on the port's slave. */ static void __enable_collecting_port(struct port *port) { struct slave *slave = port->slave; if (slave->link == BOND_LINK_UP && bond_slave_is_up(slave)) bond_set_slave_rx_enabled_flags(slave, BOND_SLAVE_NOTIFY_LATER); } /** * __disable_port - disable the port's slave * @port: the port we're looking at * * This will disable both collecting and distributing on the port's slave. */ static inline void __disable_port(struct port *port) { bond_set_slave_inactive_flags(port->slave, BOND_SLAVE_NOTIFY_LATER); } /** * __enable_port - enable the port's slave, if it's up * @port: the port we're looking at * * This will enable both collecting and distributing on the port's slave. */ static inline void __enable_port(struct port *port) { struct slave *slave = port->slave; if ((slave->link == BOND_LINK_UP) && bond_slave_is_up(slave)) bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER); } /** * __port_move_to_attached_state - check if port should transition back to attached * state. * @port: the port we're looking at */ static bool __port_move_to_attached_state(struct port *port) { if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY) || !(port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) || !(port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION)) port->sm_mux_state = AD_MUX_ATTACHED; return port->sm_mux_state == AD_MUX_ATTACHED; } /** * __port_is_collecting_distributing - check if the port's slave is in the * combined collecting/distributing state * @port: the port we're looking at */ static int __port_is_collecting_distributing(struct port *port) { return bond_is_active_slave(port->slave); } /** * __get_agg_selection_mode - get the aggregator selection mode * @port: the port we're looking at * * Get the aggregator selection mode. Can be %STABLE, %BANDWIDTH or %COUNT. */ static inline u32 __get_agg_selection_mode(struct port *port) { struct bonding *bond = __get_bond_by_port(port); if (bond == NULL) return BOND_AD_STABLE; return bond->params.ad_select; } /** * __check_agg_selection_timer - check if the selection timer has expired * @port: the port we're looking at */ static inline int __check_agg_selection_timer(struct port *port) { struct bonding *bond = __get_bond_by_port(port); if (bond == NULL) return 0; return atomic_read(&BOND_AD_INFO(bond).agg_select_timer) ? 1 : 0; } /** * __get_link_speed - get a port's speed * @port: the port we're looking at * * Return @port's speed in 802.3ad enum format. i.e. one of: * 0, * %AD_LINK_SPEED_10MBPS, * %AD_LINK_SPEED_100MBPS, * %AD_LINK_SPEED_1000MBPS, * %AD_LINK_SPEED_2500MBPS, * %AD_LINK_SPEED_5000MBPS, * %AD_LINK_SPEED_10000MBPS * %AD_LINK_SPEED_14000MBPS, * %AD_LINK_SPEED_20000MBPS * %AD_LINK_SPEED_25000MBPS * %AD_LINK_SPEED_40000MBPS * %AD_LINK_SPEED_50000MBPS * %AD_LINK_SPEED_56000MBPS * %AD_LINK_SPEED_100000MBPS * %AD_LINK_SPEED_200000MBPS * %AD_LINK_SPEED_400000MBPS * %AD_LINK_SPEED_800000MBPS */ static u16 __get_link_speed(struct port *port) { struct slave *slave = port->slave; u16 speed; /* this if covers only a special case: when the configuration starts * with link down, it sets the speed to 0. * This is done in spite of the fact that the e100 driver reports 0 * to be compatible with MVT in the future. */ if (slave->link != BOND_LINK_UP) speed = 0; else { switch (slave->speed) { case SPEED_10: speed = AD_LINK_SPEED_10MBPS; break; case SPEED_100: speed = AD_LINK_SPEED_100MBPS; break; case SPEED_1000: speed = AD_LINK_SPEED_1000MBPS; break; case SPEED_2500: speed = AD_LINK_SPEED_2500MBPS; break; case SPEED_5000: speed = AD_LINK_SPEED_5000MBPS; break; case SPEED_10000: speed = AD_LINK_SPEED_10000MBPS; break; case SPEED_14000: speed = AD_LINK_SPEED_14000MBPS; break; case SPEED_20000: speed = AD_LINK_SPEED_20000MBPS; break; case SPEED_25000: speed = AD_LINK_SPEED_25000MBPS; break; case SPEED_40000: speed = AD_LINK_SPEED_40000MBPS; break; case SPEED_50000: speed = AD_LINK_SPEED_50000MBPS; break; case SPEED_56000: speed = AD_LINK_SPEED_56000MBPS; break; case SPEED_100000: speed = AD_LINK_SPEED_100000MBPS; break; case SPEED_200000: speed = AD_LINK_SPEED_200000MBPS; break; case SPEED_400000: speed = AD_LINK_SPEED_400000MBPS; break; case SPEED_800000: speed = AD_LINK_SPEED_800000MBPS; break; default: /* unknown speed value from ethtool. shouldn't happen */ if (slave->speed != SPEED_UNKNOWN) pr_err_once("%s: (slave %s): unknown ethtool speed (%d) for port %d (set it to 0)\n", slave->bond->dev->name, slave->dev->name, slave->speed, port->actor_port_number); speed = 0; break; } } slave_dbg(slave->bond->dev, slave->dev, "Port %d Received link speed %d update from adapter\n", port->actor_port_number, speed); return speed; } /** * __get_duplex - get a port's duplex * @port: the port we're looking at * * Return @port's duplex in 802.3ad bitmask format. i.e.: * 0x01 if in full duplex * 0x00 otherwise */ static u8 __get_duplex(struct port *port) { struct slave *slave = port->slave; u8 retval = 0x0; /* handling a special case: when the configuration starts with * link down, it sets the duplex to 0. */ if (slave->link == BOND_LINK_UP) { switch (slave->duplex) { case DUPLEX_FULL: retval = 0x1; slave_dbg(slave->bond->dev, slave->dev, "Port %d Received status full duplex update from adapter\n", port->actor_port_number); break; case DUPLEX_HALF: default: retval = 0x0; slave_dbg(slave->bond->dev, slave->dev, "Port %d Received status NOT full duplex update from adapter\n", port->actor_port_number); break; } } return retval; } static void __ad_actor_update_port(struct port *port) { const struct bonding *bond = bond_get_bond_by_slave(port->slave); port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr; port->actor_system_priority = BOND_AD_INFO(bond).system.sys_priority; } /* Conversions */ /** * __ad_timer_to_ticks - convert a given timer type to AD module ticks * @timer_type: which timer to operate * @par: timer parameter. see below * * If @timer_type is %current_while_timer, @par indicates long/short timer. * If @timer_type is %periodic_timer, @par is one of %FAST_PERIODIC_TIME, * %SLOW_PERIODIC_TIME. */ static u16 __ad_timer_to_ticks(u16 timer_type, u16 par) { u16 retval = 0; /* to silence the compiler */ switch (timer_type) { case AD_CURRENT_WHILE_TIMER: /* for rx machine usage */ if (par) retval = (AD_SHORT_TIMEOUT_TIME*ad_ticks_per_sec); else retval = (AD_LONG_TIMEOUT_TIME*ad_ticks_per_sec); break; case AD_ACTOR_CHURN_TIMER: /* for local churn machine */ retval = (AD_CHURN_DETECTION_TIME*ad_ticks_per_sec); break; case AD_PERIODIC_TIMER: /* for periodic machine */ retval = (par*ad_ticks_per_sec); /* long timeout */ break; case AD_PARTNER_CHURN_TIMER: /* for remote churn machine */ retval = (AD_CHURN_DETECTION_TIME*ad_ticks_per_sec); break; case AD_WAIT_WHILE_TIMER: /* for selection machine */ retval = (AD_AGGREGATE_WAIT_TIME*ad_ticks_per_sec); break; } return retval; } /* ================= ad_rx_machine helper functions ================== */ /** * __choose_matched - update a port's matched variable from a received lacpdu * @lacpdu: the lacpdu we've received * @port: the port we're looking at * * Update the value of the matched variable, using parameter values from a * newly received lacpdu. Parameter values for the partner carried in the * received PDU are compared with the corresponding operational parameter * values for the actor. Matched is set to TRUE if all of these parameters * match and the PDU parameter partner_state.aggregation has the same value as * actor_oper_port_state.aggregation and lacp will actively maintain the link * in the aggregation. Matched is also set to TRUE if the value of * actor_state.aggregation in the received PDU is set to FALSE, i.e., indicates * an individual link and lacp will actively maintain the link. Otherwise, * matched is set to FALSE. LACP is considered to be actively maintaining the * link if either the PDU's actor_state.lacp_activity variable is TRUE or both * the actor's actor_oper_port_state.lacp_activity and the PDU's * partner_state.lacp_activity variables are TRUE. * * Note: the AD_PORT_MATCHED "variable" is not specified by 802.3ad; it is * used here to implement the language from 802.3ad 43.4.9 that requires * recordPDU to "match" the LACPDU parameters to the stored values. */ static void __choose_matched(struct lacpdu *lacpdu, struct port *port) { /* check if all parameters are alike * or this is individual link(aggregation == FALSE) * then update the state machine Matched variable. */ if (((ntohs(lacpdu->partner_port) == port->actor_port_number) && (ntohs(lacpdu->partner_port_priority) == port->actor_port_priority) && MAC_ADDRESS_EQUAL(&(lacpdu->partner_system), &(port->actor_system)) && (ntohs(lacpdu->partner_system_priority) == port->actor_system_priority) && (ntohs(lacpdu->partner_key) == port->actor_oper_port_key) && ((lacpdu->partner_state & LACP_STATE_AGGREGATION) == (port->actor_oper_port_state & LACP_STATE_AGGREGATION))) || ((lacpdu->actor_state & LACP_STATE_AGGREGATION) == 0) ) { port->sm_vars |= AD_PORT_MATCHED; } else { port->sm_vars &= ~AD_PORT_MATCHED; } } /** * __record_pdu - record parameters from a received lacpdu * @lacpdu: the lacpdu we've received * @port: the port we're looking at * * Record the parameter values for the Actor carried in a received lacpdu as * the current partner operational parameter values and sets * actor_oper_port_state.defaulted to FALSE. */ static void __record_pdu(struct lacpdu *lacpdu, struct port *port) { if (lacpdu && port) { struct port_params *partner = &port->partner_oper; __choose_matched(lacpdu, port); /* record the new parameter values for the partner * operational */ partner->port_number = ntohs(lacpdu->actor_port); partner->port_priority = ntohs(lacpdu->actor_port_priority); partner->system = lacpdu->actor_system; partner->system_priority = ntohs(lacpdu->actor_system_priority); partner->key = ntohs(lacpdu->actor_key); partner->port_state = lacpdu->actor_state; /* set actor_oper_port_state.defaulted to FALSE */ port->actor_oper_port_state &= ~LACP_STATE_DEFAULTED; /* set the partner sync. to on if the partner is sync, * and the port is matched */ if ((port->sm_vars & AD_PORT_MATCHED) && (lacpdu->actor_state & LACP_STATE_SYNCHRONIZATION)) { partner->port_state |= LACP_STATE_SYNCHRONIZATION; slave_dbg(port->slave->bond->dev, port->slave->dev, "partner sync=1\n"); } else { partner->port_state &= ~LACP_STATE_SYNCHRONIZATION; slave_dbg(port->slave->bond->dev, port->slave->dev, "partner sync=0\n"); } } } /** * __record_default - record default parameters * @port: the port we're looking at * * This function records the default parameter values for the partner carried * in the Partner Admin parameters as the current partner operational parameter * values and sets actor_oper_port_state.defaulted to TRUE. */ static void __record_default(struct port *port) { if (port) { /* record the partner admin parameters */ memcpy(&port->partner_oper, &port->partner_admin, sizeof(struct port_params)); /* set actor_oper_port_state.defaulted to true */ port->actor_oper_port_state |= LACP_STATE_DEFAULTED; } } /** * __update_selected - update a port's Selected variable from a received lacpdu * @lacpdu: the lacpdu we've received * @port: the port we're looking at * * Update the value of the selected variable, using parameter values from a * newly received lacpdu. The parameter values for the Actor carried in the * received PDU are compared with the corresponding operational parameter * values for the ports partner. If one or more of the comparisons shows that * the value(s) received in the PDU differ from the current operational values, * then selected is set to FALSE and actor_oper_port_state.synchronization is * set to out_of_sync. Otherwise, selected remains unchanged. */ static void __update_selected(struct lacpdu *lacpdu, struct port *port) { if (lacpdu && port) { const struct port_params *partner = &port->partner_oper; /* check if any parameter is different then * update the state machine selected variable. */ if (ntohs(lacpdu->actor_port) != partner->port_number || ntohs(lacpdu->actor_port_priority) != partner->port_priority || !MAC_ADDRESS_EQUAL(&lacpdu->actor_system, &partner->system) || ntohs(lacpdu->actor_system_priority) != partner->system_priority || ntohs(lacpdu->actor_key) != partner->key || (lacpdu->actor_state & LACP_STATE_AGGREGATION) != (partner->port_state & LACP_STATE_AGGREGATION)) { port->sm_vars &= ~AD_PORT_SELECTED; } } } /** * __update_default_selected - update a port's Selected variable from Partner * @port: the port we're looking at * * This function updates the value of the selected variable, using the partner * administrative parameter values. The administrative values are compared with * the corresponding operational parameter values for the partner. If one or * more of the comparisons shows that the administrative value(s) differ from * the current operational values, then Selected is set to FALSE and * actor_oper_port_state.synchronization is set to OUT_OF_SYNC. Otherwise, * Selected remains unchanged. */ static void __update_default_selected(struct port *port) { if (port) { const struct port_params *admin = &port->partner_admin; const struct port_params *oper = &port->partner_oper; /* check if any parameter is different then * update the state machine selected variable. */ if (admin->port_number != oper->port_number || admin->port_priority != oper->port_priority || !MAC_ADDRESS_EQUAL(&admin->system, &oper->system) || admin->system_priority != oper->system_priority || admin->key != oper->key || (admin->port_state & LACP_STATE_AGGREGATION) != (oper->port_state & LACP_STATE_AGGREGATION)) { port->sm_vars &= ~AD_PORT_SELECTED; } } } /** * __update_ntt - update a port's ntt variable from a received lacpdu * @lacpdu: the lacpdu we've received * @port: the port we're looking at * * Updates the value of the ntt variable, using parameter values from a newly * received lacpdu. The parameter values for the partner carried in the * received PDU are compared with the corresponding operational parameter * values for the Actor. If one or more of the comparisons shows that the * value(s) received in the PDU differ from the current operational values, * then ntt is set to TRUE. Otherwise, ntt remains unchanged. */ static void __update_ntt(struct lacpdu *lacpdu, struct port *port) { /* validate lacpdu and port */ if (lacpdu && port) { /* check if any parameter is different then * update the port->ntt. */ if ((ntohs(lacpdu->partner_port) != port->actor_port_number) || (ntohs(lacpdu->partner_port_priority) != port->actor_port_priority) || !MAC_ADDRESS_EQUAL(&(lacpdu->partner_system), &(port->actor_system)) || (ntohs(lacpdu->partner_system_priority) != port->actor_system_priority) || (ntohs(lacpdu->partner_key) != port->actor_oper_port_key) || ((lacpdu->partner_state & LACP_STATE_LACP_ACTIVITY) != (port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY)) || ((lacpdu->partner_state & LACP_STATE_LACP_TIMEOUT) != (port->actor_oper_port_state & LACP_STATE_LACP_TIMEOUT)) || ((lacpdu->partner_state & LACP_STATE_SYNCHRONIZATION) != (port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION)) || ((lacpdu->partner_state & LACP_STATE_AGGREGATION) != (port->actor_oper_port_state & LACP_STATE_AGGREGATION)) ) { port->ntt = true; } } } /** * __agg_ports_are_ready - check if all ports in an aggregator are ready * @aggregator: the aggregator we're looking at * */ static int __agg_ports_are_ready(struct aggregator *aggregator) { struct port *port; int retval = 1; if (aggregator) { /* scan all ports in this aggregator to verfy if they are * all ready. */ for (port = aggregator->lag_ports; port; port = port->next_port_in_aggregator) { if (!(port->sm_vars & AD_PORT_READY_N)) { retval = 0; break; } } } return retval; } /** * __set_agg_ports_ready - set value of Ready bit in all ports of an aggregator * @aggregator: the aggregator we're looking at * @val: Should the ports' ready bit be set on or off * */ static void __set_agg_ports_ready(struct aggregator *aggregator, int val) { struct port *port; for (port = aggregator->lag_ports; port; port = port->next_port_in_aggregator) { if (val) port->sm_vars |= AD_PORT_READY; else port->sm_vars &= ~AD_PORT_READY; } } static int __agg_active_ports(struct aggregator *agg) { struct port *port; int active = 0; for (port = agg->lag_ports; port; port = port->next_port_in_aggregator) { if (port->is_enabled) active++; } return active; } /** * __get_agg_bandwidth - get the total bandwidth of an aggregator * @aggregator: the aggregator we're looking at * */ static u32 __get_agg_bandwidth(struct aggregator *aggregator) { int nports = __agg_active_ports(aggregator); u32 bandwidth = 0; if (nports) { switch (__get_link_speed(aggregator->lag_ports)) { case AD_LINK_SPEED_1MBPS: bandwidth = nports; break; case AD_LINK_SPEED_10MBPS: bandwidth = nports * 10; break; case AD_LINK_SPEED_100MBPS: bandwidth = nports * 100; break; case AD_LINK_SPEED_1000MBPS: bandwidth = nports * 1000; break; case AD_LINK_SPEED_2500MBPS: bandwidth = nports * 2500; break; case AD_LINK_SPEED_5000MBPS: bandwidth = nports * 5000; break; case AD_LINK_SPEED_10000MBPS: bandwidth = nports * 10000; break; case AD_LINK_SPEED_14000MBPS: bandwidth = nports * 14000; break; case AD_LINK_SPEED_20000MBPS: bandwidth = nports * 20000; break; case AD_LINK_SPEED_25000MBPS: bandwidth = nports * 25000; break; case AD_LINK_SPEED_40000MBPS: bandwidth = nports * 40000; break; case AD_LINK_SPEED_50000MBPS: bandwidth = nports * 50000; break; case AD_LINK_SPEED_56000MBPS: bandwidth = nports * 56000; break; case AD_LINK_SPEED_100000MBPS: bandwidth = nports * 100000; break; case AD_LINK_SPEED_200000MBPS: bandwidth = nports * 200000; break; case AD_LINK_SPEED_400000MBPS: bandwidth = nports * 400000; break; case AD_LINK_SPEED_800000MBPS: bandwidth = nports * 800000; break; default: bandwidth = 0; /* to silence the compiler */ } } return bandwidth; } /** * __get_active_agg - get the current active aggregator * @aggregator: the aggregator we're looking at * * Caller must hold RCU lock. */ static struct aggregator *__get_active_agg(struct aggregator *aggregator) { struct bonding *bond = aggregator->slave->bond; struct list_head *iter; struct slave *slave; bond_for_each_slave_rcu(bond, slave, iter) if (SLAVE_AD_INFO(slave)->aggregator.is_active) return &(SLAVE_AD_INFO(slave)->aggregator); return NULL; } /** * __update_lacpdu_from_port - update a port's lacpdu fields * @port: the port we're looking at */ static inline void __update_lacpdu_from_port(struct port *port) { struct lacpdu *lacpdu = &port->lacpdu; const struct port_params *partner = &port->partner_oper; /* update current actual Actor parameters * lacpdu->subtype initialized * lacpdu->version_number initialized * lacpdu->tlv_type_actor_info initialized * lacpdu->actor_information_length initialized */ lacpdu->actor_system_priority = htons(port->actor_system_priority); lacpdu->actor_system = port->actor_system; lacpdu->actor_key = htons(port->actor_oper_port_key); lacpdu->actor_port_priority = htons(port->actor_port_priority); lacpdu->actor_port = htons(port->actor_port_number); lacpdu->actor_state = port->actor_oper_port_state; slave_dbg(port->slave->bond->dev, port->slave->dev, "update lacpdu: actor port state %x\n", port->actor_oper_port_state); /* lacpdu->reserved_3_1 initialized * lacpdu->tlv_type_partner_info initialized * lacpdu->partner_information_length initialized */ lacpdu->partner_system_priority = htons(partner->system_priority); lacpdu->partner_system = partner->system; lacpdu->partner_key = htons(partner->key); lacpdu->partner_port_priority = htons(partner->port_priority); lacpdu->partner_port = htons(partner->port_number); lacpdu->partner_state = partner->port_state; /* lacpdu->reserved_3_2 initialized * lacpdu->tlv_type_collector_info initialized * lacpdu->collector_information_length initialized * collector_max_delay initialized * reserved_12[12] initialized * tlv_type_terminator initialized * terminator_length initialized * reserved_50[50] initialized */ } /* ================= main 802.3ad protocol code ========================= */ /** * ad_lacpdu_send - send out a lacpdu packet on a given port * @port: the port we're looking at * * Returns: 0 on success * < 0 on error */ static int ad_lacpdu_send(struct port *port) { struct slave *slave = port->slave; struct sk_buff *skb; struct lacpdu_header *lacpdu_header; int length = sizeof(struct lacpdu_header); skb = dev_alloc_skb(length); if (!skb) return -ENOMEM; atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_tx); atomic64_inc(&BOND_AD_INFO(slave->bond).stats.lacpdu_tx); skb->dev = slave->dev; skb_reset_mac_header(skb); skb->network_header = skb->mac_header + ETH_HLEN; skb->protocol = PKT_TYPE_LACPDU; skb->priority = TC_PRIO_CONTROL; lacpdu_header = skb_put(skb, length); ether_addr_copy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr); /* Note: source address is set to be the member's PERMANENT address, * because we use it to identify loopback lacpdus in receive. */ ether_addr_copy(lacpdu_header->hdr.h_source, slave->perm_hwaddr); lacpdu_header->hdr.h_proto = PKT_TYPE_LACPDU; lacpdu_header->lacpdu = port->lacpdu; dev_queue_xmit(skb); return 0; } /** * ad_marker_send - send marker information/response on a given port * @port: the port we're looking at * @marker: marker data to send * * Returns: 0 on success * < 0 on error */ static int ad_marker_send(struct port *port, struct bond_marker *marker) { struct slave *slave = port->slave; struct sk_buff *skb; struct bond_marker_header *marker_header; int length = sizeof(struct bond_marker_header); skb = dev_alloc_skb(length + 16); if (!skb) return -ENOMEM; switch (marker->tlv_type) { case AD_MARKER_INFORMATION_SUBTYPE: atomic64_inc(&SLAVE_AD_INFO(slave)->stats.marker_tx); atomic64_inc(&BOND_AD_INFO(slave->bond).stats.marker_tx); break; case AD_MARKER_RESPONSE_SUBTYPE: atomic64_inc(&SLAVE_AD_INFO(slave)->stats.marker_resp_tx); atomic64_inc(&BOND_AD_INFO(slave->bond).stats.marker_resp_tx); break; } skb_reserve(skb, 16); skb->dev = slave->dev; skb_reset_mac_header(skb); skb->network_header = skb->mac_header + ETH_HLEN; skb->protocol = PKT_TYPE_LACPDU; marker_header = skb_put(skb, length); ether_addr_copy(marker_header->hdr.h_dest, lacpdu_mcast_addr); /* Note: source address is set to be the member's PERMANENT address, * because we use it to identify loopback MARKERs in receive. */ ether_addr_copy(marker_header->hdr.h_source, slave->perm_hwaddr); marker_header->hdr.h_proto = PKT_TYPE_LACPDU; marker_header->marker = *marker; dev_queue_xmit(skb); return 0; } /** * ad_mux_machine - handle a port's mux state machine * @port: the port we're looking at * @update_slave_arr: Does slave array need update? */ static void ad_mux_machine(struct port *port, bool *update_slave_arr) { struct bonding *bond = __get_bond_by_port(port); mux_states_t last_state; /* keep current State Machine state to compare later if it was * changed */ last_state = port->sm_mux_state; if (port->sm_vars & AD_PORT_BEGIN) { port->sm_mux_state = AD_MUX_DETACHED; } else { switch (port->sm_mux_state) { case AD_MUX_DETACHED: if ((port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY)) /* if SELECTED or STANDBY */ port->sm_mux_state = AD_MUX_WAITING; break; case AD_MUX_WAITING: /* if SELECTED == FALSE return to DETACH state */ if (!(port->sm_vars & AD_PORT_SELECTED)) { port->sm_vars &= ~AD_PORT_READY_N; /* in order to withhold the Selection Logic to * check all ports READY_N value every callback * cycle to update ready variable, we check * READY_N and update READY here */ __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); port->sm_mux_state = AD_MUX_DETACHED; break; } /* check if the wait_while_timer expired */ if (port->sm_mux_timer_counter && !(--port->sm_mux_timer_counter)) port->sm_vars |= AD_PORT_READY_N; /* in order to withhold the selection logic to check * all ports READY_N value every callback cycle to * update ready variable, we check READY_N and update * READY here */ __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); /* if the wait_while_timer expired, and the port is * in READY state, move to ATTACHED state */ if ((port->sm_vars & AD_PORT_READY) && !port->sm_mux_timer_counter) port->sm_mux_state = AD_MUX_ATTACHED; break; case AD_MUX_ATTACHED: /* check also if agg_select_timer expired (so the * edable port will take place only after this timer) */ if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { if (port->aggregator->is_active) { int state = AD_MUX_COLLECTING_DISTRIBUTING; if (!bond->params.coupled_control) state = AD_MUX_COLLECTING; port->sm_mux_state = state; } } else if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY)) { /* if UNSELECTED or STANDBY */ port->sm_vars &= ~AD_PORT_READY_N; /* in order to withhold the selection logic to * check all ports READY_N value every callback * cycle to update ready variable, we check * READY_N and update READY here */ __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); port->sm_mux_state = AD_MUX_DETACHED; } else if (port->aggregator->is_active) { port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; } break; case AD_MUX_COLLECTING_DISTRIBUTING: if (!__port_move_to_attached_state(port)) { /* if port state hasn't changed make * sure that a collecting distributing * port in an active aggregator is enabled */ if (port->aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; } } break; case AD_MUX_COLLECTING: if (!__port_move_to_attached_state(port)) { if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && (port->partner_oper.port_state & LACP_STATE_COLLECTING)) { port->sm_mux_state = AD_MUX_DISTRIBUTING; } else { /* If port state hasn't changed, make sure that a collecting * port is enabled for an active aggregator. */ struct slave *slave = port->slave; if (port->aggregator->is_active && bond_is_slave_rx_disabled(slave)) { ad_enable_collecting(port); *update_slave_arr = true; } } } break; case AD_MUX_DISTRIBUTING: if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY) || !(port->partner_oper.port_state & LACP_STATE_COLLECTING) || !(port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) || !(port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION)) { port->sm_mux_state = AD_MUX_COLLECTING; } else { /* if port state hasn't changed make * sure that a collecting distributing * port in an active aggregator is enabled */ if (port->aggregator && port->aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; } } break; default: break; } } /* check if the state machine was changed */ if (port->sm_mux_state != last_state) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Mux Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_mux_state); switch (port->sm_mux_state) { case AD_MUX_DETACHED: port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; ad_disable_collecting_distributing(port, update_slave_arr); port->actor_oper_port_state &= ~LACP_STATE_COLLECTING; port->actor_oper_port_state &= ~LACP_STATE_DISTRIBUTING; port->ntt = true; break; case AD_MUX_WAITING: port->sm_mux_timer_counter = __ad_timer_to_ticks(AD_WAIT_WHILE_TIMER, 0); break; case AD_MUX_ATTACHED: if (port->aggregator->is_active) port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; else port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; port->actor_oper_port_state &= ~LACP_STATE_COLLECTING; port->actor_oper_port_state &= ~LACP_STATE_DISTRIBUTING; ad_disable_collecting_distributing(port, update_slave_arr); port->ntt = true; break; case AD_MUX_COLLECTING_DISTRIBUTING: port->actor_oper_port_state |= LACP_STATE_COLLECTING; port->actor_oper_port_state |= LACP_STATE_DISTRIBUTING; port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; ad_enable_collecting_distributing(port, update_slave_arr); port->ntt = true; break; case AD_MUX_COLLECTING: port->actor_oper_port_state |= LACP_STATE_COLLECTING; port->actor_oper_port_state &= ~LACP_STATE_DISTRIBUTING; port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; ad_enable_collecting(port); ad_disable_distributing(port, update_slave_arr); port->ntt = true; break; case AD_MUX_DISTRIBUTING: port->actor_oper_port_state |= LACP_STATE_DISTRIBUTING; port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; ad_enable_collecting_distributing(port, update_slave_arr); break; default: break; } } } /** * ad_rx_machine - handle a port's rx State Machine * @lacpdu: the lacpdu we've received * @port: the port we're looking at * * If lacpdu arrived, stop previous timer (if exists) and set the next state as * CURRENT. If timer expired set the state machine in the proper state. * In other cases, this function checks if we need to switch to other state. */ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) { rx_states_t last_state; /* keep current State Machine state to compare later if it was * changed */ last_state = port->sm_rx_state; if (lacpdu) { atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.lacpdu_rx); atomic64_inc(&BOND_AD_INFO(port->slave->bond).stats.lacpdu_rx); } /* check if state machine should change state */ /* first, check if port was reinitialized */ if (port->sm_vars & AD_PORT_BEGIN) { port->sm_rx_state = AD_RX_INITIALIZE; port->sm_vars |= AD_PORT_CHURNED; /* check if port is not enabled */ } else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled) port->sm_rx_state = AD_RX_PORT_DISABLED; /* check if new lacpdu arrived */ else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) || (port->sm_rx_state == AD_RX_DEFAULTED) || (port->sm_rx_state == AD_RX_CURRENT))) { if (port->sm_rx_state != AD_RX_CURRENT) port->sm_vars |= AD_PORT_CHURNED; port->sm_rx_timer_counter = 0; port->sm_rx_state = AD_RX_CURRENT; } else { /* if timer is on, and if it is expired */ if (port->sm_rx_timer_counter && !(--port->sm_rx_timer_counter)) { switch (port->sm_rx_state) { case AD_RX_EXPIRED: port->sm_rx_state = AD_RX_DEFAULTED; break; case AD_RX_CURRENT: port->sm_rx_state = AD_RX_EXPIRED; break; default: break; } } else { /* if no lacpdu arrived and no timer is on */ switch (port->sm_rx_state) { case AD_RX_PORT_DISABLED: if (port->is_enabled && (port->sm_vars & AD_PORT_LACP_ENABLED)) port->sm_rx_state = AD_RX_EXPIRED; else if (port->is_enabled && ((port->sm_vars & AD_PORT_LACP_ENABLED) == 0)) port->sm_rx_state = AD_RX_LACP_DISABLED; break; default: break; } } } /* check if the State machine was changed or new lacpdu arrived */ if ((port->sm_rx_state != last_state) || (lacpdu)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Rx Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_rx_state); switch (port->sm_rx_state) { case AD_RX_INITIALIZE: if (!(port->actor_oper_port_key & AD_DUPLEX_KEY_MASKS)) port->sm_vars &= ~AD_PORT_LACP_ENABLED; else port->sm_vars |= AD_PORT_LACP_ENABLED; port->sm_vars &= ~AD_PORT_SELECTED; __record_default(port); port->actor_oper_port_state &= ~LACP_STATE_EXPIRED; port->sm_rx_state = AD_RX_PORT_DISABLED; fallthrough; case AD_RX_PORT_DISABLED: port->sm_vars &= ~AD_PORT_MATCHED; break; case AD_RX_LACP_DISABLED: port->sm_vars &= ~AD_PORT_SELECTED; __record_default(port); port->partner_oper.port_state &= ~LACP_STATE_AGGREGATION; port->sm_vars |= AD_PORT_MATCHED; port->actor_oper_port_state &= ~LACP_STATE_EXPIRED; break; case AD_RX_EXPIRED: /* Reset of the Synchronization flag (Standard 43.4.12) * This reset cause to disable this port in the * COLLECTING_DISTRIBUTING state of the mux machine in * case of EXPIRED even if LINK_DOWN didn't arrive for * the port. */ port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION; port->sm_vars &= ~AD_PORT_MATCHED; port->partner_oper.port_state |= LACP_STATE_LACP_TIMEOUT; port->partner_oper.port_state |= LACP_STATE_LACP_ACTIVITY; port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT)); port->actor_oper_port_state |= LACP_STATE_EXPIRED; port->sm_vars |= AD_PORT_CHURNED; break; case AD_RX_DEFAULTED: __update_default_selected(port); __record_default(port); port->sm_vars |= AD_PORT_MATCHED; port->actor_oper_port_state &= ~LACP_STATE_EXPIRED; break; case AD_RX_CURRENT: /* detect loopback situation */ if (MAC_ADDRESS_EQUAL(&(lacpdu->actor_system), &(port->actor_system))) { slave_err(port->slave->bond->dev, port->slave->dev, "An illegal loopback occurred on slave\n" "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n"); return; } __update_selected(lacpdu, port); __update_ntt(lacpdu, port); __record_pdu(lacpdu, port); port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(port->actor_oper_port_state & LACP_STATE_LACP_TIMEOUT)); port->actor_oper_port_state &= ~LACP_STATE_EXPIRED; break; default: break; } } } /** * ad_churn_machine - handle port churn's state machine * @port: the port we're looking at * */ static void ad_churn_machine(struct port *port) { if (port->sm_vars & AD_PORT_CHURNED) { port->sm_vars &= ~AD_PORT_CHURNED; port->sm_churn_actor_state = AD_CHURN_MONITOR; port->sm_churn_partner_state = AD_CHURN_MONITOR; port->sm_churn_actor_timer_counter = __ad_timer_to_ticks(AD_ACTOR_CHURN_TIMER, 0); port->sm_churn_partner_timer_counter = __ad_timer_to_ticks(AD_PARTNER_CHURN_TIMER, 0); return; } if (port->sm_churn_actor_timer_counter && !(--port->sm_churn_actor_timer_counter) && port->sm_churn_actor_state == AD_CHURN_MONITOR) { if (port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION) { port->sm_churn_actor_state = AD_NO_CHURN; } else { port->churn_actor_count++; port->sm_churn_actor_state = AD_CHURN; } } if (port->sm_churn_partner_timer_counter && !(--port->sm_churn_partner_timer_counter) && port->sm_churn_partner_state == AD_CHURN_MONITOR) { if (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) { port->sm_churn_partner_state = AD_NO_CHURN; } else { port->churn_partner_count++; port->sm_churn_partner_state = AD_CHURN; } } } /** * ad_tx_machine - handle a port's tx state machine * @port: the port we're looking at */ static void ad_tx_machine(struct port *port) { /* check if tx timer expired, to verify that we do not send more than * 3 packets per second */ if (port->sm_tx_timer_counter && !(--port->sm_tx_timer_counter)) { /* check if there is something to send */ if (port->ntt && (port->sm_vars & AD_PORT_LACP_ENABLED)) { __update_lacpdu_from_port(port); if (ad_lacpdu_send(port) >= 0) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Sent LACPDU on port %d\n", port->actor_port_number); /* mark ntt as false, so it will not be sent * again until demanded */ port->ntt = false; } } /* restart tx timer(to verify that we will not exceed * AD_MAX_TX_IN_SECOND */ port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; } } /** * ad_periodic_machine - handle a port's periodic state machine * @port: the port we're looking at * @bond_params: bond parameters we will use * * Turn ntt flag on priodically to perform periodic transmission of lacpdu's. */ static void ad_periodic_machine(struct port *port, struct bond_params *bond_params) { periodic_states_t last_state; /* keep current state machine state to compare later if it was changed */ last_state = port->sm_periodic_state; /* check if port was reinitialized */ if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) || (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) || !bond_params->lacp_active) { port->sm_periodic_state = AD_NO_PERIODIC; } /* check if state machine should change state */ else if (port->sm_periodic_timer_counter) { /* check if periodic state machine expired */ if (!(--port->sm_periodic_timer_counter)) { /* if expired then do tx */ port->sm_periodic_state = AD_PERIODIC_TX; } else { /* If not expired, check if there is some new timeout * parameter from the partner state */ switch (port->sm_periodic_state) { case AD_FAST_PERIODIC: if (!(port->partner_oper.port_state & LACP_STATE_LACP_TIMEOUT)) port->sm_periodic_state = AD_SLOW_PERIODIC; break; case AD_SLOW_PERIODIC: if ((port->partner_oper.port_state & LACP_STATE_LACP_TIMEOUT)) { port->sm_periodic_timer_counter = 0; port->sm_periodic_state = AD_PERIODIC_TX; } break; default: break; } } } else { switch (port->sm_periodic_state) { case AD_NO_PERIODIC: port->sm_periodic_state = AD_FAST_PERIODIC; break; case AD_PERIODIC_TX: if (!(port->partner_oper.port_state & LACP_STATE_LACP_TIMEOUT)) port->sm_periodic_state = AD_SLOW_PERIODIC; else port->sm_periodic_state = AD_FAST_PERIODIC; break; default: break; } } /* check if the state machine was changed */ if (port->sm_periodic_state != last_state) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Periodic Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_periodic_state); switch (port->sm_periodic_state) { case AD_NO_PERIODIC: port->sm_periodic_timer_counter = 0; break; case AD_FAST_PERIODIC: /* decrement 1 tick we lost in the PERIODIC_TX cycle */ port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_FAST_PERIODIC_TIME))-1; break; case AD_SLOW_PERIODIC: /* decrement 1 tick we lost in the PERIODIC_TX cycle */ port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_SLOW_PERIODIC_TIME))-1; break; case AD_PERIODIC_TX: port->ntt = true; break; default: break; } } } /** * ad_port_selection_logic - select aggregation groups * @port: the port we're looking at * @update_slave_arr: Does slave array need update? * * Select aggregation groups, and assign each port for it's aggregetor. The * selection logic is called in the inititalization (after all the handshkes), * and after every lacpdu receive (if selected is off). */ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) { struct aggregator *aggregator, *free_aggregator = NULL, *temp_aggregator; struct port *last_port = NULL, *curr_port; struct list_head *iter; struct bonding *bond; struct slave *slave; int found = 0; /* if the port is already Selected, do nothing */ if (port->sm_vars & AD_PORT_SELECTED) return; bond = __get_bond_by_port(port); /* if the port is connected to other aggregator, detach it */ if (port->aggregator) { /* detach the port from its former aggregator */ temp_aggregator = port->aggregator; for (curr_port = temp_aggregator->lag_ports; curr_port; last_port = curr_port, curr_port = curr_port->next_port_in_aggregator) { if (curr_port == port) { temp_aggregator->num_of_ports--; /* if it is the first port attached to the * aggregator */ if (!last_port) { temp_aggregator->lag_ports = port->next_port_in_aggregator; } else { /* not the first port attached to the * aggregator */ last_port->next_port_in_aggregator = port->next_port_in_aggregator; } /* clear the port's relations to this * aggregator */ port->aggregator = NULL; port->next_port_in_aggregator = NULL; port->actor_port_aggregator_identifier = 0; slave_dbg(bond->dev, port->slave->dev, "Port %d left LAG %d\n", port->actor_port_number, temp_aggregator->aggregator_identifier); /* if the aggregator is empty, clear its * parameters, and set it ready to be attached */ if (!temp_aggregator->lag_ports) ad_clear_agg(temp_aggregator); break; } } if (!curr_port) { /* meaning: the port was related to an aggregator * but was not on the aggregator port list */ net_warn_ratelimited("%s: (slave %s): Warning: Port %d was related to aggregator %d but was not on its port list\n", port->slave->bond->dev->name, port->slave->dev->name, port->actor_port_number, port->aggregator->aggregator_identifier); } } /* search on all aggregators for a suitable aggregator for this port */ bond_for_each_slave(bond, slave, iter) { aggregator = &(SLAVE_AD_INFO(slave)->aggregator); /* keep a free aggregator for later use(if needed) */ if (!aggregator->lag_ports) { if (!free_aggregator) free_aggregator = aggregator; continue; } /* check if current aggregator suits us */ if (((aggregator->actor_oper_aggregator_key == port->actor_oper_port_key) && /* if all parameters match AND */ MAC_ADDRESS_EQUAL(&(aggregator->partner_system), &(port->partner_oper.system)) && (aggregator->partner_system_priority == port->partner_oper.system_priority) && (aggregator->partner_oper_aggregator_key == port->partner_oper.key) ) && ((__agg_has_partner(aggregator) && /* partner answers */ !aggregator->is_individual) /* but is not individual OR */ ) ) { /* attach to the founded aggregator */ port->aggregator = aggregator; port->actor_port_aggregator_identifier = port->aggregator->aggregator_identifier; port->next_port_in_aggregator = aggregator->lag_ports; port->aggregator->num_of_ports++; aggregator->lag_ports = port; slave_dbg(bond->dev, slave->dev, "Port %d joined LAG %d (existing LAG)\n", port->actor_port_number, port->aggregator->aggregator_identifier); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; found = 1; break; } } /* the port couldn't find an aggregator - attach it to a new * aggregator */ if (!found) { if (free_aggregator) { /* assign port a new aggregator */ port->aggregator = free_aggregator; port->actor_port_aggregator_identifier = port->aggregator->aggregator_identifier; /* update the new aggregator's parameters * if port was responsed from the end-user */ if (port->actor_oper_port_key & AD_DUPLEX_KEY_MASKS) /* if port is full duplex */ port->aggregator->is_individual = false; else port->aggregator->is_individual = true; port->aggregator->actor_admin_aggregator_key = port->actor_admin_port_key; port->aggregator->actor_oper_aggregator_key = port->actor_oper_port_key; port->aggregator->partner_system = port->partner_oper.system; port->aggregator->partner_system_priority = port->partner_oper.system_priority; port->aggregator->partner_oper_aggregator_key = port->partner_oper.key; port->aggregator->receive_state = 1; port->aggregator->transmit_state = 1; port->aggregator->lag_ports = port; port->aggregator->num_of_ports++; /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; slave_dbg(bond->dev, port->slave->dev, "Port %d joined LAG %d (new LAG)\n", port->actor_port_number, port->aggregator->aggregator_identifier); } else { slave_err(bond->dev, port->slave->dev, "Port %d did not find a suitable aggregator\n", port->actor_port_number); return; } } /* if all aggregator's ports are READY_N == TRUE, set ready=TRUE * in all aggregator's ports, else set ready=FALSE in all * aggregator's ports */ __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); aggregator = __get_first_agg(port); ad_agg_selection_logic(aggregator, update_slave_arr); if (!port->aggregator->is_active) port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; } /* Decide if "agg" is a better choice for the new active aggregator that * the current best, according to the ad_select policy. */ static struct aggregator *ad_agg_selection_test(struct aggregator *best, struct aggregator *curr) { /* 0. If no best, select current. * * 1. If the current agg is not individual, and the best is * individual, select current. * * 2. If current agg is individual and the best is not, keep best. * * 3. Therefore, current and best are both individual or both not * individual, so: * * 3a. If current agg partner replied, and best agg partner did not, * select current. * * 3b. If current agg partner did not reply and best agg partner * did reply, keep best. * * 4. Therefore, current and best both have partner replies or * both do not, so perform selection policy: * * BOND_AD_COUNT: Select by count of ports. If count is equal, * select by bandwidth. * * BOND_AD_STABLE, BOND_AD_BANDWIDTH: Select by bandwidth. */ if (!best) return curr; if (!curr->is_individual && best->is_individual) return curr; if (curr->is_individual && !best->is_individual) return best; if (__agg_has_partner(curr) && !__agg_has_partner(best)) return curr; if (!__agg_has_partner(curr) && __agg_has_partner(best)) return best; switch (__get_agg_selection_mode(curr->lag_ports)) { case BOND_AD_COUNT: if (__agg_active_ports(curr) > __agg_active_ports(best)) return curr; if (__agg_active_ports(curr) < __agg_active_ports(best)) return best; fallthrough; case BOND_AD_STABLE: case BOND_AD_BANDWIDTH: if (__get_agg_bandwidth(curr) > __get_agg_bandwidth(best)) return curr; break; default: net_warn_ratelimited("%s: (slave %s): Impossible agg select mode %d\n", curr->slave->bond->dev->name, curr->slave->dev->name, __get_agg_selection_mode(curr->lag_ports)); break; } return best; } static int agg_device_up(const struct aggregator *agg) { struct port *port = agg->lag_ports; if (!port) return 0; for (port = agg->lag_ports; port; port = port->next_port_in_aggregator) { if (netif_running(port->slave->dev) && netif_carrier_ok(port->slave->dev)) return 1; } return 0; } /** * ad_agg_selection_logic - select an aggregation group for a team * @agg: the aggregator we're looking at * @update_slave_arr: Does slave array need update? * * It is assumed that only one aggregator may be selected for a team. * * The logic of this function is to select the aggregator according to * the ad_select policy: * * BOND_AD_STABLE: select the aggregator with the most ports attached to * it, and to reselect the active aggregator only if the previous * aggregator has no more ports related to it. * * BOND_AD_BANDWIDTH: select the aggregator with the highest total * bandwidth, and reselect whenever a link state change takes place or the * set of slaves in the bond changes. * * BOND_AD_COUNT: select the aggregator with largest number of ports * (slaves), and reselect whenever a link state change takes place or the * set of slaves in the bond changes. * * FIXME: this function MUST be called with the first agg in the bond, or * __get_active_agg() won't work correctly. This function should be better * called with the bond itself, and retrieve the first agg from it. */ static void ad_agg_selection_logic(struct aggregator *agg, bool *update_slave_arr) { struct aggregator *best, *active, *origin; struct bonding *bond = agg->slave->bond; struct list_head *iter; struct slave *slave; struct port *port; rcu_read_lock(); origin = agg; active = __get_active_agg(agg); best = (active && agg_device_up(active)) ? active : NULL; bond_for_each_slave_rcu(bond, slave, iter) { agg = &(SLAVE_AD_INFO(slave)->aggregator); agg->is_active = 0; if (__agg_active_ports(agg) && agg_device_up(agg)) best = ad_agg_selection_test(best, agg); } if (best && __get_agg_selection_mode(best->lag_ports) == BOND_AD_STABLE) { /* For the STABLE policy, don't replace the old active * aggregator if it's still active (it has an answering * partner) or if both the best and active don't have an * answering partner. */ if (active && active->lag_ports && __agg_active_ports(active) && (__agg_has_partner(active) || (!__agg_has_partner(active) && !__agg_has_partner(best)))) { if (!(!active->actor_oper_aggregator_key && best->actor_oper_aggregator_key)) { best = NULL; active->is_active = 1; } } } if (best && (best == active)) { best = NULL; active->is_active = 1; } /* if there is new best aggregator, activate it */ if (best) { netdev_dbg(bond->dev, "(slave %s): best Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", best->slave ? best->slave->dev->name : "NULL", best->aggregator_identifier, best->num_of_ports, best->actor_oper_aggregator_key, best->partner_oper_aggregator_key, best->is_individual, best->is_active); netdev_dbg(bond->dev, "(slave %s): best ports %p slave %p\n", best->slave ? best->slave->dev->name : "NULL", best->lag_ports, best->slave); bond_for_each_slave_rcu(bond, slave, iter) { agg = &(SLAVE_AD_INFO(slave)->aggregator); slave_dbg(bond->dev, slave->dev, "Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", agg->aggregator_identifier, agg->num_of_ports, agg->actor_oper_aggregator_key, agg->partner_oper_aggregator_key, agg->is_individual, agg->is_active); } /* check if any partner replies */ if (best->is_individual) net_warn_ratelimited("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n", bond->dev->name); best->is_active = 1; netdev_dbg(bond->dev, "(slave %s): LAG %d chosen as the active LAG\n", best->slave ? best->slave->dev->name : "NULL", best->aggregator_identifier); netdev_dbg(bond->dev, "(slave %s): Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", best->slave ? best->slave->dev->name : "NULL", best->aggregator_identifier, best->num_of_ports, best->actor_oper_aggregator_key, best->partner_oper_aggregator_key, best->is_individual, best->is_active); /* disable the ports that were related to the former * active_aggregator */ if (active) { for (port = active->lag_ports; port; port = port->next_port_in_aggregator) { __disable_port(port); } } /* Slave array needs update. */ *update_slave_arr = true; } /* if the selected aggregator is of join individuals * (partner_system is NULL), enable their ports */ active = __get_active_agg(origin); if (active) { if (!__agg_has_partner(active)) { for (port = active->lag_ports; port; port = port->next_port_in_aggregator) { __enable_port(port); } *update_slave_arr = true; } } rcu_read_unlock(); bond_3ad_set_carrier(bond); } /** * ad_clear_agg - clear a given aggregator's parameters * @aggregator: the aggregator we're looking at */ static void ad_clear_agg(struct aggregator *aggregator) { if (aggregator) { aggregator->is_individual = false; aggregator->actor_admin_aggregator_key = 0; aggregator->actor_oper_aggregator_key = 0; eth_zero_addr(aggregator->partner_system.mac_addr_value); aggregator->partner_system_priority = 0; aggregator->partner_oper_aggregator_key = 0; aggregator->receive_state = 0; aggregator->transmit_state = 0; aggregator->lag_ports = NULL; aggregator->is_active = 0; aggregator->num_of_ports = 0; pr_debug("%s: LAG %d was cleared\n", aggregator->slave ? aggregator->slave->dev->name : "NULL", aggregator->aggregator_identifier); } } /** * ad_initialize_agg - initialize a given aggregator's parameters * @aggregator: the aggregator we're looking at */ static void ad_initialize_agg(struct aggregator *aggregator) { if (aggregator) { ad_clear_agg(aggregator); eth_zero_addr(aggregator->aggregator_mac_address.mac_addr_value); aggregator->aggregator_identifier = 0; aggregator->slave = NULL; } } /** * ad_initialize_port - initialize a given port's parameters * @port: the port we're looking at * @lacp_fast: boolean. whether fast periodic should be used */ static void ad_initialize_port(struct port *port, int lacp_fast) { static const struct port_params tmpl = { .system_priority = 0xffff, .key = 1, .port_number = 1, .port_priority = 0xff, .port_state = 1, }; static const struct lacpdu lacpdu = { .subtype = 0x01, .version_number = 0x01, .tlv_type_actor_info = 0x01, .actor_information_length = 0x14, .tlv_type_partner_info = 0x02, .partner_information_length = 0x14, .tlv_type_collector_info = 0x03, .collector_information_length = 0x10, .collector_max_delay = htons(AD_COLLECTOR_MAX_DELAY), }; if (port) { port->actor_port_priority = 0xff; port->actor_port_aggregator_identifier = 0; port->ntt = false; port->actor_admin_port_state = LACP_STATE_AGGREGATION | LACP_STATE_LACP_ACTIVITY; port->actor_oper_port_state = LACP_STATE_AGGREGATION | LACP_STATE_LACP_ACTIVITY; if (lacp_fast) port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT; memcpy(&port->partner_admin, &tmpl, sizeof(tmpl)); memcpy(&port->partner_oper, &tmpl, sizeof(tmpl)); port->is_enabled = true; /* private parameters */ port->sm_vars = AD_PORT_BEGIN | AD_PORT_LACP_ENABLED; port->sm_rx_state = 0; port->sm_rx_timer_counter = 0; port->sm_periodic_state = 0; port->sm_periodic_timer_counter = 0; port->sm_mux_state = 0; port->sm_mux_timer_counter = 0; port->sm_tx_state = 0; port->aggregator = NULL; port->next_port_in_aggregator = NULL; port->transaction_id = 0; port->sm_churn_actor_timer_counter = 0; port->sm_churn_actor_state = 0; port->churn_actor_count = 0; port->sm_churn_partner_timer_counter = 0; port->sm_churn_partner_state = 0; port->churn_partner_count = 0; memcpy(&port->lacpdu, &lacpdu, sizeof(lacpdu)); } } /** * ad_enable_collecting - enable a port's receive * @port: the port we're looking at * * Enable @port if it's in an active aggregator */ static void ad_enable_collecting(struct port *port) { if (port->aggregator->is_active) { struct slave *slave = port->slave; slave_dbg(slave->bond->dev, slave->dev, "Enabling collecting on port %d (LAG %d)\n", port->actor_port_number, port->aggregator->aggregator_identifier); __enable_collecting_port(port); } } /** * ad_disable_distributing - disable a port's transmit * @port: the port we're looking at * @update_slave_arr: Does slave array need update? */ static void ad_disable_distributing(struct port *port, bool *update_slave_arr) { if (port->aggregator && __agg_has_partner(port->aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling distributing on port %d (LAG %d)\n", port->actor_port_number, port->aggregator->aggregator_identifier); __disable_distributing_port(port); /* Slave array needs an update */ *update_slave_arr = true; } } /** * ad_enable_collecting_distributing - enable a port's transmit/receive * @port: the port we're looking at * @update_slave_arr: Does slave array need update? * * Enable @port if it's in an active aggregator */ static void ad_enable_collecting_distributing(struct port *port, bool *update_slave_arr) { if (port->aggregator->is_active) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Enabling port %d (LAG %d)\n", port->actor_port_number, port->aggregator->aggregator_identifier); __enable_port(port); /* Slave array needs update */ *update_slave_arr = true; } } /** * ad_disable_collecting_distributing - disable a port's transmit/receive * @port: the port we're looking at * @update_slave_arr: Does slave array need update? */ static void ad_disable_collecting_distributing(struct port *port, bool *update_slave_arr) { if (port->aggregator && __agg_has_partner(port->aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling port %d (LAG %d)\n", port->actor_port_number, port->aggregator->aggregator_identifier); __disable_port(port); /* Slave array needs an update */ *update_slave_arr = true; } } /** * ad_marker_info_received - handle receive of a Marker information frame * @marker_info: Marker info received * @port: the port we're looking at */ static void ad_marker_info_received(struct bond_marker *marker_info, struct port *port) { struct bond_marker marker; atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.marker_rx); atomic64_inc(&BOND_AD_INFO(port->slave->bond).stats.marker_rx); /* copy the received marker data to the response marker */ memcpy(&marker, marker_info, sizeof(struct bond_marker)); /* change the marker subtype to marker response */ marker.tlv_type = AD_MARKER_RESPONSE_SUBTYPE; /* send the marker response */ if (ad_marker_send(port, &marker) >= 0) slave_dbg(port->slave->bond->dev, port->slave->dev, "Sent Marker Response on port %d\n", port->actor_port_number); } /** * ad_marker_response_received - handle receive of a marker response frame * @marker: marker PDU received * @port: the port we're looking at * * This function does nothing since we decided not to implement send and handle * response for marker PDU's, in this stage, but only to respond to marker * information. */ static void ad_marker_response_received(struct bond_marker *marker, struct port *port) { atomic64_inc(&SLAVE_AD_INFO(port->slave)->stats.marker_resp_rx); atomic64_inc(&BOND_AD_INFO(port->slave->bond).stats.marker_resp_rx); /* DO NOTHING, SINCE WE DECIDED NOT TO IMPLEMENT THIS FEATURE FOR NOW */ } /* ========= AD exported functions to the main bonding code ========= */ /* Check aggregators status in team every T seconds */ #define AD_AGGREGATOR_SELECTION_TIMER 8 /** * bond_3ad_initiate_agg_selection - initate aggregator selection * @bond: bonding struct * @timeout: timeout value to set * * Set the aggregation selection timer, to initiate an agg selection in * the very near future. Called during first initialization, and during * any down to up transitions of the bond. */ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) { atomic_set(&BOND_AD_INFO(bond).agg_select_timer, timeout); } /** * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures * @bond: bonding struct to work on * * Can be called only after the mac address of the bond is set. */ void bond_3ad_initialize(struct bonding *bond) { BOND_AD_INFO(bond).aggregator_identifier = 0; BOND_AD_INFO(bond).system.sys_priority = bond->params.ad_actor_sys_prio; if (is_zero_ether_addr(bond->params.ad_actor_system)) BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr); else BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->params.ad_actor_system); bond_3ad_initiate_agg_selection(bond, AD_AGGREGATOR_SELECTION_TIMER * ad_ticks_per_sec); } /** * bond_3ad_bind_slave - initialize a slave's port * @slave: slave struct to work on * * Returns: 0 on success * < 0 on error */ void bond_3ad_bind_slave(struct slave *slave) { struct bonding *bond = bond_get_bond_by_slave(slave); struct port *port; struct aggregator *aggregator; /* check that the slave has not been initialized yet. */ if (SLAVE_AD_INFO(slave)->port.slave != slave) { /* port initialization */ port = &(SLAVE_AD_INFO(slave)->port); ad_initialize_port(port, bond->params.lacp_fast); port->slave = slave; port->actor_port_number = SLAVE_AD_INFO(slave)->id; /* key is determined according to the link speed, duplex and * user key */ port->actor_admin_port_key = bond->params.ad_user_port_key << 6; ad_update_actor_keys(port, false); /* actor system is the bond's system */ __ad_actor_update_port(port); /* tx timer(to verify that no more than MAX_TX_IN_SECOND * lacpdu's are sent in one second) */ port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; __disable_port(port); /* aggregator initialization */ aggregator = &(SLAVE_AD_INFO(slave)->aggregator); ad_initialize_agg(aggregator); aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr); aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier; aggregator->slave = slave; aggregator->is_active = 0; aggregator->num_of_ports = 0; } } /** * bond_3ad_unbind_slave - deinitialize a slave's port * @slave: slave struct to work on * * Search for the aggregator that is related to this port, remove the * aggregator and assign another aggregator for other port related to it * (if any), and remove the port. */ void bond_3ad_unbind_slave(struct slave *slave) { struct port *port, *prev_port, *temp_port; struct aggregator *aggregator, *new_aggregator, *temp_aggregator; int select_new_active_agg = 0; struct bonding *bond = slave->bond; struct slave *slave_iter; struct list_head *iter; bool dummy_slave_update; /* Ignore this value as caller updates array */ /* Sync against bond_3ad_state_machine_handler() */ spin_lock_bh(&bond->mode_lock); aggregator = &(SLAVE_AD_INFO(slave)->aggregator); port = &(SLAVE_AD_INFO(slave)->port); /* if slave is null, the whole port is not initialized */ if (!port->slave) { slave_warn(bond->dev, slave->dev, "Trying to unbind an uninitialized port\n"); goto out; } slave_dbg(bond->dev, slave->dev, "Unbinding Link Aggregation Group %d\n", aggregator->aggregator_identifier); /* Tell the partner that this port is not suitable for aggregation */ port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; port->actor_oper_port_state &= ~LACP_STATE_COLLECTING; port->actor_oper_port_state &= ~LACP_STATE_DISTRIBUTING; port->actor_oper_port_state &= ~LACP_STATE_AGGREGATION; __update_lacpdu_from_port(port); ad_lacpdu_send(port); /* check if this aggregator is occupied */ if (aggregator->lag_ports) { /* check if there are other ports related to this aggregator * except the port related to this slave(thats ensure us that * there is a reason to search for new aggregator, and that we * will find one */ if ((aggregator->lag_ports != port) || (aggregator->lag_ports->next_port_in_aggregator)) { /* find new aggregator for the related port(s) */ bond_for_each_slave(bond, slave_iter, iter) { new_aggregator = &(SLAVE_AD_INFO(slave_iter)->aggregator); /* if the new aggregator is empty, or it is * connected to our port only */ if (!new_aggregator->lag_ports || ((new_aggregator->lag_ports == port) && !new_aggregator->lag_ports->next_port_in_aggregator)) break; } if (!slave_iter) new_aggregator = NULL; /* if new aggregator found, copy the aggregator's * parameters and connect the related lag_ports to the * new aggregator */ if ((new_aggregator) && ((!new_aggregator->lag_ports) || ((new_aggregator->lag_ports == port) && !new_aggregator->lag_ports->next_port_in_aggregator))) { slave_dbg(bond->dev, slave->dev, "Some port(s) related to LAG %d - replacing with LAG %d\n", aggregator->aggregator_identifier, new_aggregator->aggregator_identifier); if ((new_aggregator->lag_ports == port) && new_aggregator->is_active) { slave_info(bond->dev, slave->dev, "Removing an active aggregator\n"); select_new_active_agg = 1; } new_aggregator->is_individual = aggregator->is_individual; new_aggregator->actor_admin_aggregator_key = aggregator->actor_admin_aggregator_key; new_aggregator->actor_oper_aggregator_key = aggregator->actor_oper_aggregator_key; new_aggregator->partner_system = aggregator->partner_system; new_aggregator->partner_system_priority = aggregator->partner_system_priority; new_aggregator->partner_oper_aggregator_key = aggregator->partner_oper_aggregator_key; new_aggregator->receive_state = aggregator->receive_state; new_aggregator->transmit_state = aggregator->transmit_state; new_aggregator->lag_ports = aggregator->lag_ports; new_aggregator->is_active = aggregator->is_active; new_aggregator->num_of_ports = aggregator->num_of_ports; /* update the information that is written on * the ports about the aggregator */ for (temp_port = aggregator->lag_ports; temp_port; temp_port = temp_port->next_port_in_aggregator) { temp_port->aggregator = new_aggregator; temp_port->actor_port_aggregator_identifier = new_aggregator->aggregator_identifier; } ad_clear_agg(aggregator); if (select_new_active_agg) ad_agg_selection_logic(__get_first_agg(port), &dummy_slave_update); } else { slave_warn(bond->dev, slave->dev, "unbinding aggregator, and could not find a new aggregator for its ports\n"); } } else { /* in case that the only port related to this * aggregator is the one we want to remove */ select_new_active_agg = aggregator->is_active; ad_clear_agg(aggregator); if (select_new_active_agg) { slave_info(bond->dev, slave->dev, "Removing an active aggregator\n"); /* select new active aggregator */ temp_aggregator = __get_first_agg(port); if (temp_aggregator) ad_agg_selection_logic(temp_aggregator, &dummy_slave_update); } } } slave_dbg(bond->dev, slave->dev, "Unbinding port %d\n", port->actor_port_number); /* find the aggregator that this port is connected to */ bond_for_each_slave(bond, slave_iter, iter) { temp_aggregator = &(SLAVE_AD_INFO(slave_iter)->aggregator); prev_port = NULL; /* search the port in the aggregator's related ports */ for (temp_port = temp_aggregator->lag_ports; temp_port; prev_port = temp_port, temp_port = temp_port->next_port_in_aggregator) { if (temp_port == port) { /* the aggregator found - detach the port from * this aggregator */ if (prev_port) prev_port->next_port_in_aggregator = temp_port->next_port_in_aggregator; else temp_aggregator->lag_ports = temp_port->next_port_in_aggregator; temp_aggregator->num_of_ports--; if (__agg_active_ports(temp_aggregator) == 0) { select_new_active_agg = temp_aggregator->is_active; if (temp_aggregator->num_of_ports == 0) ad_clear_agg(temp_aggregator); if (select_new_active_agg) { slave_info(bond->dev, slave->dev, "Removing an active aggregator\n"); /* select new active aggregator */ ad_agg_selection_logic(__get_first_agg(port), &dummy_slave_update); } } break; } } } port->slave = NULL; out: spin_unlock_bh(&bond->mode_lock); } /** * bond_3ad_update_ad_actor_settings - reflect change of actor settings to ports * @bond: bonding struct to work on * * If an ad_actor setting gets changed we need to update the individual port * settings so the bond device will use the new values when it gets upped. */ void bond_3ad_update_ad_actor_settings(struct bonding *bond) { struct list_head *iter; struct slave *slave; ASSERT_RTNL(); BOND_AD_INFO(bond).system.sys_priority = bond->params.ad_actor_sys_prio; if (is_zero_ether_addr(bond->params.ad_actor_system)) BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr); else BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->params.ad_actor_system); spin_lock_bh(&bond->mode_lock); bond_for_each_slave(bond, slave, iter) { struct port *port = &(SLAVE_AD_INFO(slave))->port; __ad_actor_update_port(port); port->ntt = true; } spin_unlock_bh(&bond->mode_lock); } /** * bond_agg_timer_advance - advance agg_select_timer * @bond: bonding structure * * Return true when agg_select_timer reaches 0. */ static bool bond_agg_timer_advance(struct bonding *bond) { int val, nval; while (1) { val = atomic_read(&BOND_AD_INFO(bond).agg_select_timer); if (!val) return false; nval = val - 1; if (atomic_cmpxchg(&BOND_AD_INFO(bond).agg_select_timer, val, nval) == val) break; } return nval == 0; } /** * bond_3ad_state_machine_handler - handle state machines timeout * @work: work context to fetch bonding struct to work on from * * The state machine handling concept in this module is to check every tick * which state machine should operate any function. The execution order is * round robin, so when we have an interaction between state machines, the * reply of one to each other might be delayed until next tick. * * This function also complete the initialization when the agg_select_timer * times out, and it selects an aggregator for the ports that are yet not * related to any aggregator, and selects the active aggregator for a bond. */ void bond_3ad_state_machine_handler(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, ad_work.work); struct aggregator *aggregator; struct list_head *iter; struct slave *slave; struct port *port; bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; bool update_slave_arr = false; /* Lock to protect data accessed by all (e.g., port->sm_vars) and * against running with bond_3ad_unbind_slave. ad_rx_machine may run * concurrently due to incoming LACPDU as well. */ spin_lock_bh(&bond->mode_lock); rcu_read_lock(); /* check if there are any slaves */ if (!bond_has_slaves(bond)) goto re_arm; if (bond_agg_timer_advance(bond)) { slave = bond_first_slave_rcu(bond); port = slave ? &(SLAVE_AD_INFO(slave)->port) : NULL; /* select the active aggregator for the bond */ if (port) { if (!port->slave) { net_warn_ratelimited("%s: Warning: bond's first port is uninitialized\n", bond->dev->name); goto re_arm; } aggregator = __get_first_agg(port); ad_agg_selection_logic(aggregator, &update_slave_arr); } bond_3ad_set_carrier(bond); } /* for each port run the state machines */ bond_for_each_slave_rcu(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave)->port); if (!port->slave) { net_warn_ratelimited("%s: Warning: Found an uninitialized port\n", bond->dev->name); goto re_arm; } ad_rx_machine(NULL, port); ad_periodic_machine(port, &bond->params); ad_port_selection_logic(port, &update_slave_arr); ad_mux_machine(port, &update_slave_arr); ad_tx_machine(port); ad_churn_machine(port); /* turn off the BEGIN bit, since we already handled it */ if (port->sm_vars & AD_PORT_BEGIN) port->sm_vars &= ~AD_PORT_BEGIN; } re_arm: bond_for_each_slave_rcu(bond, slave, iter) { if (slave->should_notify) { should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; break; } } rcu_read_unlock(); spin_unlock_bh(&bond->mode_lock); if (update_slave_arr) bond_slave_arr_work_rearm(bond, 0); if (should_notify_rtnl && rtnl_trylock()) { bond_slave_state_notify(bond); rtnl_unlock(); } queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); } /** * bond_3ad_rx_indication - handle a received frame * @lacpdu: received lacpdu * @slave: slave struct to work on * * It is assumed that frames that were sent on this NIC don't returned as new * received frames (loopback). Since only the payload is given to this * function, it check for loopback. */ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave) { struct bonding *bond = slave->bond; int ret = RX_HANDLER_ANOTHER; struct bond_marker *marker; struct port *port; atomic64_t *stat; port = &(SLAVE_AD_INFO(slave)->port); if (!port->slave) { net_warn_ratelimited("%s: Warning: port of slave %s is uninitialized\n", slave->dev->name, slave->bond->dev->name); return ret; } switch (lacpdu->subtype) { case AD_TYPE_LACPDU: ret = RX_HANDLER_CONSUMED; slave_dbg(slave->bond->dev, slave->dev, "Received LACPDU on port %d\n", port->actor_port_number); /* Protect against concurrent state machines */ spin_lock(&slave->bond->mode_lock); ad_rx_machine(lacpdu, port); spin_unlock(&slave->bond->mode_lock); break; case AD_TYPE_MARKER: ret = RX_HANDLER_CONSUMED; /* No need to convert fields to Little Endian since we * don't use the marker's fields. */ marker = (struct bond_marker *)lacpdu; switch (marker->tlv_type) { case AD_MARKER_INFORMATION_SUBTYPE: slave_dbg(slave->bond->dev, slave->dev, "Received Marker Information on port %d\n", port->actor_port_number); ad_marker_info_received(marker, port); break; case AD_MARKER_RESPONSE_SUBTYPE: slave_dbg(slave->bond->dev, slave->dev, "Received Marker Response on port %d\n", port->actor_port_number); ad_marker_response_received(marker, port); break; default: slave_dbg(slave->bond->dev, slave->dev, "Received an unknown Marker subtype on port %d\n", port->actor_port_number); stat = &SLAVE_AD_INFO(slave)->stats.marker_unknown_rx; atomic64_inc(stat); stat = &BOND_AD_INFO(bond).stats.marker_unknown_rx; atomic64_inc(stat); } break; default: atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_unknown_rx); atomic64_inc(&BOND_AD_INFO(bond).stats.lacpdu_unknown_rx); } return ret; } /** * ad_update_actor_keys - Update the oper / admin keys for a port based on * its current speed and duplex settings. * * @port: the port we'are looking at * @reset: Boolean to just reset the speed and the duplex part of the key * * The logic to change the oper / admin keys is: * (a) A full duplex port can participate in LACP with partner. * (b) When the speed is changed, LACP need to be reinitiated. */ static void ad_update_actor_keys(struct port *port, bool reset) { u8 duplex = 0; u16 ospeed = 0, speed = 0; u16 old_oper_key = port->actor_oper_port_key; port->actor_admin_port_key &= ~(AD_SPEED_KEY_MASKS|AD_DUPLEX_KEY_MASKS); if (!reset) { speed = __get_link_speed(port); ospeed = (old_oper_key & AD_SPEED_KEY_MASKS) >> 1; duplex = __get_duplex(port); port->actor_admin_port_key |= (speed << 1) | duplex; } port->actor_oper_port_key = port->actor_admin_port_key; if (old_oper_key != port->actor_oper_port_key) { /* Only 'duplex' port participates in LACP */ if (duplex) port->sm_vars |= AD_PORT_LACP_ENABLED; else port->sm_vars &= ~AD_PORT_LACP_ENABLED; if (!reset) { if (!speed) { slave_err(port->slave->bond->dev, port->slave->dev, "speed changed to 0 on port %d\n", port->actor_port_number); } else if (duplex && ospeed != speed) { /* Speed change restarts LACP state-machine */ port->sm_vars |= AD_PORT_BEGIN; } } } } /** * bond_3ad_adapter_speed_duplex_changed - handle a slave's speed / duplex * change indication * * @slave: slave struct to work on * * Handle reselection of aggregator (if needed) for this port. */ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave) { struct port *port; port = &(SLAVE_AD_INFO(slave)->port); /* if slave is null, the whole port is not initialized */ if (!port->slave) { slave_warn(slave->bond->dev, slave->dev, "speed/duplex changed for uninitialized port\n"); return; } spin_lock_bh(&slave->bond->mode_lock); ad_update_actor_keys(port, false); spin_unlock_bh(&slave->bond->mode_lock); slave_dbg(slave->bond->dev, slave->dev, "Port %d changed speed/duplex\n", port->actor_port_number); } /** * bond_3ad_handle_link_change - handle a slave's link status change indication * @slave: slave struct to work on * @link: whether the link is now up or down * * Handle reselection of aggregator (if needed) for this port. */ void bond_3ad_handle_link_change(struct slave *slave, char link) { struct aggregator *agg; struct port *port; bool dummy; port = &(SLAVE_AD_INFO(slave)->port); /* if slave is null, the whole port is not initialized */ if (!port->slave) { slave_warn(slave->bond->dev, slave->dev, "link status changed for uninitialized port\n"); return; } spin_lock_bh(&slave->bond->mode_lock); /* on link down we are zeroing duplex and speed since * some of the adaptors(ce1000.lan) report full duplex/speed * instead of N/A(duplex) / 0(speed). * * on link up we are forcing recheck on the duplex and speed since * some of he adaptors(ce1000.lan) report. */ if (link == BOND_LINK_UP) { port->is_enabled = true; ad_update_actor_keys(port, false); } else { /* link has failed */ port->is_enabled = false; ad_update_actor_keys(port, true); } agg = __get_first_agg(port); ad_agg_selection_logic(agg, &dummy); spin_unlock_bh(&slave->bond->mode_lock); slave_dbg(slave->bond->dev, slave->dev, "Port %d changed link status to %s\n", port->actor_port_number, link == BOND_LINK_UP ? "UP" : "DOWN"); /* RTNL is held and mode_lock is released so it's safe * to update slave_array here. */ bond_update_slave_arr(slave->bond, NULL); } /** * bond_3ad_set_carrier - set link state for bonding master * @bond: bonding structure * * if we have an active aggregator, we're up, if not, we're down. * Presumes that we cannot have an active aggregator if there are * no slaves with link up. * * This behavior complies with IEEE 802.3 section 43.3.9. * * Called by bond_set_carrier(). Return zero if carrier state does not * change, nonzero if it does. */ int bond_3ad_set_carrier(struct bonding *bond) { struct aggregator *active; struct slave *first_slave; int ret = 1; rcu_read_lock(); first_slave = bond_first_slave_rcu(bond); if (!first_slave) { ret = 0; goto out; } active = __get_active_agg(&(SLAVE_AD_INFO(first_slave)->aggregator)); if (active) { /* are enough slaves available to consider link up? */ if (__agg_active_ports(active) < bond->params.min_links) { if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); goto out; } } else if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); goto out; } } else if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); } out: rcu_read_unlock(); return ret; } /** * __bond_3ad_get_active_agg_info - get information of the active aggregator * @bond: bonding struct to work on * @ad_info: ad_info struct to fill with the bond's info * * Returns: 0 on success * < 0 on error */ int __bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) { struct aggregator *aggregator = NULL; struct list_head *iter; struct slave *slave; struct port *port; bond_for_each_slave_rcu(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave)->port); if (port->aggregator && port->aggregator->is_active) { aggregator = port->aggregator; break; } } if (!aggregator) return -1; ad_info->aggregator_id = aggregator->aggregator_identifier; ad_info->ports = __agg_active_ports(aggregator); ad_info->actor_key = aggregator->actor_oper_aggregator_key; ad_info->partner_key = aggregator->partner_oper_aggregator_key; ether_addr_copy(ad_info->partner_system, aggregator->partner_system.mac_addr_value); return 0; } int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) { int ret; rcu_read_lock(); ret = __bond_3ad_get_active_agg_info(bond, ad_info); rcu_read_unlock(); return ret; } int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct lacpdu *lacpdu, _lacpdu; if (skb->protocol != PKT_TYPE_LACPDU) return RX_HANDLER_ANOTHER; if (!MAC_ADDRESS_EQUAL(eth_hdr(skb)->h_dest, lacpdu_mcast_addr)) return RX_HANDLER_ANOTHER; lacpdu = skb_header_pointer(skb, 0, sizeof(_lacpdu), &_lacpdu); if (!lacpdu) { atomic64_inc(&SLAVE_AD_INFO(slave)->stats.lacpdu_illegal_rx); atomic64_inc(&BOND_AD_INFO(bond).stats.lacpdu_illegal_rx); return RX_HANDLER_ANOTHER; } return bond_3ad_rx_indication(lacpdu, slave); } /** * bond_3ad_update_lacp_rate - change the lacp rate * @bond: bonding struct * * When modify lacp_rate parameter via sysfs, * update actor_oper_port_state of each port. * * Hold bond->mode_lock, * so we can modify port->actor_oper_port_state, * no matter bond is up or down. */ void bond_3ad_update_lacp_rate(struct bonding *bond) { struct port *port = NULL; struct list_head *iter; struct slave *slave; int lacp_fast; lacp_fast = bond->params.lacp_fast; spin_lock_bh(&bond->mode_lock); bond_for_each_slave(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave)->port); if (lacp_fast) port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT; else port->actor_oper_port_state &= ~LACP_STATE_LACP_TIMEOUT; } spin_unlock_bh(&bond->mode_lock); } size_t bond_3ad_stats_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */ nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_TX */ nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_UNKNOWN_RX */ nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_ILLEGAL_RX */ nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_RX */ nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_TX */ nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_RESP_RX */ nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_MARKER_RESP_TX */ nla_total_size_64bit(sizeof(u64)); /* BOND_3AD_STAT_MARKER_UNKNOWN_RX */ } int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats) { u64 val; val = atomic64_read(&stats->lacpdu_rx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_RX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->lacpdu_tx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_TX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->lacpdu_unknown_rx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_UNKNOWN_RX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->lacpdu_illegal_rx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_LACPDU_ILLEGAL_RX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->marker_rx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_RX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->marker_tx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_TX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->marker_resp_rx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_RESP_RX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->marker_resp_tx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_RESP_TX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; val = atomic64_read(&stats->marker_unknown_rx); if (nla_put_u64_64bit(skb, BOND_3AD_STAT_MARKER_UNKNOWN_RX, val, BOND_3AD_STAT_PAD)) return -EMSGSIZE; return 0; } |
| 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: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> */ #ifndef _EXT4_EXTENTS #define _EXT4_EXTENTS #include "ext4.h" /* * With AGGRESSIVE_TEST defined, the capacity of index/leaf blocks * becomes very small, so index split, in-depth growing and * other hard changes happen much more often. * This is for debug purposes only. */ #define AGGRESSIVE_TEST_ /* * With EXTENTS_STATS defined, the number of blocks and extents * are collected in the truncate path. They'll be shown at * umount time. */ #define EXTENTS_STATS__ /* * If CHECK_BINSEARCH is defined, then the results of the binary search * will also be checked by linear search. */ #define CHECK_BINSEARCH__ /* * If EXT_STATS is defined then stats numbers are collected. * These number will be displayed at umount time. */ #define EXT_STATS_ /* * ext4_inode has i_block array (60 bytes total). * The first 12 bytes store ext4_extent_header; * the remainder stores an array of ext4_extent. * For non-inode extent blocks, ext4_extent_tail * follows the array. */ /* * This is the extent tail on-disk structure. * All other extent structures are 12 bytes long. It turns out that * block_size % 12 >= 4 for at least all powers of 2 greater than 512, which * covers all valid ext4 block sizes. Therefore, this tail structure can be * crammed into the end of the block without having to rebalance the tree. */ struct ext4_extent_tail { __le32 et_checksum; /* crc32c(uuid+inum+extent_block) */ }; /* * This is the extent on-disk structure. * It's used at the bottom of the tree. */ struct ext4_extent { __le32 ee_block; /* first logical block extent covers */ __le16 ee_len; /* number of blocks covered by extent */ __le16 ee_start_hi; /* high 16 bits of physical block */ __le32 ee_start_lo; /* low 32 bits of physical block */ }; /* * This is index on-disk structure. * It's used at all the levels except the bottom. */ struct ext4_extent_idx { __le32 ei_block; /* index covers logical blocks from 'block' */ __le32 ei_leaf_lo; /* pointer to the physical block of the next * * level. leaf or next index could be there */ __le16 ei_leaf_hi; /* high 16 bits of physical block */ __u16 ei_unused; }; /* * Each block (leaves and indexes), even inode-stored has header. */ struct ext4_extent_header { __le16 eh_magic; /* probably will support different formats */ __le16 eh_entries; /* number of valid entries */ __le16 eh_max; /* capacity of store in entries */ __le16 eh_depth; /* has tree real underlying blocks? */ __le32 eh_generation; /* generation of the tree */ }; #define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) #define EXT4_MAX_EXTENT_DEPTH 5 #define EXT4_EXTENT_TAIL_OFFSET(hdr) \ (sizeof(struct ext4_extent_header) + \ (sizeof(struct ext4_extent) * le16_to_cpu((hdr)->eh_max))) static inline struct ext4_extent_tail * find_ext4_extent_tail(struct ext4_extent_header *eh) { return (struct ext4_extent_tail *)(((void *)eh) + EXT4_EXTENT_TAIL_OFFSET(eh)); } /* * Array of ext4_ext_path contains path to some extent. * Creation/lookup routines use it for traversal/splitting/etc. * Truncate uses it to simulate recursive walking. */ struct ext4_ext_path { ext4_fsblk_t p_block; __u16 p_depth; __u16 p_maxdepth; struct ext4_extent *p_ext; struct ext4_extent_idx *p_idx; struct ext4_extent_header *p_hdr; struct buffer_head *p_bh; }; /* * Used to record a portion of a cluster found at the beginning or end * of an extent while traversing the extent tree during space removal. * A partial cluster may be removed if it does not contain blocks shared * with extents that aren't being deleted (tofree state). Otherwise, * it cannot be removed (nofree state). */ struct partial_cluster { ext4_fsblk_t pclu; /* physical cluster number */ ext4_lblk_t lblk; /* logical block number within logical cluster */ enum {initial, tofree, nofree} state; }; /* * structure for external API */ /* * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an * initialized extent. This is 2^15 and not (2^16 - 1), since we use the * MSB of ee_len field in the extent datastructure to signify if this * particular extent is an initialized extent or an unwritten (i.e. * preallocated). * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an * unwritten extent. * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an * unwritten one. In other words, if MSB of ee_len is set, it is an * unwritten extent with only one special scenario when ee_len = 0x8000. * In this case we can not have an unwritten extent of zero length and * thus we make it as a special case of initialized extent with 0x8000 length. * This way we get better extent-to-group alignment for initialized extents. * Hence, the maximum number of blocks we can have in an *initialized* * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767). */ #define EXT_INIT_MAX_LEN (1UL << 15) #define EXT_UNWRITTEN_MAX_LEN (EXT_INIT_MAX_LEN - 1) #define EXT_FIRST_EXTENT(__hdr__) \ ((struct ext4_extent *) (((char *) (__hdr__)) + \ sizeof(struct ext4_extent_header))) #define EXT_FIRST_INDEX(__hdr__) \ ((struct ext4_extent_idx *) (((char *) (__hdr__)) + \ sizeof(struct ext4_extent_header))) #define EXT_HAS_FREE_INDEX(__path__) \ (le16_to_cpu((__path__)->p_hdr->eh_entries) \ < le16_to_cpu((__path__)->p_hdr->eh_max)) #define EXT_LAST_EXTENT(__hdr__) \ (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) #define EXT_LAST_INDEX(__hdr__) \ (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) #define EXT_MAX_EXTENT(__hdr__) \ ((le16_to_cpu((__hdr__)->eh_max)) ? \ ((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \ : NULL) #define EXT_MAX_INDEX(__hdr__) \ ((le16_to_cpu((__hdr__)->eh_max)) ? \ ((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \ : NULL) static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode) { return (struct ext4_extent_header *) EXT4_I(inode)->i_data; } static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh) { return (struct ext4_extent_header *) bh->b_data; } static inline unsigned short ext_depth(struct inode *inode) { return le16_to_cpu(ext_inode_hdr(inode)->eh_depth); } static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext) { /* We can not have an unwritten extent of zero length! */ BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0); ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN); } static inline int ext4_ext_is_unwritten(struct ext4_extent *ext) { /* Extent with ee_len of 0x8000 is treated as an initialized extent */ return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN); } static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) { return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ? le16_to_cpu(ext->ee_len) : (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN)); } static inline void ext4_ext_mark_initialized(struct ext4_extent *ext) { ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext)); } /* * ext4_ext_pblock: * combine low and high parts of physical block number into ext4_fsblk_t */ static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex) { ext4_fsblk_t block; block = le32_to_cpu(ex->ee_start_lo); block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1; return block; } /* * ext4_idx_pblock: * combine low and high parts of a leaf physical block number into ext4_fsblk_t */ static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix) { ext4_fsblk_t block; block = le32_to_cpu(ix->ei_leaf_lo); block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1; return block; } /* * ext4_ext_store_pblock: * stores a large physical block number into an extent struct, * breaking it into parts */ static inline void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb) { ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } /* * ext4_idx_store_pblock: * stores a large physical block number into an index struct, * breaking it into parts */ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) { ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } #endif /* _EXT4_EXTENTS */ |
| 117 1386 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> #include <linux/clocksource_ids.h> #include <linux/ktime.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void legacy_timer_tick(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); extern void ktime_get_real_ts64_mg(struct timespec64 *ts); extern unsigned long timekeeping_get_mg_floor_swaps(void); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format * * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. * * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Get the TAI time of day in ktime_t format * * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime * @mono: monotonic time to convert * * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } /** * ktime_get_ns - Get the current time in nanoseconds * * Returns: current time converted to nanoseconds */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } /** * ktime_get_real_ns - Get the current real/wall time in nanoseconds * * Returns: current real time converted to nanoseconds */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } /** * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds * * Returns: current boottime converted to nanoseconds */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } /** * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds * * Returns: current TAI time converted to nanoseconds */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } /** * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds * * Returns: current raw monotonic time converted to nanoseconds */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value * @cs_id: Clocksource ID corresponding to system counter value. Used by * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; bool use_nsecs; }; extern bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles); extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); #ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); #endif #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM lock #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LOCK_H #include <linux/sched.h> #include <linux/tracepoint.h> /* flags for lock:contention_begin */ #define LCB_F_SPIN (1U << 0) #define LCB_F_READ (1U << 1) #define LCB_F_WRITE (1U << 2) #define LCB_F_RT (1U << 3) #define LCB_F_PERCPU (1U << 4) #define LCB_F_MUTEX (1U << 5) #ifdef CONFIG_LOCKDEP #include <linux/lockdep.h> TRACE_EVENT(lock_acquire, TP_PROTO(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *next_lock, unsigned long ip), TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip), TP_STRUCT__entry( __field(unsigned int, flags) __string(name, lock->name) __field(void *, lockdep_addr) ), TP_fast_assign( __entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0); __assign_str(name); __entry->lockdep_addr = lock; ), TP_printk("%p %s%s%s", __entry->lockdep_addr, (__entry->flags & 1) ? "try " : "", (__entry->flags & 2) ? "read " : "", __get_str(name)) ); DECLARE_EVENT_CLASS(lock, TP_PROTO(struct lockdep_map *lock, unsigned long ip), TP_ARGS(lock, ip), TP_STRUCT__entry( __string( name, lock->name ) __field( void *, lockdep_addr ) ), TP_fast_assign( __assign_str(name); __entry->lockdep_addr = lock; ), TP_printk("%p %s", __entry->lockdep_addr, __get_str(name)) ); DEFINE_EVENT(lock, lock_release, TP_PROTO(struct lockdep_map *lock, unsigned long ip), TP_ARGS(lock, ip) ); #ifdef CONFIG_LOCK_STAT DEFINE_EVENT(lock, lock_contended, TP_PROTO(struct lockdep_map *lock, unsigned long ip), TP_ARGS(lock, ip) ); DEFINE_EVENT(lock, lock_acquired, TP_PROTO(struct lockdep_map *lock, unsigned long ip), TP_ARGS(lock, ip) ); #endif /* CONFIG_LOCK_STAT */ #endif /* CONFIG_LOCKDEP */ TRACE_EVENT(contention_begin, TP_PROTO(void *lock, unsigned int flags), TP_ARGS(lock, flags), TP_STRUCT__entry( __field(void *, lock_addr) __field(unsigned int, flags) ), TP_fast_assign( __entry->lock_addr = lock; __entry->flags = flags; ), TP_printk("%p (flags=%s)", __entry->lock_addr, __print_flags(__entry->flags, "|", { LCB_F_SPIN, "SPIN" }, { LCB_F_READ, "READ" }, { LCB_F_WRITE, "WRITE" }, { LCB_F_RT, "RT" }, { LCB_F_PERCPU, "PERCPU" }, { LCB_F_MUTEX, "MUTEX" } )) ); TRACE_EVENT(contention_end, TP_PROTO(void *lock, int ret), TP_ARGS(lock, ret), TP_STRUCT__entry( __field(void *, lock_addr) __field(int, ret) ), TP_fast_assign( __entry->lock_addr = lock; __entry->ret = ret; ), TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret) ); #endif /* _TRACE_LOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 36 36 36 36 36 36 36 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> * Copyright (C) IBM Corporation, 2009 * Thanks to Thomas Gleixner for conceptual design and careful reviews. * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" */ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/plist.h> #include <linux/memblock.h> #include <linux/fault-inject.h> #include <linux/slab.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * The base of the bucket array and its size are always used together * (after initialization only in futex_hash()), so ensure that they * reside in the same cacheline. */ static struct { struct futex_hash_bucket *queues; unsigned long hashmask; } __futex_data __read_mostly __aligned(2*sizeof(long)); #define futex_queues (__futex_data.queues) #define futex_hashmask (__futex_data.hashmask) /* * Fault injections for futexes. */ #ifdef CONFIG_FAIL_FUTEX static struct { struct fault_attr attr; bool ignore_private; } fail_futex = { .attr = FAULT_ATTR_INITIALIZER, .ignore_private = false, }; static int __init setup_fail_futex(char *str) { return setup_fault_attr(&fail_futex.attr, str); } __setup("fail_futex=", setup_fail_futex); bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; return should_fail(&fail_futex.attr, 1); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_futex_debugfs(void) { umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; dir = fault_create_debugfs_attr("fail_futex", NULL, &fail_futex.attr); if (IS_ERR(dir)) return PTR_ERR(dir); debugfs_create_bool("ignore-private", mode, dir, &fail_futex.ignore_private); return 0; } late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ #endif /* CONFIG_FAIL_FUTEX */ /** * futex_hash - Return the hash bucket in the global hash * @key: Pointer to the futex key for which the hash is calculated * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket in the global hash. */ struct futex_hash_bucket *futex_hash(union futex_key *key) { u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); return &futex_queues[hash & futex_hashmask]; } /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value * @timeout: the hrtimer_sleeper structure to be set up * @flags: futex flags * @range_ns: optional range in ns * * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns) { if (!time) return NULL; hrtimer_setup_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). */ hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns); return timeout; } /* * Generate a machine wide unique identifier for this inode. * * This relies on u64 not wrapping in the life-time of the machine; which with * 1ns resolution means almost 585 years. * * This further relies on the fact that a well formed program will not unmap * the file while it has a (shared) futex waiting on it. This mapping will have * a file reference which pins the mount and inode. * * If for some reason an inode gets evicted and read back in again, it will get * a new sequence number and will _NOT_ match, even though it is the exact same * file. * * It is important that futex_match() will never have a false-positive, esp. * for PI futexes that can mess up the state. The above argues that false-negatives * are only possible for malformed programs. */ static u64 get_inode_sequence_number(struct inode *inode) { static atomic64_t i_seq; u64 old; /* Does the inode already have a sequence number? */ old = atomic64_read(&inode->i_sequence); if (likely(old)) return old; for (;;) { u64 new = atomic64_inc_return(&i_seq); if (WARN_ON_ONCE(!new)) continue; old = 0; if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new)) return old; return new; } } /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) * * Return: a negative error code or 0 * * The key words are stored in @key on success. * * For shared mappings (when @fshared), the key is: * * ( inode->i_sequence, page->index, offset_within_page ) * * [ also see get_inode_sequence_number() ] * * For private mappings (or when !@fshared), the key is: * * ( current->mm, address, 0 ) * * This allows (cross process, where applicable) identification of the futex * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct page *page; struct folio *folio; struct address_space *mapping; int err, ro = 0; bool fshared; fshared = flags & FLAGS_SHARED; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((address % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; if (unlikely(!access_ok(uaddr, sizeof(u32)))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs * virtual address, we dont even have to find the underlying vma. * Note : We do have to check 'uaddr' is a valid user address, * but access_ok() should be faster than find_vma() */ if (!fshared) { /* * On no-MMU, shared futexes are treated as private, therefore * we must not include the current process in the key. Since * there is only one address space, the address is a unique key * on its own. */ if (IS_ENABLED(CONFIG_MMU)) key->private.mm = mm; else key->private.mm = NULL; key->private.address = address; return 0; } again: /* Ignore any VERIFY_READ mapping (futex common case) */ if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); /* * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } if (err < 0) return err; else err = 0; /* * The treatment of mapping from this point on is critical. The folio * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * * Strictly speaking the folio lock is not needed in all cases being * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and * folio lock will be acquired only if it is unavoidable * * Mapping checks require the folio so it is looked up now. For * anonymous pages, it does not matter if the folio is split * in the future as the key is based on the address. For * filesystem-backed pages, the precise page is required as the * index of the page determines the key. */ folio = page_folio(page); mapping = READ_ONCE(folio->mapping); /* * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* * Folio lock is required to identify which special case above * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ folio_lock(folio); shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio); folio_put(folio); if (shmem_swizzled) goto again; return -EFAULT; } /* * Private mappings are handled in a simple way. * * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; } else { struct inode *inode; /* * The associated futex object in this case is the inode and * the folio->mapping must be traversed. Ordinarily this should * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the * mapping->host can be safely accessed as being a valid inode. */ rcu_read_lock(); if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); folio_put(folio); goto again; } inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = page_pgoff(folio, page); rcu_read_unlock(); } out: folio_put(folio); return err; } /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write * access to @uaddr. * * We have no generic implementation of a non-destructive write to the * user address. We know that we faulted in the atomic pagefault * disabled section so we can as well avoid the #PF overhead by * calling get_user_pages() right away. */ int fault_in_user_writeable(u32 __user *uaddr) { struct mm_struct *mm = current->mm; int ret; mmap_read_lock(mm); ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); return ret < 0 ? ret : 0; } /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key) { struct futex_q *this; plist_for_each_entry(this, &hb->chain, list) { if (futex_match(&this->key, key)) return this; } return NULL; } /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. */ void wait_for_owner_exiting(int ret, struct task_struct *exiting) { if (ret != -EBUSY) { WARN_ON_ONCE(exiting); return; } if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; mutex_lock(&exiting->futex_exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can * have any FUTEX_STATE_* value when the waiter has acquired the * mutex. OK, if running, EXITING or DEAD if it reached exit() * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ mutex_unlock(&exiting->futex_exit_mutex); put_task_struct(exiting); } /** * __futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be NULL and must be held by the caller. */ void __futex_unqueue(struct futex_q *q) { struct futex_hash_bucket *hb; if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); } /* The key must be already stored in q->key. */ struct futex_hash_bucket *futex_q_lock(struct futex_q *q) __acquires(&hb->lock) { struct futex_hash_bucket *hb; hb = futex_hash(&q->key); /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is * waiting for the spinlock. This is safe as all futex_q_lock() * users end up calling futex_queue(). Similarly, for housekeeping, * decrement the counter at futex_q_unlock() when some error has * occurred and we don't end up adding the task to the list. */ futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; spin_lock(&hb->lock); return hb; } void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); futex_hb_waiters_dec(hb); } void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task) { int prio; /* * The priority used to register this element is * - either the real thread-priority for the real-time threads * (i.e. threads with a priority lower than MAX_RT_PRIO) * - or MAX_RT_PRIO for non-RT threads. * Thus, all RT-threads are woken first in priority order, and * the others are woken last, in FIFO order. */ prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = task; } /** * futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must * be paired with exactly one earlier call to futex_queue(). * * Return: * - 1 - if the futex_q was still queued (and we removed unqueued it); * - 0 - if the futex_q was already removed by the waking thread */ int futex_unqueue(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ retry: /* * q->lock_ptr can change between this read and the following spin_lock. * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and * optimizing lock_ptr out of the logic below. */ lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. * * Reasoning goes like this: if we have the wrong lock, * q->lock_ptr must have changed (maybe several times) * between reading it and the spin_lock(). It can * change again after the spin_lock() but only if it was * already changed before the spin_lock(). It cannot, * however, change back to the original value. Therefore * we can detect whether we acquired the correct lock. */ if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } __futex_unqueue(q); BUG_ON(q->pi_state); spin_unlock(lock_ptr); ret = 1; } return ret; } /* * PI futexes can not be requeued and must remove themselves from the hash * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { /* * If the lock was not acquired (due to timeout or signal) then the * rt_waiter is removed before futex_q is. If this is observed by * an unlocker after dropping the rtmutex wait lock and before * acquiring the hash bucket lock, then the unlocker dequeues the * futex_q from the hash bucket list to guarantee consistent state * vs. userspace. Therefore the dequeue here must be conditional. */ if (!plist_node_empty(&q->list)) __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); q->pi_state = NULL; } /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; pid_t owner; int err; /* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) return -1; retry: if (get_user(uval, uaddr)) return -1; /* * Special case for regular (non PI) futexes. The unlock path in * user space has two race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up * waiters it is killed. * * 2. A woken up waiter is killed before it can acquire the * futex in user space. * * In the second case, the wake up notification could be generated * by the unlock path in user space after setting the futex value * to zero or by the kernel after setting the OWNER_DIED bit below. * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. * * In both cases the following conditions are met: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and * trying to set the OWNER_DIED bit. If the futex value is zero, * the rest of the user space mutex state is consistent, so a woken * waiter will just take over the uncontended futex. Setting the * OWNER_DIED bit would create inconsistent state and malfunction * of the user space owner died handling. Otherwise, the OWNER_DIED * bit is already set, and the woken waiter is expected to deal with * this. */ owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); return 0; } if (owner != task_pid_vnr(curr)) return 0; /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically * via cmpxchg, and if the value had FUTEX_WAITERS * set, wake up a waiter (if any). (We have to do a * futex_wake() even if OWNER_DIED is already set - * to handle the rare but possible case of recursive * thread-death.) The rest of the cleanup is done in * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; /* * We are not holding a lock here, but we want to have * the pagefault_disable/enable() protection because * we want to handle the fault gracefully. If the * access fails we try to fault in the futex with R/W * verification via get_user_pages. get_user() above * does not guarantee R/W access. If that fails we * give up and leave the futex locked. */ if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) { switch (err) { case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; case -EAGAIN: cond_resched(); goto retry; default: WARN_ON_ONCE(1); return err; } } if (nval != uval) goto retry; /* * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, unsigned int *pi) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; *entry = (void __user *)(uentry & ~1UL); *pi = uentry & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; unsigned long futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (fetch_robust_entry(&entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { handle_futex_death((void __user *)pending + futex_offset, curr, pip, HANDLE_DEATH_PENDING); } } #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { compat_uptr_t base = ptr_to_compat(entry); void __user *uaddr = compat_ptr(base + futex_offset); return uaddr; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, compat_uptr_t __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT; *entry = compat_ptr((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != (struct robust_list __user *) &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, (compat_uptr_t __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: */ if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); if (handle_futex_death(uaddr, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } #endif #ifdef CONFIG_FUTEX_PI /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; union futex_key key = FUTEX_KEY_INIT; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = futex_hash(&key); /* * We can race against put_pi_state() removing itself from the * list (a waiter going away). put_pi_state() will first * decrement the reference count and then modify the list, so * its possible to see the list entry but fail this reference * acquire. * * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); continue; } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); put_pi_state(pi_state); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); raw_spin_lock_irq(&curr->pi_lock); } raw_spin_unlock_irq(&curr->pi_lock); } #else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); tsk->robust_list = NULL; } #ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { compat_exit_robust_list(tsk); tsk->compat_robust_list = NULL; } #endif if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); } /** * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD * @tsk: task to set the state on * * Set the futex exit state of the task lockless. The futex waiter code * observes that state when a task is exiting and loops until the task has * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can * take it over. If not, the problem is pushed back to user space. If the * futex exit code did not run yet, then an already queued waiter might * block forever, but there is nothing which can be done about that. */ void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ if (tsk->futex_state == FUTEX_STATE_EXITING) mutex_unlock(&tsk->futex_exit_mutex); tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ mutex_lock(&tsk->futex_exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * * This ensures that all subsequent checks of tsk->futex_state in * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with * tsk->pi_lock held. * * It guarantees also that a pi_state which was queued right before * the state change under tsk->pi_lock by a concurrent waiter must * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ tsk->futex_state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) { /* * The state handling is done for consistency, but in the case of * exec() there is no way to prevent further damage as the PID stays * the same. But for the unlikely and arguably buggy case that a * futex is held on exec(), this provides at least as much state * consistency protection which is possible. */ futex_cleanup_begin(tsk); futex_cleanup(tsk); /* * Reset the state to FUTEX_STATE_OK. The task is alive and about * exec a new binary. */ futex_cleanup_end(tsk, FUTEX_STATE_OK); } void futex_exit_release(struct task_struct *tsk) { futex_cleanup_begin(tsk); futex_cleanup(tsk); futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } static int __init futex_init(void) { unsigned long hashsize, i; unsigned int futex_shift; #ifdef CONFIG_BASE_SMALL hashsize = 16; #else hashsize = roundup_pow_of_two(256 * num_possible_cpus()); #endif futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), hashsize, 0, 0, &futex_shift, NULL, hashsize, hashsize); hashsize = 1UL << futex_shift; for (i = 0; i < hashsize; i++) { atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } futex_hashmask = hashsize - 1; return 0; } core_initcall(futex_init); |
| 4409 60 751 710 76 17 5304 30 431 4409 752 17 5247 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* I/O iterator iteration building functions. * * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_IOV_ITER_H #define _LINUX_IOV_ITER_H #include <linux/uio.h> #include <linux/bvec.h> #include <linux/folio_queue.h> typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len, void *priv, void *priv2); /* * Handle ITER_UBUF. */ static __always_inline size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { void __user *base = iter->ubuf; size_t progress = 0, remain; remain = step(base + iter->iov_offset, 0, len, priv, priv2); progress = len - remain; iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_IOVEC. */ static __always_inline size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { const struct iovec *p = iter->__iov; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->__iov; iter->__iov = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_KVEC. */ static __always_inline size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct kvec *p = iter->kvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->kvec; iter->kvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_BVEC. */ static __always_inline size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct bio_vec *p = iter->bvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t offset = p->bv_offset + skip, part; void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE); part = min3(len, (size_t)(p->bv_len - skip), (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2); kunmap_local(kaddr); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= p->bv_len) { skip = 0; p++; } if (remain) break; } while (len); iter->nr_segs -= p - iter->bvec; iter->bvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_FOLIOQ. */ static __always_inline size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct folio_queue *folioq = iter->folioq; unsigned int slot = iter->folioq_slot; size_t progress = 0, skip = iter->iov_offset; if (slot == folioq_nr_slots(folioq)) { /* The iterator may have been extended. */ folioq = folioq->next; slot = 0; } do { struct folio *folio = folioq_folio(folioq, slot); size_t part, remain, consumed; size_t fsize; void *base; if (!folio) break; fsize = folioq_folio_size(folioq, slot); base = kmap_local_folio(folio, skip); part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= fsize) { skip = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } if (remain) break; } while (len); iter->folioq_slot = slot; iter->folioq = folioq; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_XARRAY. */ static __always_inline size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { struct folio *folio; size_t progress = 0; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; XA_STATE(xas, iter->xarray, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { size_t remain, consumed, offset, part, flen; if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start + progress); flen = min(folio_size(folio) - offset, len); while (flen) { void *base = kmap_local_folio(folio, offset); part = min_t(size_t, flen, PAGE_SIZE - offset_in_page(offset)); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; progress += consumed; len -= consumed; if (remain || len == 0) goto out; flen -= consumed; offset += consumed; } } out: rcu_read_unlock(); iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_DISCARD. */ static __always_inline size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { size_t progress = len; iter->count -= progress; return progress; } /** * iterate_and_advance2 - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * Two step functions, @step and @ustep, must be provided, one for handling * mapped kernel addresses and the other is given user addresses which have the * potential to fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f ustep, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (likely(iter_is_ubuf(iter))) return iterate_ubuf(iter, len, priv, priv2, ustep); if (likely(iter_is_iovec(iter))) return iterate_iovec(iter, len, priv, priv2, ustep); if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } /** * iterate_and_advance - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * As iterate_and_advance2(), but priv2 is always NULL. */ static __always_inline size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, iov_ustep_f ustep, iov_step_f step) { return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } /** * iterate_and_advance_kernel - Iterate over a kernel-internal iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type * iterators; it will not handle UBUF or IOVEC-type iterators. * * A step functions, @step, must be provided, one for handling mapped kernel * addresses and the other is given user addresses which have the potential to * fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } #endif /* _LINUX_IOV_ITER_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * VMware vSockets Driver * * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. */ #ifndef __AF_VSOCK_H__ #define __AF_VSOCK_H__ #include <linux/kernel.h> #include <linux/workqueue.h> #include <net/sock.h> #include <uapi/linux/vm_sockets.h> #include "vsock_addr.h" #define LAST_RESERVED_PORT 1023 #define VSOCK_HASH_SIZE 251 extern struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; extern struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; extern spinlock_t vsock_table_lock; #define vsock_sk(__sk) ((struct vsock_sock *)__sk) #define sk_vsock(__vsk) (&(__vsk)->sk) struct vsock_sock { /* sk must be the first member. */ struct sock sk; const struct vsock_transport *transport; struct sockaddr_vm local_addr; struct sockaddr_vm remote_addr; /* Links for the global tables of bound and connected sockets. */ struct list_head bound_table; struct list_head connected_table; /* Accessed without the socket lock held. This means it can never be * modified outsided of socket create or destruct. */ bool trusted; bool cached_peer_allow_dgram; /* Dgram communication allowed to * cached peer? */ u32 cached_peer; /* Context ID of last dgram destination check. */ const struct cred *owner; /* Rest are SOCK_STREAM only. */ long connect_timeout; /* Listening socket that this came from. */ struct sock *listener; /* Used for pending list and accept queue during connection handshake. * The listening socket is the head for both lists. Sockets created * for connection requests are placed in the pending list until they * are connected, at which point they are put in the accept queue list * so they can be accepted in accept(). If accept() cannot accept the * connection, it is marked as rejected so the cleanup function knows * to clean up the socket. */ struct list_head pending_links; struct list_head accept_queue; bool rejected; struct delayed_work connect_work; struct delayed_work pending_work; struct delayed_work close_work; bool close_work_scheduled; u32 peer_shutdown; bool sent_request; bool ignore_connecting_rst; /* Protected by lock_sock(sk) */ u64 buffer_size; u64 buffer_min_size; u64 buffer_max_size; /* Private to transport. */ void *trans; }; s64 vsock_connectible_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); struct sock *vsock_create_connected(struct sock *parent); void vsock_data_ready(struct sock *sk); /**** TRANSPORT ****/ struct vsock_transport_recv_notify_data { u64 data1; /* Transport-defined. */ u64 data2; /* Transport-defined. */ bool notify_on_block; }; struct vsock_transport_send_notify_data { u64 data1; /* Transport-defined. */ u64 data2; /* Transport-defined. */ }; /* Transport features flags */ /* Transport provides host->guest communication */ #define VSOCK_TRANSPORT_F_H2G 0x00000001 /* Transport provides guest->host communication */ #define VSOCK_TRANSPORT_F_G2H 0x00000002 /* Transport provides DGRAM communication */ #define VSOCK_TRANSPORT_F_DGRAM 0x00000004 /* Transport provides local (loopback) communication */ #define VSOCK_TRANSPORT_F_LOCAL 0x00000008 struct vsock_transport { struct module *module; /* Initialize/tear-down socket. */ int (*init)(struct vsock_sock *, struct vsock_sock *); void (*destruct)(struct vsock_sock *); void (*release)(struct vsock_sock *); /* Cancel all pending packets sent on vsock. */ int (*cancel_pkt)(struct vsock_sock *vsk); /* Connections. */ int (*connect)(struct vsock_sock *); /* DGRAM. */ int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *); int (*dgram_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, struct msghdr *, size_t len); bool (*dgram_allow)(u32 cid, u32 port); /* STREAM. */ /* TODO: stream_bind() */ ssize_t (*stream_dequeue)(struct vsock_sock *, struct msghdr *, size_t len, int flags); ssize_t (*stream_enqueue)(struct vsock_sock *, struct msghdr *, size_t len); s64 (*stream_has_data)(struct vsock_sock *); s64 (*stream_has_space)(struct vsock_sock *); u64 (*stream_rcvhiwat)(struct vsock_sock *); bool (*stream_is_active)(struct vsock_sock *); bool (*stream_allow)(u32 cid, u32 port); /* SEQ_PACKET. */ ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, int flags); int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, size_t len); bool (*seqpacket_allow)(u32 remote_cid); u32 (*seqpacket_has_data)(struct vsock_sock *vsk); /* Notification. */ int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); int (*notify_recv_init)(struct vsock_sock *, size_t, struct vsock_transport_recv_notify_data *); int (*notify_recv_pre_block)(struct vsock_sock *, size_t, struct vsock_transport_recv_notify_data *); int (*notify_recv_pre_dequeue)(struct vsock_sock *, size_t, struct vsock_transport_recv_notify_data *); int (*notify_recv_post_dequeue)(struct vsock_sock *, size_t, ssize_t, bool, struct vsock_transport_recv_notify_data *); int (*notify_send_init)(struct vsock_sock *, struct vsock_transport_send_notify_data *); int (*notify_send_pre_block)(struct vsock_sock *, struct vsock_transport_send_notify_data *); int (*notify_send_pre_enqueue)(struct vsock_sock *, struct vsock_transport_send_notify_data *); int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, struct vsock_transport_send_notify_data *); /* sk_lock held by the caller */ void (*notify_buffer_size)(struct vsock_sock *, u64 *); int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); /* SIOCOUTQ ioctl */ ssize_t (*unsent_bytes)(struct vsock_sock *vsk); /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); /* Addressing. */ u32 (*get_local_cid)(void); /* Read a single skb */ int (*read_skb)(struct vsock_sock *, skb_read_actor_t); /* Zero-copy. */ bool (*msgzerocopy_allow)(void); }; /**** CORE ****/ int vsock_core_register(const struct vsock_transport *t, int features); void vsock_core_unregister(const struct vsock_transport *t); /* The transport may downcast this to access transport-specific functions */ const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk); /**** UTILS ****/ /* vsock_table_lock must be held */ static inline bool __vsock_in_bound_table(struct vsock_sock *vsk) { return !list_empty(&vsk->bound_table); } /* vsock_table_lock must be held */ static inline bool __vsock_in_connected_table(struct vsock_sock *vsk) { return !list_empty(&vsk->connected_table); } void vsock_add_pending(struct sock *listener, struct sock *pending); void vsock_remove_pending(struct sock *listener, struct sock *pending); void vsock_enqueue_accept(struct sock *listener, struct sock *connected); void vsock_insert_connected(struct vsock_sock *vsk); void vsock_remove_bound(struct vsock_sock *vsk); void vsock_remove_connected(struct vsock_sock *vsk); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk); bool vsock_find_cid(unsigned int cid); /**** TAP ****/ struct vsock_tap { struct net_device *dev; struct module *module; struct list_head list; }; int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); #ifdef CONFIG_BPF_SYSCALL extern struct proto vsock_proto; int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void __init vsock_bpf_build_proto(void); #else static inline void __init vsock_bpf_build_proto(void) {} #endif static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t) { return t->msgzerocopy_allow && t->msgzerocopy_allow(); } #endif /* __AF_VSOCK_H__ */ |
| 4 15 15 233 233 219 22 4 9 4 6 13 3 2 2 1 1 6 4 4 6 1176 3 4 59 24 59 59 59 59 63 9 24 59 54 10 281 281 281 275 6 116 116 116 28 40 7 19 18 19 12 4 4 4 12 12 12 212 8 61 146 13 13 5 13 13 13 5 8 2 4 2 2 33 5 1 21 9 3 18 8 18 18 11 10 7 7 2 2 16 5 1 10 8 10 5 8 10 494 786 492 790 127 125 1 383 19 9 356 5 4 4 3 2 2 4 3 4 2 2 4 2 2 2 1 2 1 4 16 292 63 2 9 3 2 24 10 8 8 4 3 2 3 1 7 12 23 6 10 3 12 1 3 24 1 2 2 14 3 1 2 7 2 2 4 2 2 3 4 3 1 13 7 2 6 2 2 1 1 1 28 4 2 2 2 1 295 274 2441 1430 1126 2442 1066 1458 2439 221 959 2441 1122 1424 1175 1169 1172 1172 2 1172 1171 1173 1178 399 778 1174 256 255 254 95 1171 1262 809 463 1258 1258 1356 1478 2439 2439 2440 2438 1426 1126 287 101 387 390 157 234 5 387 392 5 387 388 1464 276 837 421 425 425 425 423 839 1110 73 73 1471 1469 1470 1475 1476 3241 3241 807 805 144 144 144 20 20 2 18 484 2 482 419 416 419 13 13 5 8 2 1202 1197 1198 3 17 4 5 13 4 1180 72 51 5 2 3 2 4 29 3 4 3 3 6 34 25 7 4 27 123 233 221 194 51 53 99 199 182 182 124 123 122 516 513 469 471 168 15 15 16 16 16 12 334 334 333 333 334 333 334 318 318 318 320 316 71 131 116 1 1 1 51 49 2 529 530 529 394 179 529 227 227 226 202 49 227 226 3462 3475 3461 3466 3389 195 3462 3464 388 389 3 392 390 1 389 390 14 423 420 1 424 907 36 30 5 364 126 329 364 282 212 2445 1438 1024 2366 1367 1025 6671 6673 122 6657 6631 463 5471 1605 6671 6666 154 153 5 10 10 10 1 1 1 7 3 30 6 5 1 2 3 37 23 15 1456 188 28 161 190 188 65 20 16 2 3 1 10 10 20 8 10 14 46 42 112 73 22 17 49 24 56 87 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 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 | // 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. * * Generic socket support routines. Memory allocators, socket lock/release * handler for protocols to use and generic option handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Fixes: * Alan Cox : Numerous verify_area() problems * Alan Cox : Connecting on a connecting socket * now returns an error for tcp. * Alan Cox : sock->protocol is set correctly. * and is not sometimes left as 0. * Alan Cox : connect handles icmp errors on a * connect properly. Unfortunately there * is a restart syscall nasty there. I * can't match BSD without hacking the C * library. Ideas urgently sought! * Alan Cox : Disallow bind() to addresses that are * not ours - especially broadcast ones!! * Alan Cox : Socket 1024 _IS_ ok for users. (fencepost) * Alan Cox : sock_wfree/sock_rfree don't destroy sockets, * instead they leave that for the DESTROY timer. * Alan Cox : Clean up error flag in accept * Alan Cox : TCP ack handling is buggy, the DESTROY timer * was buggy. Put a remove_sock() in the handler * for memory when we hit 0. Also altered the timer * code. The ACK stuff can wait and needs major * TCP layer surgery. * Alan Cox : Fixed TCP ack bug, removed remove sock * and fixed timer/inet_bh race. * Alan Cox : Added zapped flag for TCP * Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code * Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb * Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources * Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing. * Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so... * Rick Sladkey : Relaxed UDP rules for matching packets. * C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support * Pauline Middelink : identd support * Alan Cox : Fixed connect() taking signals I think. * Alan Cox : SO_LINGER supported * Alan Cox : Error reporting fixes * Anonymous : inet_create tidied up (sk->reuse setting) * Alan Cox : inet sockets don't set sk->type! * Alan Cox : Split socket option code * Alan Cox : Callbacks * Alan Cox : Nagle flag for Charles & Johannes stuff * Alex : Removed restriction on inet fioctl * Alan Cox : Splitting INET from NET core * Alan Cox : Fixed bogus SO_TYPE handling in getsockopt() * Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code * Alan Cox : Split IP from generic code * Alan Cox : New kfree_skbmem() * Alan Cox : Make SO_DEBUG superuser only. * Alan Cox : Allow anyone to clear SO_DEBUG * (compatibility fix) * Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput. * Alan Cox : Allocator for a socket is settable. * Alan Cox : SO_ERROR includes soft errors. * Alan Cox : Allow NULL arguments on some SO_ opts * Alan Cox : Generic socket allocation to make hooks * easier (suggested by Craig Metz). * Michael Pall : SO_ERROR returns positive errno again * Steve Whitehouse: Added default destructor to free * protocol private data. * Steve Whitehouse: Added various other default routines * common to several socket families. * Chris Evans : Call suser() check last on F_SETOWN * Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER. * Andi Kleen : Add sock_kmalloc()/sock_kfree_s() * Andi Kleen : Fix write_space callback * Chris Evans : Security fixes - signedness again * Arnaldo C. Melo : cleanups, use skb_queue_purge * * To Fix: */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/unaligned.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> #include <linux/static_key.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> #include <linux/compat.h> #include <linux/mroute.h> #include <linux/mroute6.h> #include <linux/icmpv6.h> #include <linux/uaccess.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> #include <net/proto_memory.h> #include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> #include <net/netprio_cgroup.h> #include <linux/sock_diag.h> #include <linux/filter.h> #include <net/sock_reuseport.h> #include <net/bpf_sk_storage.h> #include <trace/events/sock.h> #include <net/tcp.h> #include <net/busy_poll.h> #include <net/phonet/phonet.h> #include <linux/ethtool.h> #include "dev.h" static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); static void sock_def_write_space_wfree(struct sock *sk); static void sock_def_write_space(struct sock *sk); /** * sk_ns_capable - General socket capability test * @sk: Socket to use a capability on or through * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in the user * namespace @user_ns. */ bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap) { return file_ns_capable(sk->sk_socket->file, user_ns, cap) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(sk_ns_capable); /** * sk_capable - Socket global capability test * @sk: Socket to use a capability on or through * @cap: The global capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in all user * namespaces. */ bool sk_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, &init_user_ns, cap); } EXPORT_SYMBOL(sk_capable); /** * sk_net_capable - Network namespace socket capability test * @sk: Socket to use a capability on or through * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was created * and the current process has the capability @cap over the network namespace * the socket is a member of. */ bool sk_net_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); } EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have * one slock key per address family and separate keys for internal and * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ #define _sock_locks(x) \ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ x "27" , x "28" , x "AF_CAN" , \ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { _sock_locks("clock-") }; static const char *const af_family_kern_key_strings[AF_MAX+1] = { _sock_locks("k-sk_lock-") }; static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { _sock_locks("k-slock-") }; static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; static const char *const af_family_rlock_key_strings[AF_MAX+1] = { _sock_locks("rlock-") }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { _sock_locks("wlock-") }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { _sock_locks("elock-") }; /* * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; static struct lock_class_key af_rlock_keys[AF_MAX]; static struct lock_class_key af_wlock_keys[AF_MAX]; static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC * @sk: socket to set it on * * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. * It's the responsibility of the admin to adjust min_free_kbytes * to meet the requirements */ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward * progress of swapping. SOCK_MEMALLOC may be cleared while * it has rmem allocations due to the last swapfile being deactivated * but there is a risk that the socket is unusable due to exceeding * the rmem limits. Reclaim the reserves and obey rmem limits again. */ sk_mem_reclaim(sk); } EXPORT_SYMBOL_GPL(sk_clear_memalloc); int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int ret; unsigned int noreclaim_flag; /* these should have been dropped before queueing */ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); noreclaim_flag = memalloc_noreclaim_save(); ret = INDIRECT_CALL_INET(sk->sk_backlog_rcv, tcp_v6_do_rcv, tcp_v4_do_rcv, sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); void sk_error_report(struct sock *sk) { sk->sk_error_report(sk); switch (sk->sk_family) { case AF_INET: fallthrough; case AF_INET6: trace_inet_sk_error_report(sk); break; default: break; } } EXPORT_SYMBOL(sk_error_report); int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; tv.tv_usec = 0; } else { tv.tv_sec = timeo / HZ; tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; } if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; *(struct old_timeval32 *)optval = tv32; return sizeof(tv32); } if (old_timeval) { struct __kernel_old_timeval old_tv; old_tv.tv_sec = tv.tv_sec; old_tv.tv_usec = tv.tv_usec; *(struct __kernel_old_timeval *)optval = old_tv; return sizeof(old_tv); } *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } EXPORT_SYMBOL(sock_get_timeout); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval) { if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) return -EINVAL; if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; tv->tv_sec = tv32.tv_sec; tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; if (optlen < sizeof(old_tv)) return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; tv->tv_sec = old_tv.tv_sec; tv->tv_usec = old_tv.tv_usec; } else { if (optlen < sizeof(*tv)) return -EINVAL; if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } return 0; } EXPORT_SYMBOL(sock_copy_user_timeval); static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, bool old_timeval) { struct __kernel_sock_timeval tv; int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); long val; if (err) return err; if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; if (tv.tv_sec < 0) { static int warned __read_mostly; WRITE_ONCE(*timeo_p, 0); if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", __func__, current->comm, task_pid_nr(current)); } return 0; } val = MAX_SCHEDULE_TIMEOUT; if ((tv.tv_sec || tv.tv_usec) && (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))) val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); WRITE_ONCE(*timeo_p, val); return 0; } static bool sk_set_prio_allowed(const struct sock *sk, int val) { return ((val >= TC_PRIO_BESTEFFORT && val <= TC_PRIO_INTERACTIVE) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); } static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { case AF_UNSPEC: case AF_UNIX: return false; default: return true; } } static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { sk->sk_flags &= ~flags; if (sock_needs_netstamp(sk) && !(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); } } int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } skb->dev = NULL; skb_set_owner_r(skb, sk); /* we escape from rcu protected region, make sure we dont leak * a norefcounted dst */ skb_dst_force(skb); spin_lock_irqsave(&list->lock, flags); sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(__sock_queue_rcv_skb); int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { enum skb_drop_reason drop_reason; int err; err = sk_filter(sk, skb); if (err) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto out; } err = __sock_queue_rcv_skb(sk, skb); switch (err) { case -ENOMEM: drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; break; case -ENOBUFS: drop_reason = SKB_DROP_REASON_PROTO_MEM; break; default: drop_reason = SKB_NOT_DROPPED_YET; break; } out: if (reason) *reason = drop_reason; return err; } EXPORT_SYMBOL(sock_queue_rcv_skb_reason); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } if (nested) bh_lock_sock_nested(sk); else bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* * trylock + unlock semantics: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; } bh_unlock_sock(sk); out: if (refcounted) sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); goto out; } EXPORT_SYMBOL(__sk_receive_skb); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, u32)); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(__sk_dst_check); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(sk_dst_check); static int sock_bindtoindex_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); /* Sorry... */ ret = -EPERM; if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; if (ifindex < 0) goto out; /* Paired with all READ_ONCE() done locklessly. */ WRITE_ONCE(sk->sk_bound_dev_if, ifindex); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); sk_dst_reset(sk); ret = 0; out: #endif return ret; } int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk) { int ret; if (lock_sk) lock_sock(sk); ret = sock_bindtoindex_locked(sk, ifindex); if (lock_sk) release_sock(sk); return ret; } EXPORT_SYMBOL(sock_bindtoindex); static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; ret = -EINVAL; if (optlen < 0) goto out; /* Bind this socket to a particular device like "eth0", * as specified in the passed interface name. If the * name is "" or the option length is zero the socket * is not bound. */ if (optlen > IFNAMSIZ - 1) optlen = IFNAMSIZ - 1; memset(devname, 0, sizeof(devname)); ret = -EFAULT; if (copy_from_sockptr(devname, optval, optlen)) goto out; index = 0; if (devname[0] != '\0') { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, devname); if (dev) index = dev->ifindex; rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; } sockopt_lock_sock(sk); ret = sock_bindtoindex_locked(sk, index); sockopt_release_sock(sk); out: #endif return ret; } static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); struct net *net = sock_net(sk); char devname[IFNAMSIZ]; if (bound_dev_if == 0) { len = 0; goto zero; } ret = -EINVAL; if (len < IFNAMSIZ) goto out; ret = netdev_get_name(net, devname, bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; out: #endif return ret; } bool sk_mc_loop(const struct sock *sk) { if (dev_recursion_level()) return false; if (!sk) return true; /* IPV6_ADDRFORM can change sk->sk_family under us. */ switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_test_bit(MC_LOOP, sk); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_test_bit(MC6_LOOP, sk); #endif } WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); void sock_set_reuseaddr(struct sock *sk) { lock_sock(sk); sk->sk_reuse = SK_CAN_REUSE; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseaddr); void sock_set_reuseport(struct sock *sk) { lock_sock(sk); sk->sk_reuseport = true; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseport); void sock_no_linger(struct sock *sk) { lock_sock(sk); WRITE_ONCE(sk->sk_lingertime, 0); sock_set_flag(sk, SOCK_LINGER); release_sock(sk); } EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { WRITE_ONCE(sk->sk_priority, priority); } EXPORT_SYMBOL(sock_set_priority); void sock_set_sndtimeo(struct sock *sk, s64 secs) { lock_sock(sk); if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) WRITE_ONCE(sk->sk_sndtimeo, secs * HZ); else WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT); release_sock(sk); } EXPORT_SYMBOL(sock_set_sndtimeo); static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) { sock_valbool_flag(sk, SOCK_RCVTSTAMP, val); sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, val && ns); if (val) { sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new); sock_enable_timestamp(sk, SOCK_TIMESTAMP); } } void sock_enable_timestamps(struct sock *sk) { lock_sock(sk); __sock_set_timestamps(sk, true, false, true); release_sock(sk); } EXPORT_SYMBOL(sock_enable_timestamps); void sock_set_timestamp(struct sock *sk, int optname, bool valbool) { switch (optname) { case SO_TIMESTAMP_OLD: __sock_set_timestamps(sk, valbool, false, false); break; case SO_TIMESTAMP_NEW: __sock_set_timestamps(sk, valbool, true, false); break; case SO_TIMESTAMPNS_OLD: __sock_set_timestamps(sk, valbool, false, true); break; case SO_TIMESTAMPNS_NEW: __sock_set_timestamps(sk, valbool, true, true); break; } } static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) { struct net *net = sock_net(sk); struct net_device *dev = NULL; bool match = false; int *vclock_index; int i, num; if (sk->sk_bound_dev_if) dev = dev_get_by_index(net, sk->sk_bound_dev_if); if (!dev) { pr_err("%s: sock not bind to device\n", __func__); return -EOPNOTSUPP; } num = ethtool_get_phc_vclocks(dev, &vclock_index); dev_put(dev); for (i = 0; i < num; i++) { if (*(vclock_index + i) == phc_index) { match = true; break; } } if (num > 0) kfree(vclock_index); if (!match) return -EINVAL; WRITE_ONCE(sk->sk_bind_phc, phc_index); return 0; } int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping) { int val = timestamping.flags; int ret; if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID_TCP && !(val & SOF_TIMESTAMPING_OPT_ID)) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk_is_tcp(sk)) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID_TCP) atomic_set(&sk->sk_tskey, tcp_sk(sk)->write_seq); else atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { atomic_set(&sk->sk_tskey, 0); } } if (val & SOF_TIMESTAMPING_OPT_STATS && !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; if (val & SOF_TIMESTAMPING_BIND_PHC) { ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); if (ret) return ret; } WRITE_ONCE(sk->sk_tsflags, val); sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); sock_valbool_flag(sk, SOCK_TIMESTAMPING_ANY, !!(val & TSFLAGS_ANY)); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); return 0; } #if defined(CONFIG_CGROUP_BPF) void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op) { struct bpf_sock_ops_kern sock_ops; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = op; sock_ops.is_fullsock = 1; sock_ops.sk = sk; bpf_skops_init_skb(&sock_ops, skb, 0); __cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS); } #endif void sock_set_keepalive(struct sock *sk) { lock_sock(sk); if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, true); sock_valbool_flag(sk, SOCK_KEEPOPEN, true); release_sock(sk); } EXPORT_SYMBOL(sock_set_keepalive); static void __sock_set_rcvbuf(struct sock *sk, int val) { /* Ensure val * 2 fits into an int, to prevent max_t() from treating it * as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* We double it on the way in to account for "struct sk_buff" etc. * overhead. Applications assume that the SO_RCVBUF setting they make * will allow that much actual data to be received on that socket. * * Applications are unaware that "struct sk_buff" and other overheads * allocate from the receive buffer during socket buffer allocation. * * And after considering the possible alternatives, returning the value * we actually used in getsockopt is the most desirable behavior. */ WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); } void sock_set_rcvbuf(struct sock *sk, int val) { lock_sock(sk); __sock_set_rcvbuf(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } void sock_set_mark(struct sock *sk, u32 val) { lock_sock(sk); __sock_set_mark(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_mark); static void sock_release_reserved_memory(struct sock *sk, int bytes) { /* Round down bytes to multiple of pages */ bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } static int sock_reserve_memory(struct sock *sk, int bytes) { long allocated; bool charged; int pages; if (!mem_cgroup_sockets_enabled || !sk->sk_memcg || !sk_has_account(sk)) return -EOPNOTSUPP; if (!bytes) return 0; pages = sk_mem_pages(bytes); /* pre-charge to memcg */ charged = mem_cgroup_charge_skmem(sk->sk_memcg, pages, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!charged) return -ENOMEM; /* pre-charge to forward_alloc */ sk_memory_allocated_add(sk, pages); allocated = sk_memory_allocated(sk); /* If the system goes into memory pressure with this * precharge, give up and return error. */ if (allocated > sk_prot_mem_limits(sk, 1)) { sk_memory_allocated_sub(sk, pages); mem_cgroup_uncharge_skmem(sk->sk_memcg, pages); return -ENOMEM; } sk_forward_alloc_add(sk, pages << PAGE_SHIFT); WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } #ifdef CONFIG_PAGE_POOL /* This is the number of tokens and frags that the user can SO_DEVMEM_DONTNEED * in 1 syscall. The limit exists to limit the amount of memory the kernel * allocates to copy these tokens, and to prevent looping over the frags for * too long. */ #define MAX_DONTNEED_TOKENS 128 #define MAX_DONTNEED_FRAGS 1024 static noinline_for_stack int sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) { unsigned int num_tokens, i, j, k, netmem_num = 0; struct dmabuf_token *tokens; int ret = 0, num_frags = 0; netmem_ref netmems[16]; if (!sk_is_tcp(sk)) return -EBADF; if (optlen % sizeof(*tokens) || optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) return -EINVAL; num_tokens = optlen / sizeof(*tokens); tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL); if (!tokens) return -ENOMEM; if (copy_from_sockptr(tokens, optval, optlen)) { kvfree(tokens); return -EFAULT; } xa_lock_bh(&sk->sk_user_frags); for (i = 0; i < num_tokens; i++) { for (j = 0; j < tokens[i].token_count; j++) { if (++num_frags > MAX_DONTNEED_FRAGS) goto frag_limit_reached; netmem_ref netmem = (__force netmem_ref)__xa_erase( &sk->sk_user_frags, tokens[i].token_start + j); if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem))) continue; netmems[netmem_num++] = netmem; if (netmem_num == ARRAY_SIZE(netmems)) { xa_unlock_bh(&sk->sk_user_frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); netmem_num = 0; xa_lock_bh(&sk->sk_user_frags); } ret++; } } frag_limit_reached: xa_unlock_bh(&sk->sk_user_frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); kvfree(tokens); return ret; } #endif void sockopt_lock_sock(struct sock *sk) { /* When current->bpf_ctx is set, the setsockopt is called from * a bpf prog. bpf has ensured the sk lock has been * acquired before calling setsockopt(). */ if (has_current_bpf_ctx()) return; lock_sock(sk); } EXPORT_SYMBOL(sockopt_lock_sock); void sockopt_release_sock(struct sock *sk) { if (has_current_bpf_ctx()) return; release_sock(sk); } EXPORT_SYMBOL(sockopt_release_sock); bool sockopt_ns_capable(struct user_namespace *ns, int cap) { return has_current_bpf_ctx() || ns_capable(ns, cap); } EXPORT_SYMBOL(sockopt_ns_capable); bool sockopt_capable(int cap) { return has_current_bpf_ctx() || capable(cap); } EXPORT_SYMBOL(sockopt_capable); static int sockopt_validate_clockid(__kernel_clockid_t value) { switch (value) { case CLOCK_REALTIME: case CLOCK_MONOTONIC: case CLOCK_TAI: return 0; } return -EINVAL; } /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. */ int sk_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct so_timestamping timestamping; struct socket *sock = sk->sk_socket; struct sock_txtime sk_txtime; int val; int valbool; struct linger ling; int ret = 0; /* * Options without arguments */ if (optname == SO_BINDTODEVICE) return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; /* handle options which do not require locking the socket. */ switch (optname) { case SO_PRIORITY: if (sk_set_prio_allowed(sk, val)) { sock_set_priority(sk, val); return 0; } return -EPERM; case SO_PASSSEC: assign_bit(SOCK_PASSSEC, &sock->flags, valbool); return 0; case SO_PASSCRED: assign_bit(SOCK_PASSCRED, &sock->flags, valbool); return 0; case SO_PASSPIDFD: assign_bit(SOCK_PASSPIDFD, &sock->flags, valbool); return 0; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: case SO_ERROR: return -ENOPROTOOPT; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: if (val < 0) return -EINVAL; WRITE_ONCE(sk->sk_ll_usec, val); return 0; case SO_PREFER_BUSY_POLL: if (valbool && !sockopt_capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); return 0; case SO_BUSY_POLL_BUDGET: if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) return -EPERM; if (val < 0 || val > U16_MAX) return -EINVAL; WRITE_ONCE(sk->sk_busy_poll_budget, val); return 0; #endif case SO_MAX_PACING_RATE: { unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; unsigned long pacing_rate; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && copy_from_sockptr(&ulval, optval, sizeof(ulval))) { return -EFAULT; } if (ulval != ~0UL) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); /* Pairs with READ_ONCE() from sk_getsockopt() */ WRITE_ONCE(sk->sk_max_pacing_rate, ulval); pacing_rate = READ_ONCE(sk->sk_pacing_rate); if (ulval < pacing_rate) WRITE_ONCE(sk->sk_pacing_rate, ulval); return 0; } case SO_TXREHASH: if (val < -1 || val > 1) return -EINVAL; if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() * and sk_getsockopt(). */ WRITE_ONCE(sk->sk_txrehash, (u8)val); return 0; case SO_PEEK_OFF: { int (*set_peek_off)(struct sock *sk, int val); set_peek_off = READ_ONCE(sock->ops)->set_peek_off; if (set_peek_off) ret = set_peek_off(sk, val); else ret = -EOPNOTSUPP; return ret; } #ifdef CONFIG_PAGE_POOL case SO_DEVMEM_DONTNEED: return sock_devmem_dontneed(sk, optval, optlen); #endif } sockopt_lock_sock(sk); switch (optname) { case SO_DEBUG: if (val && !sockopt_capable(CAP_NET_ADMIN)) ret = -EACCES; else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: if (valbool && !sk_is_inet(sk)) ret = -EOPNOTSUPP; else sk->sk_reuseport = valbool; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); sk_dst_reset(sk); break; case SO_BROADCAST: sock_valbool_flag(sk, SOCK_BROADCAST, valbool); break; case SO_SNDBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; case SO_SNDBUFFORCE: if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ if (val < 0) val = 0; goto set_sndbuf; case SO_RCVBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ __sock_set_rcvbuf(sk, max(val, 0)); break; case SO_KEEPALIVE: if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, valbool); sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); break; case SO_OOBINLINE: sock_valbool_flag(sk, SOCK_URGINLINE, valbool); break; case SO_NO_CHECK: sk->sk_no_check_tx = valbool; break; case SO_LINGER: if (optlen < sizeof(ling)) { ret = -EINVAL; /* 1003.1g */ break; } if (copy_from_sockptr(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } if (!ling.l_onoff) { sock_reset_flag(sk, SOCK_LINGER); } else { unsigned long t_sec = ling.l_linger; if (t_sec >= MAX_SCHEDULE_TIMEOUT / HZ) WRITE_ONCE(sk->sk_lingertime, MAX_SCHEDULE_TIMEOUT); else WRITE_ONCE(sk->sk_lingertime, t_sec * HZ); sock_set_flag(sk, SOCK_LINGER); } break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: if (optlen == sizeof(timestamping)) { if (copy_from_sockptr(×tamping, optval, sizeof(timestamping))) { ret = -EFAULT; break; } } else { memset(×tamping, 0, sizeof(timestamping)); timestamping.flags = val; } ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: { int (*set_rcvlowat)(struct sock *sk, int val) = NULL; if (val < 0) val = INT_MAX; if (sock) set_rcvlowat = READ_ONCE(sock->ops)->set_rcvlowat; if (set_rcvlowat) ret = set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; } case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); break; case SO_ATTACH_FILTER: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_attach_filter(&fprog, sk); break; } case SO_ATTACH_BPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_attach_bpf(ufd, sk); } break; case SO_ATTACH_REUSEPORT_CBPF: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_reuseport_attach_filter(&fprog, sk); break; } case SO_ATTACH_REUSEPORT_EBPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_reuseport_attach_bpf(ufd, sk); } break; case SO_DETACH_REUSEPORT_BPF: ret = reuseport_detach_prog(sk); break; case SO_DETACH_FILTER: ret = sk_detach_filter(sk); break; case SO_LOCK_FILTER: if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) ret = -EPERM; else sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); break; case SO_MARK: if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } __sock_set_mark(sk, val); break; case SO_RCVMARK: sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break; case SO_RCVPRIORITY: sock_valbool_flag(sk, SOCK_RCVPRIORITY, valbool); break; case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; case SO_WIFI_STATUS: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; case SO_SELECT_ERR_QUEUE: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; case SO_INCOMING_CPU: reuseport_update_incoming_cpu(sk, val); break; case SO_CNX_ADVICE: if (val == 1) dst_negative_advice(sk); break; case SO_ZEROCOPY: if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { if (!(sk_is_tcp(sk) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -EOPNOTSUPP; } else if (sk->sk_family != PF_RDS) { ret = -EOPNOTSUPP; } if (!ret) { if (val < 0 || val > 1) ret = -EINVAL; else sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); } break; case SO_TXTIME: if (optlen != sizeof(struct sock_txtime)) { ret = -EINVAL; break; } else if (copy_from_sockptr(&sk_txtime, optval, sizeof(struct sock_txtime))) { ret = -EFAULT; break; } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) { ret = -EINVAL; break; } /* CLOCK_MONOTONIC is only used by sch_fq, and this packet * scheduler has enough safe guards. */ if (sk_txtime.clockid != CLOCK_MONOTONIC && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } ret = sockopt_validate_clockid(sk_txtime.clockid); if (ret) break; sock_valbool_flag(sk, SOCK_TXTIME, true); sk->sk_clockid = sk_txtime.clockid; sk->sk_txtime_deadline_mode = !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); sk->sk_txtime_report_errors = !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); break; case SO_BINDTOIFINDEX: ret = sock_bindtoindex_locked(sk, val); break; case SO_BUF_LOCK: if (val & ~SOCK_BUF_LOCK_MASK) { ret = -EINVAL; break; } sk->sk_userlocks = val | (sk->sk_userlocks & ~SOCK_BUF_LOCK_MASK); break; case SO_RESERVE_MEM: { int delta; if (val < 0) { ret = -EINVAL; break; } delta = val - sk->sk_reserved_mem; if (delta < 0) sock_release_reserved_memory(sk, -delta); else ret = sock_reserve_memory(sk, delta); break; } default: ret = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return ret; } int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { return sk_setsockopt(sock->sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_setsockopt); static const struct cred *sk_get_peer_cred(struct sock *sk) { const struct cred *cred; spin_lock(&sk->sk_peer_lock); cred = get_cred(sk->sk_peer_cred); spin_unlock(&sk->sk_peer_lock); return cred; } static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; if (cred) { struct user_namespace *current_ns = current_user_ns(); ucred->uid = from_kuid_munged(current_ns, cred->euid); ucred->gid = from_kgid_munged(current_ns, cred->egid); } } static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; for (i = 0; i < src->ngroups; i++) { gid_t gid = from_kgid_munged(user_ns, src->gid[i]); if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; } return 0; } int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct socket *sock = sk->sk_socket; union { int val; u64 val64; unsigned long ulval; struct linger ling; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; struct so_timestamping timestamping; } v; int lv = sizeof(int); int len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; memset(&v, 0, sizeof(v)); switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; case SO_DONTROUTE: v.val = sock_flag(sk, SOCK_LOCALROUTE); break; case SO_BROADCAST: v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: v.val = sk->sk_reuse; break; case SO_REUSEPORT: v.val = sk->sk_reuseport; break; case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: v.val = sk->sk_type; break; case SO_PROTOCOL: v.val = sk->sk_protocol; break; case SO_DOMAIN: v.val = sk->sk_family; break; case SO_ERROR: v.val = -sock_error(sk); if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; case SO_OOBINLINE: v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: lv = sizeof(v.ling); v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = READ_ONCE(sk->sk_lingertime) / HZ; break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; case SO_TIMESTAMPNS_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMP_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPNS_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only * returning the flags when they were set through the same option. * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. */ if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { v.timestamping.flags = READ_ONCE(sk->sk_tsflags); v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); } break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v, SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: v.val = 1; break; case SO_PASSCRED: v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; case SO_PASSPIDFD: v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags); break; case SO_PEERCRED: { struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); spin_unlock(&sk->sk_peer_lock); if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } case SO_PEERPIDFD: { struct pid *peer_pid; struct file *pidfd_file = NULL; int pidfd; if (len > sizeof(pidfd)) len = sizeof(pidfd); spin_lock(&sk->sk_peer_lock); peer_pid = get_pid(sk->sk_peer_pid); spin_unlock(&sk->sk_peer_lock); if (!peer_pid) return -ENODATA; pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); put_pid(peer_pid); if (pidfd < 0) return pidfd; if (copy_to_sockptr(optval, &pidfd, len) || copy_to_sockptr(optlen, &len, sizeof(int))) { put_unused_fd(pidfd); fput(pidfd_file); return -EFAULT; } fd_install(pidfd, pidfd_file); return 0; } case SO_PEERGROUPS: { const struct cred *cred; int ret, n; cred = sk_get_peer_cred(sk); if (!cred) return -ENODATA; n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); put_cred(cred); return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); ret = groups_to_user(optval, cred->group_info); put_cred(cred); if (ret) return ret; goto lenout; } case SO_PEERNAME: { struct sockaddr_storage address; lv = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; if (copy_to_sockptr(optval, &address, len)) return -EFAULT; goto lenout; } /* Dubious BSD thing... Probably nobody even uses it, but * the UNIX standard wants it for whatever reason... -DaveM */ case SO_ACCEPTCONN: v.val = sk->sk_state == TCP_LISTEN; break; case SO_PASSSEC: v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); break; case SO_PEERSEC: return security_socket_getpeersec_stream(sock, optval, optlen, len); case SO_MARK: v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: v.val = sock_flag(sk, SOCK_RCVMARK); break; case SO_RCVPRIORITY: v.val = sock_flag(sk, SOCK_RCVPRIORITY); break; case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; case SO_WIFI_STATUS: v.val = sock_flag(sk, SOCK_WIFI_STATUS); break; case SO_PEEK_OFF: if (!READ_ONCE(sock->ops)->set_peek_off) return -EOPNOTSUPP; v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); break; case SO_BINDTODEVICE: return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: len = sk_get_filter(sk, optval, len); if (len < 0) return len; goto lenout; case SO_LOCK_FILTER: v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; case SO_BPF_EXTENSIONS: v.val = bpf_tell_extensions(); break; case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); break; #endif case SO_MAX_PACING_RATE: /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ v.val = min_t(unsigned long, ~0U, READ_ONCE(sk->sk_max_pacing_rate)); } break; case SO_INCOMING_CPU: v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: { u32 meminfo[SK_MEMINFO_VARS]; sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; } #ifdef CONFIG_NET_RX_BUSY_POLL case SO_INCOMING_NAPI_ID: v.val = READ_ONCE(sk->sk_napi_id); /* aggregate non-NAPI IDs down to 0 */ if (!napi_id_valid(v.val)) v.val = 0; break; #endif case SO_COOKIE: lv = sizeof(u64); if (len < lv) return -EINVAL; v.val64 = sock_gen_cookie(sk); break; case SO_ZEROCOPY: v.val = sock_flag(sk, SOCK_ZEROCOPY); break; case SO_TXTIME: lv = sizeof(v.txtime); v.txtime.clockid = sk->sk_clockid; v.txtime.flags |= sk->sk_txtime_deadline_mode ? SOF_TXTIME_DEADLINE_MODE : 0; v.txtime.flags |= sk->sk_txtime_report_errors ? SOF_TXTIME_REPORT_ERRORS : 0; break; case SO_BINDTOIFINDEX: v.val = READ_ONCE(sk->sk_bound_dev_if); break; case SO_NETNS_COOKIE: lv = sizeof(u64); if (len != lv) return -EINVAL; v.val64 = sock_net(sk)->net_cookie; break; case SO_BUF_LOCK: v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; break; case SO_RESERVE_MEM: v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: /* Paired with WRITE_ONCE() in sk_setsockopt() */ v.val = READ_ONCE(sk->sk_txrehash); break; default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). */ return -ENOPROTOOPT; } if (len > lv) len = lv; if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } /* * Initialize an sk_lock. * * (We also register the sk_lock with the lock validator.) */ static inline void sock_lock_init(struct sock *sk) { sk_owner_clear(sk); if (sk->sk_kern_sock) sock_lock_init_class_and_name( sk, af_family_kern_slock_key_strings[sk->sk_family], af_family_kern_slock_keys + sk->sk_family, af_family_kern_key_strings[sk->sk_family], af_family_kern_keys + sk->sk_family); else sock_lock_init_class_and_name( sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], af_family_keys + sk->sk_family); } /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarily, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif /* If we move sk_tx_queue_mapping out of the private section, * we must check if sk_tx_queue_clear() is called after * sock_copy() in sk_clone_lock(). */ BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < offsetof(struct sock, sk_dontcopy_begin) || offsetof(struct sock, sk_tx_queue_mapping) >= offsetof(struct sock, sk_dontcopy_end)); memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); unsafe_memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, prot->obj_size - offsetof(struct sock, sk_dontcopy_end), /* alloc is larger than struct, see sk_prot_alloc() */); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { struct sock *sk; struct kmem_cache *slab; slab = prot->slab; if (slab != NULL) { sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); if (!sk) return sk; if (want_init_on_alloc(priority)) sk_prot_clear_nulls(sk, prot->obj_size); } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { if (security_sk_alloc(sk, family, priority)) goto out_free; if (!try_module_get(prot->owner)) goto out_free_sec; } return sk; out_free_sec: security_sk_free(sk); out_free: if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); return NULL; } static void sk_prot_free(struct proto *prot, struct sock *sk) { struct kmem_cache *slab; struct module *owner; owner = prot->owner; slab = prot->slab; cgroup_sk_free(&sk->sk_cgrp_data); mem_cgroup_sk_free(sk); security_sk_free(sk); sk_owner_put(sk); if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); module_put(owner); } /** * sk_alloc - All socket objects are allocated here * @net: the applicable net namespace * @family: protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance * @kern: is this to be a kernel socket? */ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { struct sock *sk; sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family); if (sk) { sk->sk_family = family; /* * See comment in struct sock definition to understand * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } else { net_passive_inc(net); __netns_tracker_alloc(net, &sk->ns_tracker, false, priority); } sock_net_set(sk, net); refcount_set(&sk->sk_wmem_alloc, 1); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); sk_tx_queue_clear(sk); } return sk; } EXPORT_SYMBOL(sk_alloc); /* Sockets having SOCK_RCU_FREE will call this function after one RCU * grace period. This is the case for UDP sockets and TCP listeners. */ static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); struct net *net = sock_net(sk); struct sk_filter *filter; if (sk->sk_destruct) sk->sk_destruct(sk); filter = rcu_dereference_check(sk->sk_filter, refcount_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); #ifdef CONFIG_BPF_SYSCALL bpf_sk_storage_free(sk); #endif if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; } /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); if (likely(sk->sk_net_refcnt)) { put_net_track(net, &sk->ns_tracker); } else { __netns_tracker_free(net, &sk->ns_tracker, false); net_passive_dec(net); } sk_prot_free(sk->sk_prot_creator, sk); } void sk_net_refcnt_upgrade(struct sock *sk) { struct net *net = sock_net(sk); WARN_ON_ONCE(sk->sk_net_refcnt); __netns_tracker_free(net, &sk->ns_tracker, false); net_passive_dec(net); sk->sk_net_refcnt = 1; get_net_track(net, &sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); } EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade); void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); if (rcu_access_pointer(sk->sk_reuseport_cb)) { reuseport_detach_sock(sk); use_call_rcu = true; } if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); } static void __sk_free(struct sock *sk) { if (likely(sk->sk_net_refcnt)) sock_inuse_add(sock_net(sk), -1); if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk))) sock_diag_broadcast_destroy(sk); else sk_destruct(sk); } void sk_free(struct sock *sk) { /* * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ if (refcount_dec_and_test(&sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sk_free); static void sk_init_common(struct sock *sk) { skb_queue_head_init(&sk->sk_receive_queue); skb_queue_head_init(&sk->sk_write_queue); skb_queue_head_init(&sk->sk_error_queue); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_receive_queue.lock, af_rlock_keys + sk->sk_family, af_family_rlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_write_queue.lock, af_wlock_keys + sk->sk_family, af_family_wlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_error_queue.lock, af_elock_keys + sk->sk_family, af_family_elock_key_strings[sk->sk_family]); if (sk->sk_kern_sock) lockdep_set_class_and_name(&sk->sk_callback_lock, af_kern_callback_keys + sk->sk_family, af_family_kern_clock_key_strings[sk->sk_family]); else lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); } /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) */ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct proto *prot = READ_ONCE(sk->sk_prot); struct sk_filter *filter; bool is_charged = true; struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); if (!newsk) goto out; sock_copy(newsk, sk); newsk->sk_prot_creator = prot; /* SANITY */ if (likely(newsk->sk_net_refcnt)) { get_net_track(sock_net(newsk), &newsk->ns_tracker, priority); sock_inuse_add(sock_net(newsk), 1); } else { /* Kernel sockets are not elevating the struct net refcount. * Instead, use a tracker to more easily detect if a layer * is not properly dismantling its kernel sockets at netns * destroy time. */ net_passive_inc(sock_net(newsk)); __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, false, priority); } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ refcount_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; newsk->sk_reserved_mem = 0; atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); RCU_INIT_POINTER(newsk->sk_filter, filter); rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new * socket if we couldn't charge it in the first place * as otherwise we uncharge the parent's filter. */ if (!is_charged) RCU_INIT_POINTER(newsk->sk_filter, NULL); sk_free_unlock_clone(newsk); newsk = NULL; goto out; } RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); if (bpf_sk_storage_clone(sk, newsk)) { sk_free_unlock_clone(newsk); newsk = NULL; goto out; } /* Clear sk_user_data if parent had the pointer tagged * as not suitable for copying when cloning. */ if (sk_user_data_is_nocopy(newsk)) newsk->sk_user_data = NULL; newsk->sk_err = 0; newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&newsk->sk_refcnt, 2); sk_set_socket(newsk, NULL); sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); out: return newsk; } EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_free_unlock_clone(struct sock *sk) { /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ sk->sk_destruct = NULL; bh_unlock_sock(sk); sk_free(sk); } EXPORT_SYMBOL_GPL(sk_free_unlock_clone); static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst) { bool is_ipv6 = false; u32 max_size; #if IS_ENABLED(CONFIG_IPV6) is_ipv6 = (sk->sk_family == AF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)); #endif /* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ max_size = is_ipv6 ? READ_ONCE(dst->dev->gso_max_size) : READ_ONCE(dst->dev->gso_ipv4_max_size); if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk)) max_size = GSO_LEGACY_MAX_SIZE; return max_size - (MAX_TCP_HEADER + 1); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; sk->sk_route_caps = dst->dev->features; if (sk_is_tcp(sk)) { struct inet_connection_sock *icsk = inet_csk(sk); sk->sk_route_caps |= NETIF_F_GSO; icsk->icsk_ack.dst_quick_ack = dst_metric(dst, RTAX_QUICKACK); } if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; if (unlikely(sk->sk_gso_disabled)) sk->sk_route_caps &= ~NETIF_F_GSO_MASK; if (sk_can_gso(sk)) { if (dst->header_len && !xfrm_dst_offload_ok(dst)) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dst); /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); } } sk->sk_gso_max_segs = max_segs; sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); /* * Simple resource managers for sockets. */ /* * Write buffer destructor automatically called from kfree_skb. */ void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; bool free; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { if (sock_flag(sk, SOCK_RCU_FREE) && sk->sk_write_space == sock_def_write_space) { rcu_read_lock(); free = refcount_sub_and_test(len, &sk->sk_wmem_alloc); sock_def_write_space_wfree(sk); rcu_read_unlock(); if (unlikely(free)) __sk_free(sk); return; } /* * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call */ WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); sk->sk_write_space(sk); len = 1; } /* * if sk_wmem_alloc reaches 0, we must finish what sk_free() * could not do because of in-flight packets */ if (refcount_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); /* This variant of sock_wfree() is used by TCP, * since it sets SOCK_USE_WRITE_QUEUE. */ void __sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) __sk_free(sk); } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); #ifdef CONFIG_INET if (unlikely(!sk_fullsock(sk))) return skb_set_owner_edemux(skb, sk); #endif skb->sk = sk; skb->destructor = sock_wfree; skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation * is enough to guarantee sk_free() won't free this sock until * all in-flight packets are completed */ refcount_add(skb->truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(skb_set_owner_w); static bool can_skb_orphan_partial(const struct sk_buff *skb) { /* Drivers depend on in-order delivery for crypto offload, * partial orphan breaks out-of-order-OK logic. */ if (skb_is_decrypted(skb)) return false; return (skb->destructor == sock_wfree || (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); } /* This helper is used by netem, as it can hold packets in its * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. * But we also want to keep skb->sk set because some packet schedulers * rely on it (sch_fq for example). */ void skb_orphan_partial(struct sk_buff *skb) { if (skb_is_tcp_pure_ack(skb)) return; if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) return; skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); /* * Read buffer destructor automatically called from kfree_skb. */ void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; atomic_sub(len, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, len); } EXPORT_SYMBOL(sock_rfree); /* * Buffer destructor for skbs that are not used directly in read or write * path, e.g. for error handler skbs. Automatically called from kfree_skb. */ void sock_efree(struct sk_buff *skb) { sock_put(skb->sk); } EXPORT_SYMBOL(sock_efree); /* Buffer destructor for prefetch/receive path where reference count may * not be held, e.g. for listen sockets. */ #ifdef CONFIG_INET void sock_pfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (!sk_is_refcounted(sk)) return; if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { inet_reqsk(sk)->rsk_listener = NULL; reqsk_free(inet_reqsk(sk)); return; } sock_gen_put(sk); } EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); unsigned long __sock_i_ino(struct sock *sk) { unsigned long ino; read_lock(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; read_unlock(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(__sock_i_ino); unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; local_bh_disable(); ino = __sock_i_ino(sk); local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. */ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; } } return NULL; } EXPORT_SYMBOL(sock_wmalloc); static void sock_ofree(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_omem_alloc); } struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority) { struct sk_buff *skb; /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); if (!skb) return NULL; atomic_add(skb->truesize, &sk->sk_omem_alloc); skb->sk = sk; skb->destructor = sock_ofree; return skb; } /* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if ((unsigned int)size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. */ atomic_add(size, &sk->sk_omem_alloc); mem = kmalloc(size, priority); if (mem) return mem; atomic_sub(size, &sk->sk_omem_alloc); } return NULL; } EXPORT_SYMBOL(sock_kmalloc); /* * Duplicate the input "src" memory block using the socket's * option memory buffer. */ void *sock_kmemdup(struct sock *sk, const void *src, int size, gfp_t priority) { void *mem; mem = sock_kmalloc(sk, size, priority); if (mem) memcpy(mem, src, size); return mem; } EXPORT_SYMBOL(sock_kmemdup); /* Free an option memory block. Note, we actually want the inline * here as this allows gcc to detect the nullify and fold away the * condition entirely. */ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size, const bool nullify) { if (WARN_ON_ONCE(!mem)) return; if (nullify) kfree_sensitive(mem); else kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } void sock_kfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, false); } EXPORT_SYMBOL(sock_kfree_s); void sock_kzfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, true); } EXPORT_SYMBOL(sock_kzfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); for (;;) { if (!timeo) break; if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; if (READ_ONCE(sk->sk_err)) break; timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(sk), &wait); return timeo; } /* * Generic send/receive buffer handlers */ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order) { struct sk_buff *skb; long timeo; int err; timeo = sock_sndtimeo(sk, noblock); for (;;) { err = sock_error(sk); if (err != 0) goto failure; err = -EPIPE; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto failure; if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; if (!timeo) goto failure; if (signal_pending(current)) goto interrupted; timeo = sock_wait_for_wmem(sk, timeo); } skb = alloc_skb_with_frags(header_len, data_len, max_page_order, errcode, sk->sk_allocation); if (skb) skb_set_owner_w(skb, sk); return skb; interrupted: err = sock_intr_errno(timeo); failure: *errcode = err; return NULL; } EXPORT_SYMBOL(sock_alloc_send_pskb); int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; BUILD_BUG_ON(SOF_TIMESTAMPING_LAST == (1 << 31)); switch (cmsg->cmsg_type) { case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; tsflags = *(u32 *)CMSG_DATA(cmsg); if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) return -EINVAL; sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; case SCM_TXTIME: if (!sock_flag(sk, SOCK_TXTIME)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64))) return -EINVAL; sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg)); break; case SCM_TS_OPT_ID: if (sk_is_tcp(sk)) return -EINVAL; tsflags = READ_ONCE(sk->sk_tsflags); if (!(tsflags & SOF_TIMESTAMPING_OPT_ID)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->ts_opt_id = *(u32 *)CMSG_DATA(cmsg); sockc->tsflags |= SOCKCM_FLAG_TS_OPT_ID; break; /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: break; case SO_PRIORITY: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; if (!sk_set_prio_allowed(sk, *(u32 *)CMSG_DATA(cmsg))) return -EPERM; sockc->priority = *(u32 *)CMSG_DATA(cmsg); break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL(__sock_cmsg_send); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc) { struct cmsghdr *cmsg; int ret; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; ret = __sock_cmsg_send(sk, cmsg, sockc); if (ret) return ret; } return 0; } EXPORT_SYMBOL(sock_cmsg_send); static void sk_enter_memory_pressure(struct sock *sk) { if (!sk->sk_prot->enter_memory_pressure) return; sk->sk_prot->enter_memory_pressure(sk); } static void sk_leave_memory_pressure(struct sock *sk) { if (sk->sk_prot->leave_memory_pressure) { INDIRECT_CALL_INET_1(sk->sk_prot->leave_memory_pressure, tcp_leave_memory_pressure, sk); } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; if (memory_pressure && READ_ONCE(*memory_pressure)) WRITE_ONCE(*memory_pressure, 0); } } DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); /** * skb_page_frag_refill - check that a page_frag contains enough room * @sz: minimum size of the fragment we want to get * @pfrag: pointer to page_frag * @gfp: priority for memory allocation * * Note: While this allocator tries to use high order pages, there is * no guarantee that allocations succeed. Therefore, @sz MUST be * less or equal than PAGE_SIZE. */ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { if (page_ref_count(pfrag->page) == 1) { pfrag->offset = 0; return true; } if (pfrag->offset + sz <= pfrag->size) return true; put_page(pfrag->page); } pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER && !static_branch_unlikely(&net_high_order_alloc_disable_key)) { /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; return true; } } pfrag->page = alloc_page(gfp); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE; return true; } return false; } EXPORT_SYMBOL(skb_page_frag_refill); bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) return true; sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return false; } EXPORT_SYMBOL(sk_page_frag_refill); void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); } void __release_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { struct sk_buff *skb, *next; while ((skb = sk->sk_backlog.head) != NULL) { sk->sk_backlog.head = sk->sk_backlog.tail = NULL; spin_unlock_bh(&sk->sk_lock.slock); do { next = skb->next; prefetch(next); DEBUG_NET_WARN_ON_ONCE(skb_dst_is_noref(skb)); skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); cond_resched(); skb = next; } while (skb != NULL); spin_lock_bh(&sk->sk_lock.slock); } /* * Doing the zeroing here guarantee we can not loop forever * while a wild producer attempts to flood us. */ sk->sk_backlog.len = 0; } void __sk_flush_backlog(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); __release_sock(sk); if (sk->sk_prot->release_cb) INDIRECT_CALL_INET_1(sk->sk_prot->release_cb, tcp_release_cb, sk); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL_GPL(__sk_flush_backlog); /** * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return rc; } EXPORT_SYMBOL(sk_wait_data); /** * __sk_mem_raise_allocated - increase memory_allocated * @sk: socket * @size: memory size to allocate * @amt: pages to allocate * @kind: allocation type * * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc. * * Unlike the globally shared limits among the sockets under same protocol, * consuming the budget of a memcg won't have direct effect on other ones. * So be optimistic about memcg's tolerance, and leave the callers to decide * whether or not to raise allocated through sk_under_memory_pressure() or * its variants. */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct mem_cgroup *memcg = mem_cgroup_sockets_enabled ? sk->sk_memcg : NULL; struct proto *prot = sk->sk_prot; bool charged = false; long allocated; sk_memory_allocated_add(sk, amt); allocated = sk_memory_allocated(sk); if (memcg) { if (!mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge())) goto suppress_allocation; charged = true; } /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } /* Under pressure. */ if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); /* Over hard limit. */ if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* Guarantee minimum buffer size under pressure (either global * or memcg) to make sure features described in RFC 7323 (TCP * Extensions for High Performance) work properly. * * This rule does NOT stand when exceeds global or memcg's hard * limit, or else a DoS attack can be taken place by spawning * lots of sockets whose usage are under minimum buffer size. */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; } else { /* SK_MEM_SEND */ int wmem0 = sk_get_wmem0(sk, prot); if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < wmem0) return 1; } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) { return 1; } } if (sk_has_memory_pressure(sk)) { u64 alloc; /* The following 'average' heuristic is within the * scope of global accounting, so it only makes * sense for global memory pressure. */ if (!sk_under_global_memory_pressure(sk)) return 1; /* Try to be fair among all the sockets under global * pressure by allowing the ones that below average * usage to raise. */ alloc = sk_sockets_allocated_read_positive(sk); if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) return 1; } suppress_allocation: if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) { sk_stream_moderate_sndbuf(sk); /* Fail only if socket is _under_ its sndbuf. * In this case we cannot block, so that we have to fail. */ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { /* Force charge with __GFP_NOFAIL */ if (memcg && !charged) { mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge() | __GFP_NOFAIL); } return 1; } } if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) trace_sock_exceed_buf_limit(sk, prot, allocated, kind); sk_memory_allocated_sub(sk, amt); if (charged) mem_cgroup_uncharge_skmem(memcg, amt); return 0; } /** * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated * @sk: socket * @size: memory size to allocate * @kind: allocation type * * If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means * rmem allocation. This function assumes that protocols which have * memory_pressure use sk_wmem_queued as write buffer accounting. */ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); sk_forward_alloc_add(sk, amt << PAGE_SHIFT); ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) sk_forward_alloc_add(sk, -(amt << PAGE_SHIFT)); return ret; } EXPORT_SYMBOL(__sk_mem_schedule); /** * __sk_mem_reduce_allocated - reclaim memory_allocated * @sk: socket * @amount: number of quanta * * Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc */ void __sk_mem_reduce_allocated(struct sock *sk, int amount) { sk_memory_allocated_sub(sk, amount); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket * @amount: number of bytes (rounded down to a PAGE_SIZE multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { amount >>= PAGE_SHIFT; sk_forward_alloc_add(sk, -(amount << PAGE_SHIFT)); __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); /* * Set of default routines for initialising struct proto_ops when * the protocol does not support a particular function. In certain * cases where it makes no sense for a protocol to have a "do nothing" * function, some default processing is provided. */ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int peer) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_getname); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_shutdown); int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg_locked); int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } EXPORT_SYMBOL(sock_no_mmap); /* * When a file is received (via SCM_RIGHTS, etc), we must bump the * various sock-based usage counts. */ void __receive_sock(struct file *file) { struct socket *sock; sock = sock_from_file(file); if (sock) { sock_update_netprioidx(&sock->sk->sk_cgrp_data); sock_update_classid(&sock->sk->sk_cgrp_data); } } /* * Default Socket Callbacks */ static void sock_def_wakeup(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLERR); sk_wake_async_rcu(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } void sock_def_readable(struct sock *sk) { struct socket_wq *wq; trace_sk_data_ready(sk); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if (sock_writeable(sk)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } /* An optimised version of sock_def_write_space(), should only be called * for SOCK_RCU_FREE sockets under RCU read section and after putting * ->sk_wmem_alloc. */ static void sock_def_write_space_wfree(struct sock *sk) { /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if (sock_writeable(sk)) { struct socket_wq *wq = rcu_dereference(sk->sk_wq); /* rely on refcount_sub from sock_wfree() */ smp_mb__after_atomic(); if (wq && waitqueue_active(&wq->wait)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } } static void sock_def_destruct(struct sock *sk) { } void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) if (send_sigurg(sk->sk_socket->file)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) { if (!mod_timer(timer, expires)) sock_hold(sk); } EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { if (timer_delete(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) { if (timer_delete_sync(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer_sync); void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk->sk_use_task_frag = true; sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); if (sock) { sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); } sk->sk_uid = uid; sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; spin_lock_init(&sk->sk_peer_lock); sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; #if BITS_PER_LONG==32 seqlock_init(&sk->sk_stamp_seq); #endif atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data_uid); void sock_init_data(struct socket *sock, struct sock *sk) { kuid_t uid = sock ? SOCK_INODE(sock)->i_uid : make_kuid(sock_net(sk)->user_ns, 0); sock_init_data_uid(sock, sk, uid); } EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { /* The sk_lock has mutex_lock() semantics here. */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (sock_owned_by_user_nocheck(sk)) __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); if (sk->sk_prot->release_cb) INDIRECT_CALL_INET_1(sk->sk_prot->release_cb, tcp_release_cb, sk); sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (!sock_owned_by_user_nocheck(sk)) { /* * Fast path return with bottom halves disabled and * sock::sk_lock.slock held. * * The 'mutex' is not contended and holding * sock::sk_lock.slock prevents all other lockers to * proceed so the corresponding unlock_sock_fast() can * avoid the slow path of release_sock() completely and * just release slock. * * From a semantical POV this is equivalent to 'acquiring' * the 'mutex', hence the corresponding lockdep * mutex_release() has to happen in the fast path of * unlock_sock_fast(). */ return false; } __lock_sock(sk); sk->sk_lock.owned = 1; __acquire(&sk->sk_lock.slock); spin_unlock_bh(&sk->sk_lock.slock); return true; } EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) { struct sock *sk = sock->sk; struct timespec64 ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec64(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return -ENOENT; if (ts.tv_sec == 0) { ktime_t kt = ktime_get_real(); sock_write_timestamp(sk, kt); ts = ktime_to_timespec64(kt); } if (timeval) ts.tv_nsec /= 1000; #ifdef CONFIG_COMPAT_32BIT_TIME if (time32) return put_old_timespec32(&ts, userstamp); #endif #ifdef CONFIG_SPARC64 /* beware of padding in sparc64 timeval */ if (timeval && !in_compat_syscall()) { struct __kernel_old_timeval __user tv = { .tv_sec = ts.tv_sec, .tv_usec = ts.tv_nsec, }; if (copy_to_user(userstamp, &tv, sizeof(tv))) return -EFAULT; return 0; } #endif return put_timespec64(&ts, userstamp); } EXPORT_SYMBOL(sock_gettstamp); void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) { if (!sock_flag(sk, flag)) { unsigned long previous_flags = sk->sk_flags; sock_set_flag(sk, flag); /* * we just set one of the two flags which require net * time stamping, but time stamping might have been on * already because of the other one */ if (sock_needs_netstamp(sk) && !(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type) { struct sock_exterr_skb *serr; struct sk_buff *skb; int copied, err; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); msg->msg_flags |= MSG_ERRQUEUE; err = copied; out_free_skb: kfree_skb(skb); out: return err; } EXPORT_SYMBOL(sock_recv_errqueue); /* * Get a socket option on an socket. * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume * this means if you specify SO_ERROR (otherwise what is the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_getsockopt); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; err = sk->sk_prot->recvmsg(sk, msg, size, flags, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(sock_common_recvmsg); /* * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_setsockopt); void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) sk->sk_prot->destroy(sk); /* * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * * A. Remove from hash tables. */ sk->sk_prot->unhash(sk); /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and * did hash table lookup before we unhashed socket. They will achieve * receive queue and will be purged by socket destructor. * * Also we still have packets pending on receive queue and probably, * our own packets waiting in device queues. sock_destroy will drain * receive queue, but transmitted packets will delay socket destruction * until the last reference will be released. */ sock_orphan(sk); xfrm_sk_free_policy(sk); sock_put(sk); } EXPORT_SYMBOL(sk_common_release); void sk_get_meminfo(const struct sock *sk, u32 *mem) { memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = READ_ONCE(sk->sk_forward_alloc); mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } #ifdef CONFIG_PROC_FS static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); int sock_prot_inuse_get(struct net *net, struct proto *prot) { int cpu, idx = prot->inuse_idx; int res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx]; return res >= 0 ? res : 0; } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); int sock_inuse_get(struct net *net) { int cpu, res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->all; return res; } EXPORT_SYMBOL_GPL(sock_inuse_get); static int __net_init sock_inuse_init_net(struct net *net) { net->core.prot_inuse = alloc_percpu(struct prot_inuse); if (net->core.prot_inuse == NULL) return -ENOMEM; return 0; } static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.prot_inuse); } static struct pernet_operations net_inuse_ops = { .init = sock_inuse_init_net, .exit = sock_inuse_exit_net, }; static __init int net_inuse_init(void) { if (register_pernet_subsys(&net_inuse_ops)) panic("Cannot initialize net inuse counters"); return 0; } core_initcall(net_inuse_init); static int assign_proto_idx(struct proto *prot) { prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { pr_err("PROTO_INUSE_NR exhausted\n"); return -ENOSPC; } set_bit(prot->inuse_idx, proto_inuse_idx); return 0; } static void release_proto_idx(struct proto *prot) { if (prot->inuse_idx != PROTO_INUSE_NR - 1) clear_bit(prot->inuse_idx, proto_inuse_idx); } #else static inline int assign_proto_idx(struct proto *prot) { return 0; } static inline void release_proto_idx(struct proto *prot) { } #endif static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) { if (!twsk_prot) return; kfree(twsk_prot->twsk_slab_name); twsk_prot->twsk_slab_name = NULL; kmem_cache_destroy(twsk_prot->twsk_slab); twsk_prot->twsk_slab = NULL; } static int tw_prot_init(const struct proto *prot) { struct timewait_sock_ops *twsk_prot = prot->twsk_prot; if (!twsk_prot) return 0; twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); if (!twsk_prot->twsk_slab_name) return -ENOMEM; twsk_prot->twsk_slab = kmem_cache_create(twsk_prot->twsk_slab_name, twsk_prot->twsk_obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!twsk_prot->twsk_slab) { pr_crit("%s: Can't create timewait sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) return; kfree(rsk_prot->slab_name); rsk_prot->slab_name = NULL; kmem_cache_destroy(rsk_prot->slab); rsk_prot->slab = NULL; } static int req_prot_init(const struct proto *prot) { struct request_sock_ops *rsk_prot = prot->rsk_prot; if (!rsk_prot) return 0; rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); if (!rsk_prot->slab_name) return -ENOMEM; rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } int proto_register(struct proto *prot, int alloc_slab) { int ret = -ENOBUFS; if (prot->memory_allocated && !prot->sysctl_mem) { pr_err("%s: missing sysctl_mem\n", prot->name); return -EINVAL; } if (prot->memory_allocated && !prot->per_cpu_fw_alloc) { pr_err("%s: missing per_cpu_fw_alloc\n", prot->name); return -EINVAL; } if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | prot->slab_flags, prot->useroffset, prot->usersize, NULL); if (prot->slab == NULL) { pr_crit("%s: Can't create sock SLAB cache!\n", prot->name); goto out; } if (req_prot_init(prot)) goto out_free_request_sock_slab; if (tw_prot_init(prot)) goto out_free_timewait_sock_slab; } mutex_lock(&proto_list_mutex); ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; out_free_timewait_sock_slab: if (alloc_slab) tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); kmem_cache_destroy(prot->slab); prot->slab = NULL; } out: return ret; } EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { mutex_lock(&proto_list_mutex); release_proto_idx(prot); list_del(&prot->node); mutex_unlock(&proto_list_mutex); kmem_cache_destroy(prot->slab); prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); int sock_load_diag_module(int family, int protocol) { if (!protocol) { if (!sock_is_registered(family)) return -ENOENT; return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family); } #ifdef CONFIG_INET if (family == AF_INET && protocol != IPPROTO_RAW && protocol < MAX_INET_PROTOS && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family, protocol); } EXPORT_SYMBOL(sock_load_diag_module); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) { mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &proto_list, pos); } static void proto_seq_stop(struct seq_file *seq, void *v) __releases(proto_list_mutex) { mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } static long sock_prot_memory_allocated(struct proto *proto) { return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; } static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), sock_prot_memory_allocated(proto), sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), proto_method_implemented(proto->close), proto_method_implemented(proto->connect), proto_method_implemented(proto->disconnect), proto_method_implemented(proto->accept), proto_method_implemented(proto->ioctl), proto_method_implemented(proto->init), proto_method_implemented(proto->destroy), proto_method_implemented(proto->shutdown), proto_method_implemented(proto->setsockopt), proto_method_implemented(proto->getsockopt), proto_method_implemented(proto->sendmsg), proto_method_implemented(proto->recvmsg), proto_method_implemented(proto->bind), proto_method_implemented(proto->backlog_rcv), proto_method_implemented(proto->hash), proto_method_implemented(proto->unhash), proto_method_implemented(proto->get_port), proto_method_implemented(proto->enter_memory_pressure)); } static int proto_seq_show(struct seq_file *seq, void *v) { if (v == &proto_list) seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s", "protocol", "size", "sockets", "memory", "press", "maxhdr", "slab", "module", "cl co di ac io in de sh ss gs se re bi br ha uh gp em\n"); else proto_seq_printf(seq, list_entry(v, struct proto, node)); return 0; } static const struct seq_operations proto_seq_ops = { .start = proto_seq_start, .next = proto_seq_next, .stop = proto_seq_stop, .show = proto_seq_show, }; static __net_init int proto_init_net(struct net *net) { if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static __net_exit void proto_exit_net(struct net *net) { remove_proc_entry("protocols", net->proc_net); } static __net_initdata struct pernet_operations proto_net_ops = { .init = proto_init_net, .exit = proto_exit_net, }; static int __init proto_init(void) { return register_pernet_subsys(&proto_net_ops); } subsys_initcall(proto_init); #endif /* PROC_FS */ #ifdef CONFIG_NET_RX_BUSY_POLL bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) return true; if (sk_is_udp(sk) && !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) return true; return sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len) { if (!sk->sk_prot->bind_add) return -EOPNOTSUPP; return sk->sk_prot->bind_add(sk, addr, addr_len); } EXPORT_SYMBOL(sock_bind_add); /* Copy 'size' bytes from userspace and return `size` back to userspace */ int sock_ioctl_inout(struct sock *sk, unsigned int cmd, void __user *arg, void *karg, size_t size) { int ret; if (copy_from_user(karg, arg, size)) return -EFAULT; ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, karg); if (ret) return ret; if (copy_to_user(arg, karg, size)) return -EFAULT; return 0; } EXPORT_SYMBOL(sock_ioctl_inout); /* This is the most common ioctl prep function, where the result (4 bytes) is * copied back to userspace if the ioctl() returns successfully. No input is * copied from userspace as input argument. */ static int sock_ioctl_out(struct sock *sk, unsigned int cmd, void __user *arg) { int ret, karg = 0; ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, &karg); if (ret) return ret; return put_user(karg, (int __user *)arg); } /* A wrapper around sock ioctls, which copies the data from userspace * (depending on the protocol/ioctl), and copies back the result to userspace. * The main motivation for this function is to pass kernel memory to the * protocol ioctl callbacks, instead of userspace memory. */ int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { int rc = 1; if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET) rc = ipmr_sk_ioctl(sk, cmd, arg); else if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET6) rc = ip6mr_sk_ioctl(sk, cmd, arg); else if (sk_is_phonet(sk)) rc = phonet_sk_ioctl(sk, cmd, arg); /* If ioctl was processed, returns its value */ if (rc <= 0) return rc; /* Otherwise call the default handler */ return sock_ioctl_out(sk, cmd, arg); } EXPORT_SYMBOL(sk_ioctl); static int __init sock_struct_check(void) { CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_drops); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_peek_off); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_error_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_receive_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_backlog); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_ifindex); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_cookie); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvbuf); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_filter); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_wq); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_data_ready); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvlowat); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_err); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_socket); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_memcg); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_lock); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_reserved_mem); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_forward_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_tsflags); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_sndbuf); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_queued); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tsq_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_dst_pending_confirm); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_status); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_mark); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_route_caps); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_type); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_allocation); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_txhash); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_shift); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_use_task_frag); return 0; } core_initcall(sock_struct_check); |
| 96 91 7 94 4 93 5 78 21 47 29 16 2 7 2 9 1 1 1 1 1 4 16 1 17 17 28 27 4 4 7 6 16 151 67 107 110 53 29 9 25 4 4 28 3 8 12 2 2 23 4 11 3 1 1 2 5 5 3 7 3 17 15 6 3 10 11 4 4 9 25 23 124 111 3 117 86 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 | // SPDX-License-Identifier: GPL-2.0 /* * 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. * * The options processing module for ip.c * * Authors: A.N.Kuznetsov * */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/uaccess.h> #include <linux/unaligned.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/cipso_ipv4.h> #include <net/ip_fib.h> /* * Write options to IP header, record destination address to * source route option, address of outgoing interface * (we should already know it, so that this function is allowed be * called only after routing decision) and timestamp, * if we originate this datagram. * * daddr is real destination address, next hop is recorded in IP header. * saddr is address of outgoing interface. */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt) { unsigned char *iph = skb_network_header(skb); memcpy(&(IPCB(skb)->opt), opt, sizeof(struct ip_options)); memcpy(iph + sizeof(struct iphdr), opt->__data, opt->optlen); opt = &(IPCB(skb)->opt); if (opt->srr) memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4); if (opt->rr_needaddr) ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); if (opt->ts_needaddr) ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); if (opt->ts_needtime) { __be32 midtime; midtime = inet_current_timestamp(); memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); } } /* * Provided (sopt, skb) points to received options, * build in dopt compiled option set appropriate for answering. * i.e. invert SRR option, copy anothers, * and grab room in RR/TS options. * * NOTE: dopt cannot point to skb. */ int __ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb, const struct ip_options *sopt) { unsigned char *sptr, *dptr; int soffset, doffset; int optlen; memset(dopt, 0, sizeof(struct ip_options)); if (sopt->optlen == 0) return 0; sptr = skb_network_header(skb); dptr = dopt->__data; if (sopt->rr) { optlen = sptr[sopt->rr+1]; soffset = sptr[sopt->rr+2]; dopt->rr = dopt->optlen + sizeof(struct iphdr); memcpy(dptr, sptr+sopt->rr, optlen); if (sopt->rr_needaddr && soffset <= optlen) { if (soffset + 3 > optlen) return -EINVAL; dptr[2] = soffset + 4; dopt->rr_needaddr = 1; } dptr += optlen; dopt->optlen += optlen; } if (sopt->ts) { optlen = sptr[sopt->ts+1]; soffset = sptr[sopt->ts+2]; dopt->ts = dopt->optlen + sizeof(struct iphdr); memcpy(dptr, sptr+sopt->ts, optlen); if (soffset <= optlen) { if (sopt->ts_needaddr) { if (soffset + 3 > optlen) return -EINVAL; dopt->ts_needaddr = 1; soffset += 4; } if (sopt->ts_needtime) { if (soffset + 3 > optlen) return -EINVAL; if ((dptr[3]&0xF) != IPOPT_TS_PRESPEC) { dopt->ts_needtime = 1; soffset += 4; } else { dopt->ts_needtime = 0; if (soffset + 7 <= optlen) { __be32 addr; memcpy(&addr, dptr+soffset-1, 4); if (inet_addr_type(net, addr) != RTN_UNICAST) { dopt->ts_needtime = 1; soffset += 8; } } } } dptr[2] = soffset; } dptr += optlen; dopt->optlen += optlen; } if (sopt->srr) { unsigned char *start = sptr+sopt->srr; __be32 faddr; optlen = start[1]; soffset = start[2]; doffset = 0; if (soffset > optlen) soffset = optlen + 1; soffset -= 4; if (soffset > 3) { memcpy(&faddr, &start[soffset-1], 4); for (soffset -= 4, doffset = 4; soffset > 3; soffset -= 4, doffset += 4) memcpy(&dptr[doffset-1], &start[soffset-1], 4); /* * RFC1812 requires to fix illegal source routes. */ if (memcmp(&ip_hdr(skb)->saddr, &start[soffset + 3], 4) == 0) doffset -= 4; } if (doffset > 3) { dopt->faddr = faddr; dptr[0] = start[0]; dptr[1] = doffset+3; dptr[2] = 4; dptr += doffset+3; dopt->srr = dopt->optlen + sizeof(struct iphdr); dopt->optlen += doffset+3; dopt->is_strictroute = sopt->is_strictroute; } } if (sopt->cipso) { optlen = sptr[sopt->cipso+1]; dopt->cipso = dopt->optlen+sizeof(struct iphdr); memcpy(dptr, sptr+sopt->cipso, optlen); dptr += optlen; dopt->optlen += optlen; } while (dopt->optlen & 3) { *dptr++ = IPOPT_END; dopt->optlen++; } return 0; } /* * Options "fragmenting", just fill options not * allowed in fragments with NOOPs. * Simple and stupid 8), but the most efficient way. */ void ip_options_fragment(struct sk_buff *skb) { unsigned char *optptr = skb_network_header(skb) + sizeof(struct iphdr); struct ip_options *opt = &(IPCB(skb)->opt); int l = opt->optlen; int optlen; while (l > 0) { switch (*optptr) { case IPOPT_END: return; case IPOPT_NOOP: l--; optptr++; continue; } optlen = optptr[1]; if (optlen < 2 || optlen > l) return; if (!IPOPT_COPIED(*optptr)) memset(optptr, IPOPT_NOOP, optlen); l -= optlen; optptr += optlen; } opt->ts = 0; opt->rr = 0; opt->rr_needaddr = 0; opt->ts_needaddr = 0; opt->ts_needtime = 0; } /* helper used by ip_options_compile() to call fib_compute_spec_dst() * at most one time. */ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb) { if (*spec_dst == htonl(INADDR_ANY)) *spec_dst = fib_compute_spec_dst(skb); } /* * Verify options and fill pointers in struct options. * Caller should clear *opt, and set opt->data. * If opt == NULL, then skb->data should point to IP header. */ int __ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb, __be32 *info) { __be32 spec_dst = htonl(INADDR_ANY); unsigned char *pp_ptr = NULL; struct rtable *rt = NULL; unsigned char *optptr; unsigned char *iph; int optlen, l; if (skb) { rt = skb_rtable(skb); optptr = (unsigned char *)&(ip_hdr(skb)[1]); } else optptr = opt->__data; iph = optptr - sizeof(struct iphdr); for (l = opt->optlen; l > 0; ) { switch (*optptr) { case IPOPT_END: for (optptr++, l--; l > 0; optptr++, l--) { if (*optptr != IPOPT_END) { *optptr = IPOPT_END; opt->is_changed = 1; } } goto eol; case IPOPT_NOOP: l--; optptr++; continue; } if (unlikely(l < 2)) { pp_ptr = optptr; goto error; } optlen = optptr[1]; if (optlen < 2 || optlen > l) { pp_ptr = optptr; goto error; } switch (*optptr) { case IPOPT_SSRR: case IPOPT_LSRR: if (optlen < 3) { pp_ptr = optptr + 1; goto error; } if (optptr[2] < 4) { pp_ptr = optptr + 2; goto error; } /* NB: cf RFC-1812 5.2.4.1 */ if (opt->srr) { pp_ptr = optptr; goto error; } if (!skb) { if (optptr[2] != 4 || optlen < 7 || ((optlen-3) & 3)) { pp_ptr = optptr + 1; goto error; } memcpy(&opt->faddr, &optptr[3], 4); if (optlen > 7) memmove(&optptr[3], &optptr[7], optlen-7); } opt->is_strictroute = (optptr[0] == IPOPT_SSRR); opt->srr = optptr - iph; break; case IPOPT_RR: if (opt->rr) { pp_ptr = optptr; goto error; } if (optlen < 3) { pp_ptr = optptr + 1; goto error; } if (optptr[2] < 4) { pp_ptr = optptr + 2; goto error; } if (optptr[2] <= optlen) { if (optptr[2]+3 > optlen) { pp_ptr = optptr + 2; goto error; } if (rt) { spec_dst_fill(&spec_dst, skb); memcpy(&optptr[optptr[2]-1], &spec_dst, 4); opt->is_changed = 1; } optptr[2] += 4; opt->rr_needaddr = 1; } opt->rr = optptr - iph; break; case IPOPT_TIMESTAMP: if (opt->ts) { pp_ptr = optptr; goto error; } if (optlen < 4) { pp_ptr = optptr + 1; goto error; } if (optptr[2] < 5) { pp_ptr = optptr + 2; goto error; } if (optptr[2] <= optlen) { unsigned char *timeptr = NULL; if (optptr[2]+3 > optlen) { pp_ptr = optptr + 2; goto error; } switch (optptr[3]&0xF) { case IPOPT_TS_TSONLY: if (skb) timeptr = &optptr[optptr[2]-1]; opt->ts_needtime = 1; optptr[2] += 4; break; case IPOPT_TS_TSANDADDR: if (optptr[2]+7 > optlen) { pp_ptr = optptr + 2; goto error; } if (rt) { spec_dst_fill(&spec_dst, skb); memcpy(&optptr[optptr[2]-1], &spec_dst, 4); timeptr = &optptr[optptr[2]+3]; } opt->ts_needaddr = 1; opt->ts_needtime = 1; optptr[2] += 8; break; case IPOPT_TS_PRESPEC: if (optptr[2]+7 > optlen) { pp_ptr = optptr + 2; goto error; } { __be32 addr; memcpy(&addr, &optptr[optptr[2]-1], 4); if (inet_addr_type(net, addr) == RTN_UNICAST) break; if (skb) timeptr = &optptr[optptr[2]+3]; } opt->ts_needtime = 1; optptr[2] += 8; break; default: if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr + 3; goto error; } break; } if (timeptr) { __be32 midtime; midtime = inet_current_timestamp(); memcpy(timeptr, &midtime, 4); opt->is_changed = 1; } } else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) { unsigned int overflow = optptr[3]>>4; if (overflow == 15) { pp_ptr = optptr + 3; goto error; } if (skb) { optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4); opt->is_changed = 1; } } opt->ts = optptr - iph; break; case IPOPT_RA: if (optlen < 4) { pp_ptr = optptr + 1; goto error; } if (optptr[2] == 0 && optptr[3] == 0) opt->router_alert = optptr - iph; break; case IPOPT_CIPSO: if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) { pp_ptr = optptr; goto error; } opt->cipso = optptr - iph; if (cipso_v4_validate(skb, &optptr)) { pp_ptr = optptr; goto error; } break; case IPOPT_SEC: case IPOPT_SID: default: if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr; goto error; } break; } l -= optlen; optptr += optlen; } eol: if (!pp_ptr) return 0; error: if (info) *info = htonl((pp_ptr-iph)<<24); return -EINVAL; } EXPORT_SYMBOL(__ip_options_compile); int ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb) { int ret; __be32 info; ret = __ip_options_compile(net, opt, skb, &info); if (ret != 0 && skb) icmp_send(skb, ICMP_PARAMETERPROB, 0, info); return ret; } EXPORT_SYMBOL(ip_options_compile); /* * Undo all the changes done by ip_options_compile(). */ void ip_options_undo(struct ip_options *opt) { if (opt->srr) { unsigned char *optptr = opt->__data + opt->srr - sizeof(struct iphdr); memmove(optptr + 7, optptr + 3, optptr[1] - 7); memcpy(optptr + 3, &opt->faddr, 4); } if (opt->rr_needaddr) { unsigned char *optptr = opt->__data + opt->rr - sizeof(struct iphdr); optptr[2] -= 4; memset(&optptr[optptr[2] - 1], 0, 4); } if (opt->ts) { unsigned char *optptr = opt->__data + opt->ts - sizeof(struct iphdr); if (opt->ts_needtime) { optptr[2] -= 4; memset(&optptr[optptr[2] - 1], 0, 4); if ((optptr[3] & 0xF) == IPOPT_TS_PRESPEC) optptr[2] -= 4; } if (opt->ts_needaddr) { optptr[2] -= 4; memset(&optptr[optptr[2] - 1], 0, 4); } } } int ip_options_get(struct net *net, struct ip_options_rcu **optp, sockptr_t data, int optlen) { struct ip_options_rcu *opt; opt = kzalloc(sizeof(struct ip_options_rcu) + ((optlen + 3) & ~3), GFP_KERNEL); if (!opt) return -ENOMEM; if (optlen && copy_from_sockptr(opt->opt.__data, data, optlen)) { kfree(opt); return -EFAULT; } while (optlen & 3) opt->opt.__data[optlen++] = IPOPT_END; opt->opt.optlen = optlen; if (optlen && ip_options_compile(net, &opt->opt, NULL)) { kfree(opt); return -EINVAL; } kfree(*optp); *optp = opt; return 0; } void ip_forward_options(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); unsigned char *optptr; struct rtable *rt = skb_rtable(skb); unsigned char *raw = skb_network_header(skb); if (opt->rr_needaddr) { optptr = (unsigned char *)raw + opt->rr; ip_rt_get_source(&optptr[optptr[2]-5], skb, rt); opt->is_changed = 1; } if (opt->srr_is_hit) { int srrptr, srrspace; optptr = raw + opt->srr; for ( srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4 ) { if (srrptr + 3 > srrspace) break; if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_hdr(skb)->daddr = opt->nexthop; ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; } else { net_crit_ratelimited("%s(): Argh! Destination lost!\n", __func__); } if (opt->ts_needaddr) { optptr = raw + opt->ts; ip_rt_get_source(&optptr[optptr[2]-9], skb, rt); opt->is_changed = 1; } } if (opt->is_changed) { opt->is_changed = 0; ip_send_check(ip_hdr(skb)); } } int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt = &(IPCB(skb)->opt); int srrspace, srrptr; __be32 nexthop; struct iphdr *iph = ip_hdr(skb); unsigned char *optptr = skb_network_header(skb) + opt->srr; struct rtable *rt = skb_rtable(skb); struct rtable *rt2; unsigned long orefdst; int err; if (!rt) return 0; if (skb->pkt_type != PACKET_HOST) return -EINVAL; if (rt->rt_type == RTN_UNICAST) { if (!opt->is_strictroute) return 0; icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl(16<<24)); return -EINVAL; } if (rt->rt_type != RTN_LOCAL) return -EINVAL; for (srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) { if (srrptr + 3 > srrspace) { icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((opt->srr+2)<<24)); return -EINVAL; } memcpy(&nexthop, &optptr[srrptr-1], 4); orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); err = ip_route_input(skb, nexthop, iph->saddr, ip4h_dscp(iph), dev) ? -EINVAL : 0; rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb); skb->_skb_refdst = orefdst; return -EINVAL; } refdst_drop(orefdst); if (rt2->rt_type != RTN_LOCAL) break; /* Superfast 8) loopback forward */ iph->daddr = nexthop; opt->is_changed = 1; } if (srrptr <= srrspace) { opt->srr_is_hit = 1; opt->nexthop = nexthop; opt->is_changed = 1; } return 0; } EXPORT_SYMBOL(ip_options_rcv_srr); |
| 22 22 208 208 259 156 156 150 156 155 156 156 156 156 232 232 208 208 208 207 3 205 228 231 10 10 230 31 232 228 229 230 23 13 13 229 26 229 232 229 228 229 229 13 33 34 34 231 30 32 32 30 31 28 22 22 27 27 232 229 34 35 34 35 232 232 231 232 26 26 26 26 26 26 17 26 26 26 26 26 26 26 26 26 2 20 7 26 26 26 26 26 26 26 17 17 26 26 26 17 9 17 17 9 17 17 26 26 26 17 26 26 26 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 Intel Corp. * * This file is part of the SCTP kernel implementation * * These functions implement the sctp_outq class. The outqueue handles * bundling and queueing of outgoing SCTP chunks. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Perry Melange <pmelange@null.cc.uic.edu> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Jon Grimm <jgrimm@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/list.h> /* For struct list_head */ #include <linux/socket.h> #include <linux/ip.h> #include <linux/slab.h> #include <net/sock.h> /* For skb_set_owner_w */ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> #include <trace/events/sctp.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn); static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn, int count_of_newacks); static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add(&ch->stream_list, &oute->outq); } /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { return q->sched->dequeue(q); } /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add_tail(&ch->stream_list, &oute->outq); } /* * SFR-CACC algorithm: * D) If count_of_newacks is greater than or equal to 2 * and t was not sent to the current primary then the * sender MUST NOT increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks >= 2 && transport != primary) return 1; return 0; } /* * SFR-CACC algorithm: * F) If count_of_newacks is less than 2, let d be the * destination to which t was sent. If cacc_saw_newack * is 0 for destination d, then the sender MUST NOT * increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_f(struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks < 2 && (transport && !transport->cacc.cacc_saw_newack)) return 1; return 0; } /* * SFR-CACC algorithm: * 3.1) If CYCLING_CHANGEOVER is 0, the sender SHOULD * execute steps C, D, F. * * C has been implemented in sctp_outq_sack */ static inline int sctp_cacc_skip_3_1(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (!primary->cacc.cycling_changeover) { if (sctp_cacc_skip_3_1_d(primary, transport, count_of_newacks)) return 1; if (sctp_cacc_skip_3_1_f(transport, count_of_newacks)) return 1; return 0; } return 0; } /* * SFR-CACC algorithm: * 3.2) Else if CYCLING_CHANGEOVER is 1, and t is less * than next_tsn_at_change of the current primary, then * the sender MUST NOT increment missing report count * for t. */ static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn) { if (primary->cacc.cycling_changeover && TSN_lt(tsn, primary->cacc.next_tsn_at_change)) return 1; return 0; } /* * SFR-CACC algorithm: * 3) If the missing report count for TSN t is to be * incremented according to [RFC2960] and * [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set, * then the sender MUST further execute steps 3.1 and * 3.2 to determine if the missing report count for * TSN t SHOULD NOT be incremented. * * 3.3) If 3.1 and 3.2 do not dictate that the missing * report count for t should not be incremented, then * the sender SHOULD increment missing report count for * t (according to [RFC2960] and [SCTP_STEWART_2002]). */ static inline int sctp_cacc_skip(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks, __u32 tsn) { if (primary->cacc.changeover_active && (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) || sctp_cacc_skip_3_2(primary, tsn))) return 1; return 0; } /* Initialize an existing sctp_outq. This does the boring stuff. * You still need to define handlers if you really want to DO * something with this structure... */ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) { memset(q, 0, sizeof(struct sctp_outq)); q->asoc = asoc; INIT_LIST_HEAD(&q->out_chunk_list); INIT_LIST_HEAD(&q->control_chunk_list); INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); sctp_sched_set_sched(asoc, sctp_sk(asoc->base.sk)->default_ss); } /* Free the outqueue structure and any related pending chunks. */ static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; struct sctp_chunk *chunk, *tmp; /* Throw away unacknowledged chunks. */ list_for_each_entry(transport, &q->asoc->peer.transport_addr_list, transports) { while ((lchunk = sctp_list_dequeue(&transport->transmitted)) != NULL) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* Mark as part of a failed message. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } } /* Throw away chunks that have been gap ACKed. */ list_for_each_safe(lchunk, temp, &q->sacked) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks in the retransmit queue. */ list_for_each_safe(lchunk, temp, &q->retransmit) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks that are in the abandoned queue. */ list_for_each_safe(lchunk, temp, &q->abandoned) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover data chunks. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { sctp_sched_dequeue_done(q, chunk); /* Mark as send failure. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); sctp_chunk_free(chunk); } } void sctp_outq_teardown(struct sctp_outq *q) { __sctp_outq_teardown(q); sctp_outq_init(q->asoc, q); } /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ __sctp_outq_teardown(q); } /* Put a new chunk in an sctp_outq. */ void sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) { struct net *net = q->asoc->base.net; pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); /* If it is data, queue it up, otherwise, send it * immediately. */ if (sctp_chunk_is_data(chunk)) { pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); sctp_outq_tail_data(q, chunk); if (chunk->asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) chunk->asoc->sent_cnt_removable++; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); else SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS); } else { list_add_tail(&chunk->list, &q->control_chunk_list); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); } if (!q->cork) sctp_outq_flush(q, 0, gfp); } /* Insert a chunk into the sorted list based on the TSNs. The retransmit list * and the abandoned list are in ascending order. */ static void sctp_insert_list(struct list_head *head, struct list_head *new) { struct list_head *pos; struct sctp_chunk *nchunk, *lchunk; __u32 ntsn, ltsn; int done = 0; nchunk = list_entry(new, struct sctp_chunk, transmitted_list); ntsn = ntohl(nchunk->subh.data_hdr->tsn); list_for_each(pos, head) { lchunk = list_entry(pos, struct sctp_chunk, transmitted_list); ltsn = ntohl(lchunk->subh.data_hdr->tsn); if (TSN_lt(ntsn, ltsn)) { list_add(new, pos->prev); done = 1; break; } } if (!done) list_add_tail(new, head); } static int sctp_prsctp_prune_sent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct list_head *queue, int msg_len) { struct sctp_chunk *chk, *temp; list_for_each_entry_safe(chk, temp, queue, transmitted_list) { struct sctp_stream_out *streamout; if (!chk->msg->abandoned && (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; list_del_init(&chk->transmitted_list); sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); streamout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; if (queue != &asoc->outqueue.retransmit && !chk->tsn_gap_acked) { if (chk->transport) chk->transport->flight_size -= sctp_data_size(chk); asoc->outqueue.outstanding_bytes -= sctp_data_size(chk); } msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); if (msg_len <= 0) break; } return msg_len; } static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; struct sctp_stream_out *sout; q->sched->unsched_all(&asoc->stream); list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!chk->msg->abandoned && (!(chk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) || !SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; sout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); sout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; /* clear out_curr if all frag chunks are pruned */ if (asoc->stream.out_curr == sout && list_is_last(&chk->frag_list, &chk->msg->chunks)) asoc->stream.out_curr = NULL; msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); sctp_chunk_free(chk); if (msg_len <= 0) break; } q->sched->sched_all(&asoc->stream); return msg_len; } /* Abandon the chunks according their priorities */ void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_transport *transport; if (!asoc->peer.prsctp_capable || !asoc->sent_cnt_removable) return; msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &asoc->outqueue.retransmit, msg_len); if (msg_len <= 0) return; list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &transport->transmitted, msg_len); if (msg_len <= 0) return; } sctp_prsctp_prune_unsent(asoc, sinfo, msg_len); } /* Mark all the eligible packets on a transport for retransmission. */ void sctp_retransmit_mark(struct sctp_outq *q, struct sctp_transport *transport, __u8 reason) { struct list_head *lchunk, *ltemp; struct sctp_chunk *chunk; /* Walk through the specified transmitted queue. */ list_for_each_safe(lchunk, ltemp, &transport->transmitted) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(lchunk); sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been previousely acked, * stop considering it 'outstanding'. Our peer * will most likely never see it since it will * not be retransmitted */ if (!chunk->tsn_gap_acked) { if (chunk->transport) chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } /* If we are doing retransmission due to a timeout or pmtu * discovery, only the chunks that are not yet acked should * be added to the retransmit queue. */ if ((reason == SCTP_RTXR_FAST_RTX && (chunk->fast_retransmit == SCTP_NEED_FRTX)) || (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for * retransmission (via either T3-rtx timer expiration * (Section 6.3.3) or via fast retransmit * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); /* sctpimpguide-05 Section 2.8.2 * M5) If a T3-rtx timer expires, the * 'TSN.Missing.Report' of all affected TSNs is set * to 0. */ chunk->tsn_missing_report = 0; /* If a chunk that is being used for RTT measurement * has to be retransmitted, we cannot use this chunk * anymore for RTT measurements. Reset rto_pending so * that a new RTT measurement is started when a new * data chunk is sent. */ if (chunk->rtt_in_progress) { chunk->rtt_in_progress = 0; transport->rto_pending = 0; } /* Move the chunk to the retransmit queue. The chunks * on the retransmit queue are always kept in order. */ list_del_init(lchunk); sctp_insert_list(&q->retransmit, lchunk); } } pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, reason, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } /* Mark all the eligible packets on a transport for retransmission and force * one packet out. */ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, enum sctp_retransmit_reason reason) { struct net *net = q->asoc->base.net; switch (reason) { case SCTP_RTXR_T3_RTX: SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX); /* Update the retran path if the T3-rtx timer has expired for * the current retran path. */ if (transport == transport->asoc->peer.retran_path) sctp_assoc_update_retran_path(transport->asoc); transport->asoc->rtx_data_chunks += transport->asoc->unack_data; if (transport->pl.state == SCTP_PL_COMPLETE && transport->asoc->unack_data) sctp_transport_reset_probe_timer(transport); break; case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(net, SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(net, SCTP_MIB_PMTUD_RETRANSMITS); break; case SCTP_RTXR_T1_RTX: SCTP_INC_STATS(net, SCTP_MIB_T1_RETRANSMITS); transport->asoc->init_retries++; break; default: BUG(); } sctp_retransmit_mark(q, transport, reason); /* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by * following the procedures outlined in C1 - C5. */ if (reason == SCTP_RTXR_T3_RTX) q->asoc->stream.si->generate_ftsn(q, q->asoc->ctsn_ack_point); /* Flush the queues only on timeout, since fast_rtx is only * triggered during sack processing and the queue * will be flushed at the end. */ if (reason != SCTP_RTXR_FAST_RTX) sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC); } /* * Transmit DATA chunks on the retransmit queue. Upon return from * __sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which * need to be transmitted by the caller. * We assume that pkt->transport has already been set. * * The return value is a normal kernel error return value. */ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int rtx_timeout, int *start_timer, gfp_t gfp) { struct sctp_transport *transport = pkt->transport; struct sctp_chunk *chunk, *chunk1; struct list_head *lqueue; enum sctp_xmit status; int error = 0; int timer = 0; int done = 0; int fast_rtx; lqueue = &q->retransmit; fast_rtx = q->fast_rtx; /* This loop handles time-out retransmissions, fast retransmissions, * and retransmissions due to opening of whindow. * * RFC 2960 6.3.3 Handle T3-rtx Expiration * * E3) Determine how many of the earliest (i.e., lowest TSN) * outstanding DATA chunks for the address for which the * T3-rtx has expired will fit into a single packet, subject * to the MTU constraint for the path corresponding to the * destination transport address to which the retransmission * is being sent (this may be different from the address for * which the timer expires [see Section 6.4]). Call this value * K. Bundle and retransmit those K DATA chunks in a single * packet to the destination endpoint. * * [Just to be painfully clear, if we are retransmitting * because a timeout just happened, we should send only ONE * packet of retransmitted data.] * * For fast retransmissions we also send only ONE packet. However, * if we are just flushing the queue due to open window, we'll * try to send as much as possible. */ list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) { /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(&chunk->transmitted_list); sctp_insert_list(&q->abandoned, &chunk->transmitted_list); continue; } /* Make sure that Gap Acked TSNs are not retransmitted. A * simple approach is just to move such TSNs out of the * way and into a 'transmitted' queue and skip to the * next chunk. */ if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); continue; } /* If we are doing fast retransmit, ignore non-fast_rtransmit * chunks */ if (fast_rtx && !chunk->fast_retransmit) continue; redo: /* Attempt to append this chunk to the packet. */ status = sctp_packet_append_chunk(pkt, chunk); switch (status) { case SCTP_XMIT_PMTU_FULL: if (!pkt->has_data && !pkt->has_cookie_echo) { /* If this packet did not contain DATA then * retransmission did not happen, so do it * again. We'll ignore the error here since * control chunks are already freed so there * is nothing we can do. */ sctp_packet_transmit(pkt, gfp); goto redo; } /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* If we are retransmitting, we should only * send a single packet. * Otherwise, try appending this chunk again. */ if (rtx_timeout || fast_rtx) done = 1; else goto redo; /* Bundle next chunk in the next round. */ break; case SCTP_XMIT_RWND_FULL: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA as there is no more room * at the receiver. */ done = 1; break; case SCTP_XMIT_DELAY: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA because of nagle delay. */ done = 1; break; default: /* The append was successful, so add this chunk to * the transmitted list. */ list_move_tail(&chunk->transmitted_list, &transport->transmitted); /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. */ if (chunk->fast_retransmit == SCTP_NEED_FRTX) chunk->fast_retransmit = SCTP_DONT_FRTX; q->asoc->stats.rtxchunks++; break; } /* Set the timer if there were no errors */ if (!error && !timer) timer = 1; if (done) break; } /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. */ if (rtx_timeout || fast_rtx) { list_for_each_entry(chunk1, lqueue, transmitted_list) { if (chunk1->fast_retransmit == SCTP_NEED_FRTX) chunk1->fast_retransmit = SCTP_DONT_FRTX; } } *start_timer = timer; /* Clear fast retransmit hint */ if (fast_rtx) q->fast_rtx = 0; return error; } /* Cork the outqueue so queued chunks are really queued. */ void sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) { if (q->cork) q->cork = 0; sctp_outq_flush(q, 0, gfp); } static int sctp_packet_singleton(struct sctp_transport *transport, struct sctp_chunk *chunk, gfp_t gfp) { const struct sctp_association *asoc = transport->asoc; const __u16 sport = asoc->base.bind_addr.port; const __u16 dport = asoc->peer.port; const __u32 vtag = asoc->peer.i.init_tag; struct sctp_packet singleton; sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) { list_del_init(&chunk->list); sctp_chunk_free(chunk); return -ENOMEM; } return sctp_packet_transmit(&singleton, gfp); } /* Struct to hold the context during sctp outq flush */ struct sctp_flush_ctx { struct sctp_outq *q; /* Current transport being used. It's NOT the same as curr active one */ struct sctp_transport *transport; /* These transports have chunks to send. */ struct list_head transport_list; struct sctp_association *asoc; /* Packet on the current transport above */ struct sctp_packet *packet; gfp_t gfp; }; /* transport: current transport */ static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx, struct sctp_chunk *chunk) { struct sctp_transport *new_transport = chunk->transport; if (!new_transport) { if (!sctp_chunk_is_data(chunk)) { /* If we have a prior transport pointer, see if * the destination address of the chunk * matches the destination address of the * current transport. If not a match, then * try to look up the transport with a given * destination address. We do this because * after processing ASCONFs, we may have new * transports created. */ if (ctx->transport && sctp_cmp_addr_exact(&chunk->dest, &ctx->transport->ipaddr)) new_transport = ctx->transport; else new_transport = sctp_assoc_lookup_paddr(ctx->asoc, &chunk->dest); } /* if we still don't have a new transport, then * use the current active path. */ if (!new_transport) new_transport = ctx->asoc->peer.active_path; } else { __u8 type; switch (new_transport->state) { case SCTP_INACTIVE: case SCTP_UNCONFIRMED: case SCTP_PF: /* If the chunk is Heartbeat or Heartbeat Ack, * send it to chunk->transport, even if it's * inactive. * * 3.3.6 Heartbeat Acknowledgement: * ... * A HEARTBEAT ACK is always sent to the source IP * address of the IP datagram containing the * HEARTBEAT chunk to which this ack is responding. * ... * * ASCONF_ACKs also must be sent to the source. */ type = chunk->chunk_hdr->type; if (type != SCTP_CID_HEARTBEAT && type != SCTP_CID_HEARTBEAT_ACK && type != SCTP_CID_ASCONF_ACK) new_transport = ctx->asoc->peer.active_path; break; default: break; } } /* Are we switching transports? Take care of transport locks. */ if (new_transport != ctx->transport) { ctx->transport = new_transport; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); /* We've switched transports, so apply the * Burst limit to the new transport. */ sctp_transport_burst_limited(ctx->transport); } } static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) { struct sctp_chunk *chunk, *tmp; enum sctp_xmit status; int one_packet, error; list_for_each_entry_safe(chunk, tmp, &ctx->q->control_chunk_list, list) { one_packet = 0; /* RFC 5061, 5.3 * F1) This means that until such time as the ASCONF * containing the add is acknowledged, the sender MUST * NOT use the new IP address as a source for ANY SCTP * packet except on carrying an ASCONF Chunk. */ if (ctx->asoc->src_out_of_asoc_ok && chunk->chunk_hdr->type != SCTP_CID_ASCONF) continue; list_del_init(&chunk->list); /* Pick the right transport to use. Should always be true for * the first chunk as we don't have a transport by then. */ sctp_outq_select_transport(ctx, chunk); switch (chunk->chunk_hdr->type) { /* 6.10 Bundling * ... * An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN * COMPLETE with any other chunks. [Send them immediately.] */ case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: case SCTP_CID_SHUTDOWN_COMPLETE: error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (error < 0) { ctx->asoc->base.sk->sk_err = -error; return; } ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: if (sctp_test_T_bit(chunk)) ctx->packet->vtag = ctx->asoc->c.my_vtag; fallthrough; /* The following chunks are "response" chunks, i.e. * they are generated in response to something we * received. If we are sending these, then we can * send only 1 packet containing these chunks. */ case SCTP_CID_HEARTBEAT_ACK: case SCTP_CID_SHUTDOWN_ACK: case SCTP_CID_COOKIE_ACK: case SCTP_CID_COOKIE_ECHO: case SCTP_CID_ERROR: case SCTP_CID_ECN_CWR: case SCTP_CID_ASCONF_ACK: one_packet = 1; fallthrough; case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (!error) ctx->asoc->stats.octrlchunks++; break; } fallthrough; case SCTP_CID_SACK: case SCTP_CID_SHUTDOWN: case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: case SCTP_CID_RECONF: status = sctp_packet_transmit_chunk(ctx->packet, chunk, one_packet, ctx->gfp); if (status != SCTP_XMIT_OK) { /* put the chunk back */ list_add(&chunk->list, &ctx->q->control_chunk_list); break; } ctx->asoc->stats.octrlchunks++; /* PR-SCTP C5) If a FORWARD TSN is sent, the * sender MUST assure that at least one T3-rtx * timer is running. */ if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN || chunk->chunk_hdr->type == SCTP_CID_I_FWD_TSN) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } if (chunk == ctx->asoc->strreset_chunk) sctp_transport_reset_reconf_timer(ctx->transport); break; default: /* We built a chunk with an illegal type! */ BUG(); } } } /* Returns false if new data shouldn't be sent */ static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx, int rtx_timeout) { int error, start_timer = 0; if (ctx->asoc->peer.retran_path->state == SCTP_UNCONFIRMED) return false; if (ctx->transport != ctx->asoc->peer.retran_path) { /* Switch transports & prepare the packet. */ ctx->transport = ctx->asoc->peer.retran_path; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); } error = __sctp_outq_flush_rtx(ctx->q, ctx->packet, rtx_timeout, &start_timer, ctx->gfp); if (error < 0) ctx->asoc->base.sk->sk_err = -error; if (start_timer) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. */ if (ctx->packet->has_cookie_echo) return false; /* Don't send new data if there is still data * waiting to retransmit. */ if (!list_empty(&ctx->q->retransmit)) return false; return true; } static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, int rtx_timeout) { struct sctp_chunk *chunk; enum sctp_xmit status; /* Is it OK to send data chunks? */ switch (ctx->asoc->state) { case SCTP_STATE_COOKIE_ECHOED: /* Only allow bundling when this packet has a COOKIE-ECHO * chunk. */ if (!ctx->packet || !ctx->packet->has_cookie_echo) return; fallthrough; case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: break; default: /* Do nothing. */ return; } /* RFC 2960 6.1 Transmission of DATA Chunks * * C) When the time comes for the sender to transmit, * before sending new DATA chunks, the sender MUST * first transmit any outstanding DATA chunks which * are marked for retransmission (limited by the * current cwnd). */ if (!list_empty(&ctx->q->retransmit) && !sctp_outq_flush_rtx(ctx, rtx_timeout)) return; /* Apply Max.Burst limitation to the current transport in * case it will be used for new data. We are going to * rest it before we return, but we want to apply the limit * to the currently queued data. */ if (ctx->transport) sctp_transport_burst_limited(ctx->transport); /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); __u8 stream_state = SCTP_SO(&ctx->asoc->stream, sid)->state; /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { sctp_sched_dequeue_done(ctx->q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; } if (stream_state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(ctx->q, chunk); break; } sctp_outq_select_transport(ctx, chunk); pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p skb->users:%d\n", __func__, ctx->q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk", ntohl(chunk->subh.data_hdr->tsn), chunk->skb ? chunk->skb->head : NULL, chunk->skb ? refcount_read(&chunk->skb->users) : -1); /* Add the chunk to the packet. */ status = sctp_packet_transmit_chunk(ctx->packet, chunk, 0, ctx->gfp); if (status != SCTP_XMIT_OK) { /* We could not append this chunk, so put * the chunk back on the output queue. */ pr_debug("%s: could not transmit tsn:0x%x, status:%d\n", __func__, ntohl(chunk->subh.data_hdr->tsn), status); sctp_outq_head_data(ctx->q, chunk); break; } /* The sender is in the SHUTDOWN-PENDING state, * The sender MAY set the I-bit in the DATA * chunk header. */ if (ctx->asoc->state == SCTP_STATE_SHUTDOWN_PENDING) chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) ctx->asoc->stats.ouodchunks++; else ctx->asoc->stats.oodchunks++; /* Only now it's safe to consider this * chunk as sent, sched-wise. */ sctp_sched_dequeue_done(ctx->q, chunk); list_add_tail(&chunk->transmitted_list, &ctx->transport->transmitted); sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; /* Only let one DATA chunk get bundled with a * COOKIE-ECHO chunk. */ if (ctx->packet->has_cookie_echo) break; } } static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx) { struct sock *sk = ctx->asoc->base.sk; struct list_head *ltransport; struct sctp_packet *packet; struct sctp_transport *t; int error = 0; while ((ltransport = sctp_list_dequeue(&ctx->transport_list)) != NULL) { t = list_entry(ltransport, struct sctp_transport, send_ready); packet = &t->packet; if (!sctp_packet_empty(packet)) { rcu_read_lock(); if (t->dst && __sk_dst_get(sk) != t->dst) { dst_hold(t->dst); sk_setup_caps(sk, t->dst); } rcu_read_unlock(); error = sctp_packet_transmit(packet, ctx->gfp); if (error < 0) ctx->q->asoc->base.sk->sk_err = -error; } /* Clear the burst limited state, if any */ sctp_transport_burst_reset(t); } } /* Try to flush an outqueue. * * Description: Send everything in q which we legally can, subject to * congestion limitations. * * Note: This function can be called from multiple contexts so appropriate * locking concerns must be made. Today we use the sock lock to protect * this function. */ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) { struct sctp_flush_ctx ctx = { .q = q, .transport = NULL, .transport_list = LIST_HEAD_INIT(ctx.transport_list), .asoc = q->asoc, .packet = NULL, .gfp = gfp, }; /* 6.10 Bundling * ... * When bundling control chunks with DATA chunks, an * endpoint MUST place control chunks first in the outbound * SCTP packet. The transmitter MUST transmit DATA chunks * within a SCTP packet in increasing order of TSN. * ... */ sctp_outq_flush_ctrl(&ctx); if (q->asoc->src_out_of_asoc_ok) goto sctp_flush_out; sctp_outq_flush_data(&ctx, rtx_timeout); sctp_flush_out: sctp_outq_flush_transports(&ctx); } /* Update unack_data based on the incoming SACK chunk */ static void sctp_sack_update_unack_data(struct sctp_association *assoc, struct sctp_sackhdr *sack) { union sctp_sack_variable *frags; __u16 unack_data; int i; unack_data = assoc->next_tsn - assoc->ctsn_ack_point - 1; frags = (union sctp_sack_variable *)(sack + 1); for (i = 0; i < ntohs(sack->num_gap_ack_blocks); i++) { unack_data -= ((ntohs(frags[i].gab.end) - ntohs(frags[i].gab.start) + 1)); } assoc->unack_data = unack_data; } /* This is where we REALLY process a SACK. * * Process the SACK against the outqueue. Mostly, this just frees * things off the transmitted queue. */ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) { struct sctp_association *asoc = q->asoc; struct sctp_sackhdr *sack = chunk->subh.sack_hdr; struct sctp_transport *transport; struct sctp_chunk *tchunk = NULL; struct list_head *lchunk, *transport_list, *temp; __u32 sack_ctsn, ctsn, tsn; __u32 highest_tsn, highest_new_tsn; __u32 sack_a_rwnd; unsigned int outstanding; struct sctp_transport *primary = asoc->peer.primary_path; int count_of_newacks = 0; int gap_ack_blocks; u8 accum_moved = 0; /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list; /* SCTP path tracepoint for congestion control debugging. */ if (trace_sctp_probe_path_enabled()) { list_for_each_entry(transport, transport_list, transports) trace_sctp_probe_path(transport, asoc); } sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks; /* * SFR-CACC algorithm: * On receipt of a SACK the sender SHOULD execute the * following statements. * * 1) If the cumulative ack in the SACK passes next tsn_at_change * on the current primary, the CHANGEOVER_ACTIVE flag SHOULD be * cleared. The CYCLING_CHANGEOVER flag SHOULD also be cleared for * all destinations. * 2) If the SACK contains gap acks and the flag CHANGEOVER_ACTIVE * is set the receiver of the SACK MUST take the following actions: * * A) Initialize the cacc_saw_newack to 0 for all destination * addresses. * * Only bother if changeover_active is set. Otherwise, this is * totally suboptimal to do on every SACK. */ if (primary->cacc.changeover_active) { u8 clear_cycling = 0; if (TSN_lte(primary->cacc.next_tsn_at_change, sack_ctsn)) { primary->cacc.changeover_active = 0; clear_cycling = 1; } if (clear_cycling || gap_ack_blocks) { list_for_each_entry(transport, transport_list, transports) { if (clear_cycling) transport->cacc.cycling_changeover = 0; if (gap_ack_blocks) transport->cacc.cacc_saw_newack = 0; } } } /* Get the highest TSN in the sack. */ highest_tsn = sack_ctsn; if (gap_ack_blocks) { union sctp_sack_variable *frags = (union sctp_sack_variable *)(sack + 1); highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end); } if (TSN_lt(asoc->highest_sacked, highest_tsn)) asoc->highest_sacked = highest_tsn; highest_new_tsn = sack_ctsn; /* Run through the retransmit queue. Credit bytes received * and free those chunks that we can. */ sctp_check_transmitted(q, &q->retransmit, NULL, NULL, sack, &highest_new_tsn); /* Run through the transmitted queue. * Credit bytes received and free those chunks which we can. * * This is a MASSIVE candidate for optimization. */ list_for_each_entry(transport, transport_list, transports) { sctp_check_transmitted(q, &transport->transmitted, transport, &chunk->source, sack, &highest_new_tsn); /* * SFR-CACC algorithm: * C) Let count_of_newacks be the number of * destinations for which cacc_saw_newack is set. */ if (transport->cacc.cacc_saw_newack) count_of_newacks++; } /* Move the Cumulative TSN Ack Point if appropriate. */ if (TSN_lt(asoc->ctsn_ack_point, sack_ctsn)) { asoc->ctsn_ack_point = sack_ctsn; accum_moved = 1; } if (gap_ack_blocks) { if (asoc->fast_recovery && accum_moved) highest_new_tsn = highest_tsn; list_for_each_entry(transport, transport_list, transports) sctp_mark_missing(q, &transport->transmitted, transport, highest_new_tsn, count_of_newacks); } /* Update unack_data field in the assoc. */ sctp_sack_update_unack_data(asoc, sack); ctsn = asoc->ctsn_ack_point; /* Throw away stuff rotting on the sack queue. */ list_for_each_safe(lchunk, temp, &q->sacked) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(tchunk->subh.data_hdr->tsn); if (TSN_lte(tsn, ctsn)) { list_del_init(&tchunk->transmitted_list); if (asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) asoc->sent_cnt_removable--; sctp_chunk_free(tchunk); } } /* ii) Set rwnd equal to the newly received a_rwnd minus the * number of bytes still outstanding after processing the * Cumulative TSN Ack and the Gap Ack Blocks. */ sack_a_rwnd = ntohl(sack->a_rwnd); asoc->peer.zero_window_announced = !sack_a_rwnd; outstanding = q->outstanding_bytes; if (outstanding < sack_a_rwnd) sack_a_rwnd -= outstanding; else sack_a_rwnd = 0; asoc->peer.rwnd = sack_a_rwnd; asoc->stream.si->generate_ftsn(q, sack_ctsn); pr_debug("%s: sack cumulative tsn ack:0x%x\n", __func__, sack_ctsn); pr_debug("%s: cumulative tsn ack of assoc:%p is 0x%x, " "advertised peer ack point:0x%x\n", __func__, asoc, ctsn, asoc->adv_peer_ack_point); return sctp_outq_is_empty(q); } /* Is the outqueue empty? * The queue is empty when we have not pending data, no in-flight data * and nothing pending retransmissions. */ int sctp_outq_is_empty(const struct sctp_outq *q) { return q->out_qlen == 0 && q->outstanding_bytes == 0 && list_empty(&q->retransmit); } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Go through a transport's transmitted list or the association's retransmit * list and move chunks that are acked by the Cumulative TSN Ack to q->sacked. * The retransmit list will not have an associated transport. * * I added coherent debug information output. --xguo * * Instead of printing 'sacked' or 'kept' for each TSN on the * transmitted_queue, we print a range: SACKED: TSN1-TSN2, TSN3, TSN4-TSN5. * KEPT TSN6-TSN7, etc. */ static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn_in_sack) { struct list_head *lchunk; struct sctp_chunk *tchunk; struct list_head tlist; __u32 tsn; __u32 sack_ctsn; __u32 rtt; __u8 restart_timer = 0; int bytes_acked = 0; int migrate_bytes = 0; bool forward_progress = false; sack_ctsn = ntohl(sack->cum_tsn_ack); INIT_LIST_HEAD(&tlist); /* The while loop will skip empty transmitted queues. */ while (NULL != (lchunk = sctp_list_dequeue(transmitted_queue))) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); if (sctp_chunk_abandoned(tchunk)) { /* Move the chunk to abandoned list. */ sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been acked, stop * considering it as 'outstanding'. */ if (transmitted_queue != &q->retransmit && !tchunk->tsn_gap_acked) { if (tchunk->transport) tchunk->transport->flight_size -= sctp_data_size(tchunk); q->outstanding_bytes -= sctp_data_size(tchunk); } continue; } tsn = ntohl(tchunk->subh.data_hdr->tsn); if (sctp_acked(sack, tsn)) { /* If this queue is the retransmit queue, the * retransmit timer has already reclaimed * the outstanding bytes for this chunk, so only * count bytes associated with a transport. */ if (transport && !tchunk->tsn_gap_acked) { /* If this chunk is being used for RTT * measurement, calculate the RTT and update * the RTO using this value. * * 6.3.1 C5) Karn's algorithm: RTT measurements * MUST NOT be made using packets that were * retransmitted (and thus for which it is * ambiguous whether the reply was for the * first instance of the packet or a later * instance). */ if (!sctp_chunk_retransmitted(tchunk) && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; sctp_transport_update_rto(transport, rtt); } if (TSN_lte(tsn, sack_ctsn)) { /* * SFR-CACC algorithm: * 2) If the SACK contains gap acks * and the flag CHANGEOVER_ACTIVE is * set the receiver of the SACK MUST * take the following action: * * B) For each TSN t being acked that * has not been acked in any SACK so * far, set cacc_saw_newack to 1 for * the destination that the TSN was * sent to. */ if (sack->num_gap_ack_blocks && q->asoc->peer.primary_path->cacc. changeover_active) transport->cacc.cacc_saw_newack = 1; } } /* If the chunk hasn't been marked as ACKED, * mark it and account bytes_acked if the * chunk had a valid transport (it will not * have a transport if ASCONF had deleted it * while DATA was outstanding). */ if (!tchunk->tsn_gap_acked) { tchunk->tsn_gap_acked = 1; if (TSN_lt(*highest_new_tsn_in_sack, tsn)) *highest_new_tsn_in_sack = tsn; bytes_acked += sctp_data_size(tchunk); if (!tchunk->transport) migrate_bytes += sctp_data_size(tchunk); forward_progress = true; } if (TSN_lte(tsn, sack_ctsn)) { /* RFC 2960 6.3.2 Retransmission Timer Rules * * R3) Whenever a SACK is received * that acknowledges the DATA chunk * with the earliest outstanding TSN * for that address, restart T3-rtx * timer for that address with its * current RTO. */ restart_timer = 1; forward_progress = true; list_add_tail(&tchunk->transmitted_list, &q->sacked); } else { /* RFC2960 7.2.4, sctpimpguide-05 2.8.2 * M2) Each time a SACK arrives reporting * 'Stray DATA chunk(s)' record the highest TSN * reported as newly acknowledged, call this * value 'HighestTSNinSack'. A newly * acknowledged DATA chunk is one not * previously acknowledged in a SACK. * * When the SCTP sender of data receives a SACK * chunk that acknowledges, for the first time, * the receipt of a DATA chunk, all the still * unacknowledged DATA chunks whose TSN is * older than that newly acknowledged DATA * chunk, are qualified as 'Stray DATA chunks'. */ list_add_tail(lchunk, &tlist); } } else { if (tchunk->tsn_gap_acked) { pr_debug("%s: receiver reneged on data TSN:0x%x\n", __func__, tsn); tchunk->tsn_gap_acked = 0; if (tchunk->transport) bytes_acked -= sctp_data_size(tchunk); /* RFC 2960 6.3.2 Retransmission Timer Rules * * R4) Whenever a SACK is received missing a * TSN that was previously acknowledged via a * Gap Ack Block, start T3-rtx for the * destination address to which the DATA * chunk was originally * transmitted if it is not already running. */ restart_timer = 1; } list_add_tail(lchunk, &tlist); } } if (transport) { if (bytes_acked) { struct sctp_association *asoc = transport->asoc; /* We may have counted DATA that was migrated * to this transport due to DEL-IP operation. * Subtract those bytes, since the were never * send on this transport and shouldn't be * credited to this transport. */ bytes_acked -= migrate_bytes; /* 8.2. When an outstanding TSN is acknowledged, * the endpoint shall clear the error counter of * the destination transport address to which the * DATA chunk was last sent. * The association's overall error counter is * also cleared. */ transport->error_count = 0; transport->asoc->overall_error_count = 0; forward_progress = true; /* * While in SHUTDOWN PENDING, we may have started * the T5 shutdown guard timer after reaching the * retransmission limit. Stop that timer as soon * as the receiver acknowledged any data. */ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && timer_delete(&asoc->timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) sctp_association_put(asoc); /* Mark the destination transport address as * active if it is not so marked. */ if ((transport->state == SCTP_INACTIVE || transport->state == SCTP_UNCONFIRMED) && sctp_cmp_addr_exact(&transport->ipaddr, saddr)) { sctp_assoc_control_transport( transport->asoc, transport, SCTP_TRANSPORT_UP, SCTP_RECEIVED_SACK); } sctp_transport_raise_cwnd(transport, sack_ctsn, bytes_acked); transport->flight_size -= bytes_acked; if (transport->flight_size == 0) transport->partial_bytes_acked = 0; q->outstanding_bytes -= bytes_acked + migrate_bytes; } else { /* RFC 2960 6.1, sctpimpguide-06 2.15.2 * When a sender is doing zero window probing, it * should not timeout the association if it continues * to receive new packets from the receiver. The * reason is that the receiver MAY keep its window * closed for an indefinite time. * A sender is doing zero window probing when the * receiver's advertised window is zero, and there is * only one data chunk in flight to the receiver. * * Allow the association to timeout while in SHUTDOWN * PENDING or SHUTDOWN RECEIVED in case the receiver * stays in zero window mode forever. */ if (!q->asoc->peer.rwnd && !list_empty(&tlist) && (sack_ctsn+2 == q->asoc->next_tsn) && q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) { pr_debug("%s: sack received for zero window " "probe:%u\n", __func__, sack_ctsn); q->asoc->overall_error_count = 0; transport->error_count = 0; } } /* RFC 2960 6.3.2 Retransmission Timer Rules * * R2) Whenever all outstanding data sent to an address have * been acknowledged, turn off the T3-rtx timer of that * address. */ if (!transport->flight_size) { if (timer_delete(&transport->T3_rtx_timer)) sctp_transport_put(transport); } else if (restart_timer) { if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); } if (forward_progress) { if (transport->dst) sctp_transport_dst_confirm(transport); } } list_splice(&tlist, transmitted_queue); } /* Mark chunks as missing and consequently may get retransmitted. */ static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn_in_sack, int count_of_newacks) { struct sctp_chunk *chunk; __u32 tsn; char do_fast_retransmit = 0; struct sctp_association *asoc = q->asoc; struct sctp_transport *primary = asoc->peer.primary_path; list_for_each_entry(chunk, transmitted_queue, transmitted_list) { tsn = ntohl(chunk->subh.data_hdr->tsn); /* RFC 2960 7.2.4, sctpimpguide-05 2.8.2 M3) Examine all * 'Unacknowledged TSN's', if the TSN number of an * 'Unacknowledged TSN' is smaller than the 'HighestTSNinSack' * value, increment the 'TSN.Missing.Report' count on that * chunk if it has NOT been fast retransmitted or marked for * fast retransmit already. */ if (chunk->fast_retransmit == SCTP_CAN_FRTX && !chunk->tsn_gap_acked && TSN_lt(tsn, highest_new_tsn_in_sack)) { /* SFR-CACC may require us to skip marking * this chunk as missing. */ if (!transport || !sctp_cacc_skip(primary, chunk->transport, count_of_newacks, tsn)) { chunk->tsn_missing_report++; pr_debug("%s: tsn:0x%x missing counter:%d\n", __func__, tsn, chunk->tsn_missing_report); } } /* * M4) If any DATA chunk is found to have a * 'TSN.Missing.Report' * value larger than or equal to 3, mark that chunk for * retransmission and start the fast retransmit procedure. */ if (chunk->tsn_missing_report >= 3) { chunk->fast_retransmit = SCTP_NEED_FRTX; do_fast_retransmit = 1; } } if (transport) { if (do_fast_retransmit) sctp_retransmit(q, transport, SCTP_RTXR_FAST_RTX); pr_debug("%s: transport:%p, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } } /* Is the given TSN acked by this packet? */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) { __u32 ctsn = ntohl(sack->cum_tsn_ack); union sctp_sack_variable *frags; __u16 tsn_offset, blocks; int i; if (TSN_lte(tsn, ctsn)) goto pass; /* 3.3.4 Selective Acknowledgment (SACK) (3): * * Gap Ack Blocks: * These fields contain the Gap Ack Blocks. They are repeated * for each Gap Ack Block up to the number of Gap Ack Blocks * defined in the Number of Gap Ack Blocks field. All DATA * chunks with TSNs greater than or equal to (Cumulative TSN * Ack + Gap Ack Block Start) and less than or equal to * (Cumulative TSN Ack + Gap Ack Block End) of each Gap Ack * Block are assumed to have been received correctly. */ frags = (union sctp_sack_variable *)(sack + 1); blocks = ntohs(sack->num_gap_ack_blocks); tsn_offset = tsn - ctsn; for (i = 0; i < blocks; ++i) { if (tsn_offset >= ntohs(frags[i].gab.start) && tsn_offset <= ntohs(frags[i].gab.end)) goto pass; } return 0; pass: return 1; } static inline int sctp_get_skip_pos(struct sctp_fwdtsn_skip *skiplist, int nskips, __be16 stream) { int i; for (i = 0; i < nskips; i++) { if (skiplist[i].stream == stream) return i; } return i; } /* Create and add a fwdtsn chunk to the outq's control queue if needed. */ void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 ctsn) { struct sctp_association *asoc = q->asoc; struct sctp_chunk *ftsn_chunk = NULL; struct sctp_fwdtsn_skip ftsn_skip_arr[10]; int nskips = 0; int skip_pos = 0; __u32 tsn; struct sctp_chunk *chunk; struct list_head *lchunk, *temp; if (!asoc->peer.prsctp_capable) return; /* PR-SCTP C1) Let SackCumAck be the Cumulative TSN ACK carried in the * received SACK. * * If (Advanced.Peer.Ack.Point < SackCumAck), then update * Advanced.Peer.Ack.Point to be equal to SackCumAck. */ if (TSN_lt(asoc->adv_peer_ack_point, ctsn)) asoc->adv_peer_ack_point = ctsn; /* PR-SCTP C2) Try to further advance the "Advanced.Peer.Ack.Point" * locally, that is, to move "Advanced.Peer.Ack.Point" up as long as * the chunk next in the out-queue space is marked as "abandoned" as * shown in the following example: * * Assuming that a SACK arrived with the Cumulative TSN ACK 102 * and the Advanced.Peer.Ack.Point is updated to this value: * * out-queue at the end of ==> out-queue after Adv.Ack.Point * normal SACK processing local advancement * ... ... * Adv.Ack.Pt-> 102 acked 102 acked * 103 abandoned 103 abandoned * 104 abandoned Adv.Ack.P-> 104 abandoned * 105 105 * 106 acked 106 acked * ... ... * * In this example, the data sender successfully advanced the * "Advanced.Peer.Ack.Point" from 102 to 104 locally. */ list_for_each_safe(lchunk, temp, &q->abandoned) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(chunk->subh.data_hdr->tsn); /* Remove any chunks in the abandoned queue that are acked by * the ctsn. */ if (TSN_lte(tsn, ctsn)) { list_del_init(lchunk); sctp_chunk_free(chunk); } else { if (TSN_lte(tsn, asoc->adv_peer_ack_point+1)) { asoc->adv_peer_ack_point = tsn; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) continue; skip_pos = sctp_get_skip_pos(&ftsn_skip_arr[0], nskips, chunk->subh.data_hdr->stream); ftsn_skip_arr[skip_pos].stream = chunk->subh.data_hdr->stream; ftsn_skip_arr[skip_pos].ssn = chunk->subh.data_hdr->ssn; if (skip_pos == nskips) nskips++; if (nskips == 10) break; } else break; } } /* PR-SCTP C3) If, after step C1 and C2, the "Advanced.Peer.Ack.Point" * is greater than the Cumulative TSN ACK carried in the received * SACK, the data sender MUST send the data receiver a FORWARD TSN * chunk containing the latest value of the * "Advanced.Peer.Ack.Point". * * C4) For each "abandoned" TSN the sender of the FORWARD TSN SHOULD * list each stream and sequence number in the forwarded TSN. This * information will enable the receiver to easily find any * stranded TSN's waiting on stream reorder queues. Each stream * SHOULD only be reported once; this means that if multiple * abandoned messages occur in the same stream then only the * highest abandoned stream sequence number is reported. If the * total size of the FORWARD TSN does NOT fit in a single MTU then * the sender of the FORWARD TSN SHOULD lower the * Advanced.Peer.Ack.Point to the last TSN that will fit in a * single MTU. */ if (asoc->adv_peer_ack_point > ctsn) ftsn_chunk = sctp_make_fwdtsn(asoc, asoc->adv_peer_ack_point, nskips, &ftsn_skip_arr[0]); if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IPV6 GSO/GRO offload support * Linux INET implementation * * Copyright (C) 2016 secunet Security Networks AG * Author: Steffen Klassert <steffen.klassert@secunet.com> * * ESP GRO support */ #include <linux/skbuff.h> #include <linux/init.h> #include <net/protocol.h> #include <crypto/aead.h> #include <crypto/authenc.h> #include <linux/err.h> #include <linux/module.h> #include <net/gro.h> #include <net/gso.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> #include <linux/scatterlist.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/ip6_route.h> #include <net/ipv6.h> #include <linux/icmpv6.h> static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen) { int off = sizeof(struct ipv6hdr); struct ipv6_opt_hdr *exthdr; /* ESP or ESPINUDP */ if (likely(ipv6_hdr->nexthdr == NEXTHDR_ESP || ipv6_hdr->nexthdr == NEXTHDR_UDP)) return offsetof(struct ipv6hdr, nexthdr); while (off < nhlen) { exthdr = (void *)ipv6_hdr + off; if (exthdr->nexthdr == NEXTHDR_ESP) return off; off += ipv6_optlen(exthdr); } return 0; } static struct sk_buff *esp6_gro_receive(struct list_head *head, struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; struct xfrm_state *x; int encap_type = 0; __be32 seq; __be32 spi; int nhoff; if (NAPI_GRO_CB(skb)->proto == IPPROTO_UDP) encap_type = UDP_ENCAP_ESPINUDP; if (!pskb_pull(skb, offset)) return NULL; if (xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq) != 0) goto out; xo = xfrm_offload(skb); if (!xo || !(xo->flags & CRYPTO_DONE)) { struct sec_path *sp = secpath_set(skb); if (!sp) goto out; if (sp->len == XFRM_MAX_DEPTH) goto out_reset; x = xfrm_input_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ipv6_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET6); if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) { /* non-offload path will record the error and audit log */ xfrm_state_put(x); x = NULL; } if (!x) goto out_reset; skb->mark = xfrm_smark_get(skb->mark, x); sp->xvec[sp->len++] = x; sp->olen++; xo = xfrm_offload(skb); if (!xo) goto out_reset; } xo->flags |= XFRM_GRO; nhoff = esp6_nexthdr_esp_offset(ipv6_hdr(skb), offset); if (!nhoff) goto out; IP6CB(skb)->nhoff = nhoff; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); XFRM_SPI_SKB_CB(skb)->seq = seq; /* We don't need to handle errors from xfrm_input, it does all * the error handling and frees the resources on error. */ xfrm_input(skb, IPPROTO_ESP, spi, encap_type); return ERR_PTR(-EINPROGRESS); out_reset: secpath_reset(skb); out: skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 1; return NULL; } static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb) { struct ip_esp_hdr *esph; struct ipv6hdr *iph = ipv6_hdr(skb); struct xfrm_offload *xo = xfrm_offload(skb); u8 proto = iph->nexthdr; skb_push(skb, -skb_network_offset(skb)); if (x->outer_mode.encap == XFRM_MODE_TRANSPORT) { __be16 frag; ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag); } esph = ip_esp_hdr(skb); *skb_mac_header(skb) = IPPROTO_ESP; esph->spi = x->id.spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); xo->proto = proto; } static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { __be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP) : htons(ETH_P_IPV6); return skb_eth_gso_segment(skb, features, type); } static struct sk_buff *xfrm6_transport_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct xfrm_offload *xo = xfrm_offload(skb); skb->transport_header += x->props.header_len; ops = rcu_dereference(inet6_offloads[xo->proto]); if (likely(ops && ops->callbacks.gso_segment)) segs = ops->callbacks.gso_segment(skb, features); return segs; } static struct sk_buff *xfrm6_beet_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { struct xfrm_offload *xo = xfrm_offload(skb); struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; u8 proto = xo->proto; skb->transport_header += x->props.header_len; if (x->sel.family != AF_INET6) { skb->transport_header -= (sizeof(struct ipv6hdr) - sizeof(struct iphdr)); if (proto == IPPROTO_BEETPH) { struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data; skb->transport_header += ph->hdrlen * 8; proto = ph->nexthdr; } else { skb->transport_header -= IPV4_BEET_PHMAXLEN; } if (proto == IPPROTO_TCP) skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; } else { __be16 frag; skb->transport_header += ipv6_skip_exthdr(skb, 0, &proto, &frag); } if (proto == IPPROTO_IPIP) skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6; __skb_pull(skb, skb_transport_offset(skb)); ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) segs = ops->callbacks.gso_segment(skb, features); return segs; } static struct sk_buff *xfrm6_outer_mode_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { switch (x->outer_mode.encap) { case XFRM_MODE_TUNNEL: return xfrm6_tunnel_gso_segment(x, skb, features); case XFRM_MODE_TRANSPORT: return xfrm6_transport_gso_segment(x, skb, features); case XFRM_MODE_BEET: return xfrm6_beet_gso_segment(x, skb, features); } return ERR_PTR(-EOPNOTSUPP); } static struct sk_buff *esp6_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct xfrm_state *x; struct ip_esp_hdr *esph; struct crypto_aead *aead; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; if (!xo) return ERR_PTR(-EINVAL); if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP)) return ERR_PTR(-EINVAL); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; aead = x->data; esph = ip_esp_hdr(skb); if (esph->spi != x->id.spi) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) return ERR_PTR(-EINVAL); __skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)); skb->encap_hdr_csum = 1; if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC); else if (!(features & NETIF_F_HW_ESP_TX_CSUM)) esp_features = features & ~(NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC); xo->flags |= XFRM_GSO_SEGMENT; return xfrm6_outer_mode_gso_segment(x, skb, esp_features); } static int esp6_input_tail(struct xfrm_state *x, struct sk_buff *skb) { struct crypto_aead *aead = x->data; struct xfrm_offload *xo = xfrm_offload(skb); if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead))) return -EINVAL; if (!(xo->flags & CRYPTO_DONE)) skb->ip_summed = CHECKSUM_NONE; return esp6_input_done2(skb, 0); } static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { int len; int err; int alen; int blksize; struct xfrm_offload *xo; struct crypto_aead *aead; struct esp_info esp; bool hw_offload = true; __u32 seq; esp.inplace = true; xo = xfrm_offload(skb); if (!xo) return -EINVAL; if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) { xo->flags |= CRYPTO_FALLBACK; hw_offload = false; } esp.proto = xo->proto; /* skb is pure payload to encrypt */ aead = x->data; alen = crypto_aead_authsize(aead); esp.tfclen = 0; /* XXX: Add support for tfc padding here. */ blksize = ALIGN(crypto_aead_blocksize(aead), 4); esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize); esp.plen = esp.clen - skb->len - esp.tfclen; esp.tailen = esp.tfclen + esp.plen + alen; if (!hw_offload || !skb_is_gso(skb)) { esp.nfrags = esp6_output_head(x, skb, &esp); if (esp.nfrags < 0) return esp.nfrags; } seq = xo->seq.low; esp.esph = ip_esp_hdr(skb); esp.esph->spi = x->id.spi; skb_push(skb, -skb_network_offset(skb)); if (xo->flags & XFRM_GSO_SEGMENT) { esp.esph->seq_no = htonl(seq); if (!skb_is_gso(skb)) xo->seq.low++; else xo->seq.low += skb_shinfo(skb)->gso_segs; } if (xo->seq.low < seq) xo->seq.hi++; esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); len = skb->len - sizeof(struct ipv6hdr); if (len > IPV6_MAXPLEN) len = 0; ipv6_hdr(skb)->payload_len = htons(len); if (hw_offload) { if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) return -ENOMEM; xo = xfrm_offload(skb); if (!xo) return -EINVAL; xo->flags |= XFRM_XMIT; return 0; } err = esp6_output_tail(x, skb, &esp); if (err) return err; secpath_reset(skb); if (skb_needs_linearize(skb, skb->dev->features) && __skb_linearize(skb)) return -ENOMEM; return 0; } static const struct net_offload esp6_offload = { .callbacks = { .gro_receive = esp6_gro_receive, .gso_segment = esp6_gso_segment, }, }; static const struct xfrm_type_offload esp6_type_offload = { .owner = THIS_MODULE, .proto = IPPROTO_ESP, .input_tail = esp6_input_tail, .xmit = esp6_xmit, .encap = esp6_gso_encap, }; static int __init esp6_offload_init(void) { if (xfrm_register_type_offload(&esp6_type_offload, AF_INET6) < 0) { pr_info("%s: can't add xfrm type offload\n", __func__); return -EAGAIN; } return inet6_add_offload(&esp6_offload, IPPROTO_ESP); } static void __exit esp6_offload_exit(void) { xfrm_unregister_type_offload(&esp6_type_offload, AF_INET6); inet6_del_offload(&esp6_offload, IPPROTO_ESP); } module_init(esp6_offload_init); module_exit(esp6_offload_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET6, XFRM_PROTO_ESP); MODULE_DESCRIPTION("IPV6 GSO/GRO offload support"); |
| 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 | /* * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/slab.h> #include <linux/types.h> #include <linux/rbtree.h> #include <linux/bitops.h> #include <linux/export.h> #include "rds.h" /* * This file implements the receive side of the unconventional congestion * management in RDS. * * Messages waiting in the receive queue on the receiving socket are accounted * against the sockets SO_RCVBUF option value. Only the payload bytes in the * message are accounted for. If the number of bytes queued equals or exceeds * rcvbuf then the socket is congested. All sends attempted to this socket's * address should return block or return -EWOULDBLOCK. * * Applications are expected to be reasonably tuned such that this situation * very rarely occurs. An application encountering this "back-pressure" is * considered a bug. * * This is implemented by having each node maintain bitmaps which indicate * which ports on bound addresses are congested. As the bitmap changes it is * sent through all the connections which terminate in the local address of the * bitmap which changed. * * The bitmaps are allocated as connections are brought up. This avoids * allocation in the interrupt handling path which queues messages on sockets. * The dense bitmaps let transports send the entire bitmap on any bitmap change * reasonably efficiently. This is much easier to implement than some * finer-grained communication of per-port congestion. The sender does a very * inexpensive bit test to test if the port it's about to send to is congested * or not. */ /* * Interaction with poll is a tad tricky. We want all processes stuck in * poll to wake up and check whether a congested destination became uncongested. * The really sad thing is we have no idea which destinations the application * wants to send to - we don't even know which rds_connections are involved. * So until we implement a more flexible rds poll interface, we have to make * do with this: * We maintain a global counter that is incremented each time a congestion map * update is received. Each rds socket tracks this value, and if rds_poll * finds that the saved generation number is smaller than the global generation * number, it wakes up the process. */ static atomic_t rds_cong_generation = ATOMIC_INIT(0); /* * Congestion monitoring */ static LIST_HEAD(rds_cong_monitor); static DEFINE_RWLOCK(rds_cong_monitor_lock); /* * Yes, a global lock. It's used so infrequently that it's worth keeping it * global to simplify the locking. It's only used in the following * circumstances: * * - on connection buildup to associate a conn with its maps * - on map changes to inform conns of a new map to send * * It's sadly ordered under the socket callback lock and the connection lock. * Receive paths can mark ports congested from interrupt context so the * lock masks interrupts. */ static DEFINE_SPINLOCK(rds_cong_lock); static struct rb_root rds_cong_tree = RB_ROOT; static struct rds_cong_map *rds_cong_tree_walk(const struct in6_addr *addr, struct rds_cong_map *insert) { struct rb_node **p = &rds_cong_tree.rb_node; struct rb_node *parent = NULL; struct rds_cong_map *map; while (*p) { int diff; parent = *p; map = rb_entry(parent, struct rds_cong_map, m_rb_node); diff = rds_addr_cmp(addr, &map->m_addr); if (diff < 0) p = &(*p)->rb_left; else if (diff > 0) p = &(*p)->rb_right; else return map; } if (insert) { rb_link_node(&insert->m_rb_node, parent, p); rb_insert_color(&insert->m_rb_node, &rds_cong_tree); } return NULL; } /* * There is only ever one bitmap for any address. Connections try and allocate * these bitmaps in the process getting pointers to them. The bitmaps are only * ever freed as the module is removed after all connections have been freed. */ static struct rds_cong_map *rds_cong_from_addr(const struct in6_addr *addr) { struct rds_cong_map *map; struct rds_cong_map *ret = NULL; unsigned long zp; unsigned long i; unsigned long flags; map = kzalloc(sizeof(struct rds_cong_map), GFP_KERNEL); if (!map) return NULL; map->m_addr = *addr; init_waitqueue_head(&map->m_waitq); INIT_LIST_HEAD(&map->m_conn_list); for (i = 0; i < RDS_CONG_MAP_PAGES; i++) { zp = get_zeroed_page(GFP_KERNEL); if (zp == 0) goto out; map->m_page_addrs[i] = zp; } spin_lock_irqsave(&rds_cong_lock, flags); ret = rds_cong_tree_walk(addr, map); spin_unlock_irqrestore(&rds_cong_lock, flags); if (!ret) { ret = map; map = NULL; } out: if (map) { for (i = 0; i < RDS_CONG_MAP_PAGES && map->m_page_addrs[i]; i++) free_page(map->m_page_addrs[i]); kfree(map); } rdsdebug("map %p for addr %pI6c\n", ret, addr); return ret; } /* * Put the conn on its local map's list. This is called when the conn is * really added to the hash. It's nested under the rds_conn_lock, sadly. */ void rds_cong_add_conn(struct rds_connection *conn) { unsigned long flags; rdsdebug("conn %p now on map %p\n", conn, conn->c_lcong); spin_lock_irqsave(&rds_cong_lock, flags); list_add_tail(&conn->c_map_item, &conn->c_lcong->m_conn_list); spin_unlock_irqrestore(&rds_cong_lock, flags); } void rds_cong_remove_conn(struct rds_connection *conn) { unsigned long flags; rdsdebug("removing conn %p from map %p\n", conn, conn->c_lcong); spin_lock_irqsave(&rds_cong_lock, flags); list_del_init(&conn->c_map_item); spin_unlock_irqrestore(&rds_cong_lock, flags); } int rds_cong_get_maps(struct rds_connection *conn) { conn->c_lcong = rds_cong_from_addr(&conn->c_laddr); conn->c_fcong = rds_cong_from_addr(&conn->c_faddr); if (!(conn->c_lcong && conn->c_fcong)) return -ENOMEM; return 0; } void rds_cong_queue_updates(struct rds_cong_map *map) { struct rds_connection *conn; unsigned long flags; spin_lock_irqsave(&rds_cong_lock, flags); list_for_each_entry(conn, &map->m_conn_list, c_map_item) { struct rds_conn_path *cp = &conn->c_path[0]; rcu_read_lock(); if (!test_and_set_bit(0, &conn->c_map_queued) && !rds_destroy_pending(cp->cp_conn)) { rds_stats_inc(s_cong_update_queued); /* We cannot inline the call to rds_send_xmit() here * for two reasons (both pertaining to a TCP transport): * 1. When we get here from the receive path, we * are already holding the sock_lock (held by * tcp_v4_rcv()). So inlining calls to * tcp_setsockopt and/or tcp_sendmsg will deadlock * when it tries to get the sock_lock()) * 2. Interrupts are masked so that we can mark the * port congested from both send and recv paths. * (See comment around declaration of rdc_cong_lock). * An attempt to get the sock_lock() here will * therefore trigger warnings. * Defer the xmit to rds_send_worker() instead. */ queue_delayed_work(rds_wq, &cp->cp_send_w, 0); } rcu_read_unlock(); } spin_unlock_irqrestore(&rds_cong_lock, flags); } void rds_cong_map_updated(struct rds_cong_map *map, uint64_t portmask) { rdsdebug("waking map %p for %pI4\n", map, &map->m_addr); rds_stats_inc(s_cong_update_received); atomic_inc(&rds_cong_generation); if (waitqueue_active(&map->m_waitq)) wake_up(&map->m_waitq); if (waitqueue_active(&rds_poll_waitq)) wake_up_all(&rds_poll_waitq); if (portmask && !list_empty(&rds_cong_monitor)) { unsigned long flags; struct rds_sock *rs; read_lock_irqsave(&rds_cong_monitor_lock, flags); list_for_each_entry(rs, &rds_cong_monitor, rs_cong_list) { spin_lock(&rs->rs_lock); rs->rs_cong_notify |= (rs->rs_cong_mask & portmask); rs->rs_cong_mask &= ~portmask; spin_unlock(&rs->rs_lock); if (rs->rs_cong_notify) rds_wake_sk_sleep(rs); } read_unlock_irqrestore(&rds_cong_monitor_lock, flags); } } EXPORT_SYMBOL_GPL(rds_cong_map_updated); int rds_cong_updated_since(unsigned long *recent) { unsigned long gen = atomic_read(&rds_cong_generation); if (likely(*recent == gen)) return 0; *recent = gen; return 1; } /* * We're called under the locking that protects the sockets receive buffer * consumption. This makes it a lot easier for the caller to only call us * when it knows that an existing set bit needs to be cleared, and vice versa. * We can't block and we need to deal with concurrent sockets working against * the same per-address map. */ void rds_cong_set_bit(struct rds_cong_map *map, __be16 port) { unsigned long i; unsigned long off; rdsdebug("setting congestion for %pI4:%u in map %p\n", &map->m_addr, ntohs(port), map); i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; set_bit_le(off, (void *)map->m_page_addrs[i]); } void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port) { unsigned long i; unsigned long off; rdsdebug("clearing congestion for %pI4:%u in map %p\n", &map->m_addr, ntohs(port), map); i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; clear_bit_le(off, (void *)map->m_page_addrs[i]); } static int rds_cong_test_bit(struct rds_cong_map *map, __be16 port) { unsigned long i; unsigned long off; i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS; off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS; return test_bit_le(off, (void *)map->m_page_addrs[i]); } void rds_cong_add_socket(struct rds_sock *rs) { unsigned long flags; write_lock_irqsave(&rds_cong_monitor_lock, flags); if (list_empty(&rs->rs_cong_list)) list_add(&rs->rs_cong_list, &rds_cong_monitor); write_unlock_irqrestore(&rds_cong_monitor_lock, flags); } void rds_cong_remove_socket(struct rds_sock *rs) { unsigned long flags; struct rds_cong_map *map; write_lock_irqsave(&rds_cong_monitor_lock, flags); list_del_init(&rs->rs_cong_list); write_unlock_irqrestore(&rds_cong_monitor_lock, flags); /* update congestion map for now-closed port */ spin_lock_irqsave(&rds_cong_lock, flags); map = rds_cong_tree_walk(&rs->rs_bound_addr, NULL); spin_unlock_irqrestore(&rds_cong_lock, flags); if (map && rds_cong_test_bit(map, rs->rs_bound_port)) { rds_cong_clear_bit(map, rs->rs_bound_port); rds_cong_queue_updates(map); } } int rds_cong_wait(struct rds_cong_map *map, __be16 port, int nonblock, struct rds_sock *rs) { if (!rds_cong_test_bit(map, port)) return 0; if (nonblock) { if (rs && rs->rs_cong_monitor) { unsigned long flags; /* It would have been nice to have an atomic set_bit on * a uint64_t. */ spin_lock_irqsave(&rs->rs_lock, flags); rs->rs_cong_mask |= RDS_CONG_MONITOR_MASK(ntohs(port)); spin_unlock_irqrestore(&rs->rs_lock, flags); /* Test again - a congestion update may have arrived in * the meantime. */ if (!rds_cong_test_bit(map, port)) return 0; } rds_stats_inc(s_cong_send_error); return -ENOBUFS; } rds_stats_inc(s_cong_send_blocked); rdsdebug("waiting on map %p for port %u\n", map, be16_to_cpu(port)); return wait_event_interruptible(map->m_waitq, !rds_cong_test_bit(map, port)); } void rds_cong_exit(void) { struct rb_node *node; struct rds_cong_map *map; unsigned long i; while ((node = rb_first(&rds_cong_tree))) { map = rb_entry(node, struct rds_cong_map, m_rb_node); rdsdebug("freeing map %p\n", map); rb_erase(&map->m_rb_node, &rds_cong_tree); for (i = 0; i < RDS_CONG_MAP_PAGES && map->m_page_addrs[i]; i++) free_page(map->m_page_addrs[i]); kfree(map); } } /* * Allocate a RDS message containing a congestion update. */ struct rds_message *rds_cong_update_alloc(struct rds_connection *conn) { struct rds_cong_map *map = conn->c_lcong; struct rds_message *rm; rm = rds_message_map_pages(map->m_page_addrs, RDS_CONG_MAP_BYTES); if (!IS_ERR(rm)) rm->m_inc.i_hdr.h_flags = RDS_FLAG_CONG_BITMAP; return rm; } |
| 29 29 225 82 22 20 20 20 20 213 212 2 2 20 20 20 20 20 2 2 214 215 2 9 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Process number limiting controller for cgroups. * * Used to allow a cgroup hierarchy to stop any new processes from fork()ing * after a certain limit is reached. * * Since it is trivial to hit the task limit without hitting any kmemcg limits * in place, PIDs are a fundamental resource. As such, PID exhaustion must be * preventable in the scope of a cgroup hierarchy by allowing resource limiting * of the number of tasks in a cgroup. * * In order to use the `pids` controller, set the maximum number of tasks in * pids.max (this is not available in the root cgroup for obvious reasons). The * number of processes currently in the cgroup is given by pids.current. * Organisational operations are not blocked by cgroup policies, so it is * possible to have pids.current > pids.max. However, it is not possible to * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking * would cause a cgroup policy to be violated. * * To set a cgroup to have no limit, set pids.max to "max". This is the default * for all new cgroups (N.B. that PID limits are hierarchical, so the most * stringent limit in the hierarchy is followed). * * pids.current tracks all child cgroup hierarchies, so parent/pids.current is * a superset of parent/child/pids.current. * * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com> */ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cgroup.h> #include <linux/slab.h> #include <linux/sched/task.h> #define PIDS_MAX (PID_MAX_LIMIT + 1ULL) #define PIDS_MAX_STR "max" enum pidcg_event { /* Fork failed in subtree because this pids_cgroup limit was hit. */ PIDCG_MAX, /* Fork failed in this pids_cgroup because ancestor limit was hit. */ PIDCG_FORKFAIL, NR_PIDCG_EVENTS, }; struct pids_cgroup { struct cgroup_subsys_state css; /* * Use 64-bit types so that we can safely represent "max" as * %PIDS_MAX = (%PID_MAX_LIMIT + 1). */ atomic64_t counter; atomic64_t limit; int64_t watermark; /* Handles for pids.events[.local] */ struct cgroup_file events_file; struct cgroup_file events_local_file; atomic64_t events[NR_PIDCG_EVENTS]; atomic64_t events_local[NR_PIDCG_EVENTS]; }; static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css) { return container_of(css, struct pids_cgroup, css); } static struct pids_cgroup *parent_pids(struct pids_cgroup *pids) { return css_pids(pids->css.parent); } static struct cgroup_subsys_state * pids_css_alloc(struct cgroup_subsys_state *parent) { struct pids_cgroup *pids; pids = kzalloc(sizeof(struct pids_cgroup), GFP_KERNEL); if (!pids) return ERR_PTR(-ENOMEM); atomic64_set(&pids->limit, PIDS_MAX); return &pids->css; } static void pids_css_free(struct cgroup_subsys_state *css) { kfree(css_pids(css)); } static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids) { /* * This is racy, but we don't need perfectly accurate tallying of * the watermark, and this lets us avoid extra atomic overhead. */ if (nr_pids > READ_ONCE(p->watermark)) WRITE_ONCE(p->watermark, nr_pids); } /** * pids_cancel - uncharge the local pid count * @pids: the pid cgroup state * @num: the number of pids to cancel * * This function will WARN if the pid count goes under 0, because such a case is * a bug in the pids controller proper. */ static void pids_cancel(struct pids_cgroup *pids, int num) { /* * A negative count (or overflow for that matter) is invalid, * and indicates a bug in the `pids` controller proper. */ WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter)); } /** * pids_uncharge - hierarchically uncharge the pid count * @pids: the pid cgroup state * @num: the number of pids to uncharge */ static void pids_uncharge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; for (p = pids; parent_pids(p); p = parent_pids(p)) pids_cancel(p, num); } /** * pids_charge - hierarchically charge the pid count * @pids: the pid cgroup state * @num: the number of pids to charge * * This function does *not* follow the pid limit set. It cannot fail and the new * pid count may exceed the limit. This is only used for reverting failed * attaches, where there is no other way out than violating the limit. */ static void pids_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); pids_update_watermark(p, new); } } /** * pids_try_charge - hierarchically try to charge the pid count * @pids: the pid cgroup state * @num: the number of pids to charge * @fail: storage of pid cgroup causing the fail * * This function follows the set limit. It will fail if the charge would cause * the new value to exceed the hierarchical limit. Returns 0 if the charge * succeeded, otherwise -EAGAIN. */ static int pids_try_charge(struct pids_cgroup *pids, int num, struct pids_cgroup **fail) { struct pids_cgroup *p, *q; for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); int64_t limit = atomic64_read(&p->limit); /* * Since new is capped to the maximum number of pid_t, if * p->limit is %PIDS_MAX then we know that this test will never * fail. */ if (new > limit) { *fail = p; goto revert; } /* * Not technically accurate if we go over limit somewhere up * the hierarchy, but that's tolerable for the watermark. */ pids_update_watermark(p, new); } return 0; revert: for (q = pids; q != p; q = parent_pids(q)) pids_cancel(q, num); pids_cancel(p, num); return -EAGAIN; } static int pids_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *dst_css; cgroup_taskset_for_each(task, dst_css, tset) { struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; /* * No need to pin @old_css between here and cancel_attach() * because cgroup core protects it from being freed before * the migration completes or fails. */ old_css = task_css(task, pids_cgrp_id); old_pids = css_pids(old_css); pids_charge(pids, 1); pids_uncharge(old_pids, 1); } return 0; } static void pids_cancel_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *dst_css; cgroup_taskset_for_each(task, dst_css, tset) { struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; old_css = task_css(task, pids_cgrp_id); old_pids = css_pids(old_css); pids_charge(old_pids, 1); pids_uncharge(pids, 1); } } static void pids_event(struct pids_cgroup *pids_forking, struct pids_cgroup *pids_over_limit) { struct pids_cgroup *p = pids_forking; /* Only log the first time limit is hit. */ if (atomic64_inc_return(&p->events_local[PIDCG_FORKFAIL]) == 1) { pr_info("cgroup: fork rejected by pids controller in "); pr_cont_cgroup_path(p->css.cgroup); pr_cont("\n"); } if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { cgroup_file_notify(&p->events_local_file); return; } atomic64_inc(&pids_over_limit->events_local[PIDCG_MAX]); cgroup_file_notify(&pids_over_limit->events_local_file); for (p = pids_over_limit; parent_pids(p); p = parent_pids(p)) { atomic64_inc(&p->events[PIDCG_MAX]); cgroup_file_notify(&p->events_file); } } /* * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies * on cgroup_threadgroup_change_begin() held by the copy_process(). */ static int pids_can_fork(struct task_struct *task, struct css_set *cset) { struct pids_cgroup *pids, *pids_over_limit; int err; pids = css_pids(cset->subsys[pids_cgrp_id]); err = pids_try_charge(pids, 1, &pids_over_limit); if (err) pids_event(pids, pids_over_limit); return err; } static void pids_cancel_fork(struct task_struct *task, struct css_set *cset) { struct pids_cgroup *pids; pids = css_pids(cset->subsys[pids_cgrp_id]); pids_uncharge(pids, 1); } static void pids_release(struct task_struct *task) { struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id)); pids_uncharge(pids, 1); } static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_subsys_state *css = of_css(of); struct pids_cgroup *pids = css_pids(css); int64_t limit; int err; buf = strstrip(buf); if (!strcmp(buf, PIDS_MAX_STR)) { limit = PIDS_MAX; goto set_limit; } err = kstrtoll(buf, 0, &limit); if (err) return err; if (limit < 0 || limit >= PIDS_MAX) return -EINVAL; set_limit: /* * Limit updates don't need to be mutex'd, since it isn't * critical that any racing fork()s follow the new limit. */ atomic64_set(&pids->limit, limit); return nbytes; } static int pids_max_show(struct seq_file *sf, void *v) { struct cgroup_subsys_state *css = seq_css(sf); struct pids_cgroup *pids = css_pids(css); int64_t limit = atomic64_read(&pids->limit); if (limit >= PIDS_MAX) seq_printf(sf, "%s\n", PIDS_MAX_STR); else seq_printf(sf, "%lld\n", limit); return 0; } static s64 pids_current_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct pids_cgroup *pids = css_pids(css); return atomic64_read(&pids->counter); } static s64 pids_peak_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct pids_cgroup *pids = css_pids(css); return READ_ONCE(pids->watermark); } static int __pids_events_show(struct seq_file *sf, bool local) { struct pids_cgroup *pids = css_pids(seq_css(sf)); enum pidcg_event pe = PIDCG_MAX; atomic64_t *events; if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { pe = PIDCG_FORKFAIL; local = true; } events = local ? pids->events_local : pids->events; seq_printf(sf, "max %lld\n", (s64)atomic64_read(&events[pe])); return 0; } static int pids_events_show(struct seq_file *sf, void *v) { __pids_events_show(sf, false); return 0; } static int pids_events_local_show(struct seq_file *sf, void *v) { __pids_events_show(sf, true); return 0; } static struct cftype pids_files[] = { { .name = "max", .write = pids_max_write, .seq_show = pids_max_show, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .read_s64 = pids_current_read, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, .read_s64 = pids_peak_read, }, { .name = "events", .seq_show = pids_events_show, .file_offset = offsetof(struct pids_cgroup, events_file), .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "events.local", .seq_show = pids_events_local_show, .file_offset = offsetof(struct pids_cgroup, events_local_file), .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; static struct cftype pids_files_legacy[] = { { .name = "max", .write = pids_max_write, .seq_show = pids_max_show, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .read_s64 = pids_current_read, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, .read_s64 = pids_peak_read, }, { .name = "events", .seq_show = pids_events_show, .file_offset = offsetof(struct pids_cgroup, events_file), .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; struct cgroup_subsys pids_cgrp_subsys = { .css_alloc = pids_css_alloc, .css_free = pids_css_free, .can_attach = pids_can_attach, .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, .release = pids_release, .legacy_cftypes = pids_files_legacy, .dfl_cftypes = pids_files, .threaded = true, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PIPE_FS_I_H #define _LINUX_PIPE_FS_I_H #define PIPE_DEF_BUFFERS 16 #define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ #define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */ #define PIPE_BUF_FLAG_WHOLE 0x20 /* read() must return entire buffer or error */ #ifdef CONFIG_WATCH_QUEUE #define PIPE_BUF_FLAG_LOSS 0x40 /* Message loss happened after this buffer */ #endif /** * struct pipe_buffer - a linux kernel pipe buffer * @page: the page containing the data for the pipe buffer * @offset: offset of data inside the @page * @len: length of data inside the @page * @ops: operations associated with this buffer. See @pipe_buf_operations. * @flags: pipe buffer flags. See above. * @private: private data owned by the ops. **/ struct pipe_buffer { struct page *page; unsigned int offset, len; const struct pipe_buf_operations *ops; unsigned int flags; unsigned long private; }; /* * Really only alpha needs 32-bit fields, but * might as well do it for 64-bit architectures * since that's what we've historically done, * and it makes 'head_tail' always be a simple * 'unsigned long'. */ #ifdef CONFIG_64BIT typedef unsigned int pipe_index_t; #else typedef unsigned short pipe_index_t; #endif /* * We have to declare this outside 'struct pipe_inode_info', * but then we can't use 'union pipe_index' for an anonymous * union, so we end up having to duplicate this declaration * below. Annoying. */ union pipe_index { unsigned long head_tail; struct { pipe_index_t head; pipe_index_t tail; }; }; /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption * @head_tail: unsigned long union of @head and @tail * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers * @user: the user who created this pipe * @watch_queue: If this pipe is a watch_queue, this is the stuff for that **/ struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; /* This has to match the 'union pipe_index' above */ union { unsigned long head_tail; struct { pipe_index_t head; pipe_index_t tail; }; }; unsigned int max_usage; unsigned int ring_size; unsigned int nr_accounted; unsigned int readers; unsigned int writers; unsigned int files; unsigned int r_counter; unsigned int w_counter; bool poll_usage; #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif struct page *tmp_page[2]; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; struct user_struct *user; #ifdef CONFIG_WATCH_QUEUE struct watch_queue *watch_queue; #endif }; /* * Note on the nesting of these functions: * * ->confirm() * ->try_steal() * * That is, ->try_steal() must be called on a confirmed buffer. See below for * the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the * pipe and generic variants of these hooks. */ struct pipe_buf_operations { /* * ->confirm() verifies that the data in the pipe buffer is there * and that the contents are good. If the pages in the pipe belong * to a file system, we may need to wait for IO completion in this * hook. Returns 0 for good, or a negative error value in case of * error. If not present all pages are considered good. */ int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *); /* * When the contents of this pipe buffer has been completely * consumed by a reader, ->release() is called. */ void (*release)(struct pipe_inode_info *, struct pipe_buffer *); /* * Attempt to take ownership of the pipe buffer and its contents. * ->try_steal() returns %true for success, in which case the contents * of the pipe (the buf->page) is locked and now completely owned by the * caller. The page may then be transferred to a different mapping, the * most often used case is insertion into different file address space * cache. */ bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *); /* * Get a reference to the pipe buffer. */ bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_has_watch_queue - Check whether the pipe is a watch_queue, * i.e. it was created with O_NOTIFICATION_PIPE * @pipe: The pipe to check * * Return: true if pipe is a watch queue, false otherwise. */ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) { #ifdef CONFIG_WATCH_QUEUE return pipe->watch_queue != NULL; #else return false; #endif } /** * pipe_occupancy - Return number of slots used in the pipe * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) { return (pipe_index_t)(head - tail); } /** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline bool pipe_empty(unsigned int head, unsigned int tail) { return !pipe_occupancy(head, tail); } /** * pipe_full - Return true if the pipe is full * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer * @limit: The maximum amount of slots available. */ static inline bool pipe_full(unsigned int head, unsigned int tail, unsigned int limit) { return pipe_occupancy(head, tail) >= limit; } /** * pipe_is_full - Return true if the pipe is full * @pipe: the pipe */ static inline bool pipe_is_full(const struct pipe_inode_info *pipe) { return pipe_full(pipe->head, pipe->tail, pipe->max_usage); } /** * pipe_is_empty - Return true if the pipe is empty * @pipe: the pipe */ static inline bool pipe_is_empty(const struct pipe_inode_info *pipe) { return pipe_empty(pipe->head, pipe->tail); } /** * pipe_buf_usage - Return how many pipe buffers are in use * @pipe: the pipe */ static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe) { return pipe_occupancy(pipe->head, pipe->tail); } /** * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring * @pipe: The pipe to access * @slot: The slot of interest */ static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, unsigned int slot) { return &pipe->bufs[slot & (pipe->ring_size - 1)]; } /** * pipe_head_buf - Return the pipe buffer at the head of the pipe ring * @pipe: The pipe to access */ static inline struct pipe_buffer *pipe_head_buf(const struct pipe_inode_info *pipe) { return pipe_buf(pipe, pipe->head); } /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Return: %true if the reference was successfully obtained. */ static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return buf->ops->get(pipe, buf); } /** * pipe_buf_release - put a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to */ static inline void pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { const struct pipe_buf_operations *ops = buf->ops; buf->ops = NULL; ops->release(pipe, buf); } /** * pipe_buf_confirm - verify contents of the pipe buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to confirm */ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->confirm) return 0; return buf->ops->confirm(pipe, buf); } /** * pipe_buf_try_steal - attempt to take ownership of a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal */ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->try_steal) return false; return buf->ops->try_steal(pipe, buf); } /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE /* Pipe lock and unlock operations */ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); long pipe_fcntl(struct file *, unsigned int, unsigned int arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); int create_pipe_files(struct file **, int); unsigned int round_pipe_size(unsigned int size); #endif |
| 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 | // 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_linecard { struct list_head list; struct devlink *devlink; unsigned int index; const struct devlink_linecard_ops *ops; void *priv; enum devlink_linecard_state state; struct mutex state_lock; /* Protects state */ const char *type; struct devlink_linecard_type *types; unsigned int types_count; u32 rel_index; }; unsigned int devlink_linecard_index(struct devlink_linecard *linecard) { return linecard->index; } static struct devlink_linecard * devlink_linecard_get_by_index(struct devlink *devlink, unsigned int linecard_index) { struct devlink_linecard *devlink_linecard; list_for_each_entry(devlink_linecard, &devlink->linecard_list, list) { if (devlink_linecard->index == linecard_index) return devlink_linecard; } return NULL; } static bool devlink_linecard_index_exists(struct devlink *devlink, unsigned int linecard_index) { return devlink_linecard_get_by_index(devlink, linecard_index); } static struct devlink_linecard * devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_LINECARD_INDEX]) { u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]); struct devlink_linecard *linecard; linecard = devlink_linecard_get_by_index(devlink, linecard_index); if (!linecard) return ERR_PTR(-ENODEV); return linecard; } return ERR_PTR(-EINVAL); } static struct devlink_linecard * devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_linecard_get_from_attrs(devlink, info->attrs); } struct devlink_linecard_type { const char *type; const void *priv; }; static int devlink_nl_linecard_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_linecard *linecard, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { struct devlink_linecard_type *linecard_type; struct nlattr *attr; void *hdr; int i; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, linecard->index)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_LINECARD_STATE, linecard->state)) goto nla_put_failure; if (linecard->type && nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard->type)) goto nla_put_failure; if (linecard->types_count) { attr = nla_nest_start(msg, DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES); if (!attr) goto nla_put_failure; for (i = 0; i < linecard->types_count; i++) { linecard_type = &linecard->types[i]; if (nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard_type->type)) { nla_nest_cancel(msg, attr); goto nla_put_failure; } } nla_nest_end(msg, attr); } if (devlink_rel_devlink_handle_put(msg, devlink, linecard->rel_index, DEVLINK_ATTR_NESTED_DEVLINK, NULL)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_linecard_notify(struct devlink_linecard *linecard, enum devlink_command cmd) { struct devlink *devlink = linecard->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW && cmd != DEVLINK_CMD_LINECARD_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_linecard_fill(msg, devlink, linecard, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; } devlink_nl_notify_send(devlink, msg); } void devlink_linecards_notify_register(struct devlink *devlink) { struct devlink_linecard *linecard; list_for_each_entry(linecard, &devlink->linecard_list, list) devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); } void devlink_linecards_notify_unregister(struct devlink *devlink) { struct devlink_linecard *linecard; list_for_each_entry_reverse(linecard, &devlink->linecard_list, list) devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); } int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_linecard *linecard; struct sk_buff *msg; int err; linecard = devlink_linecard_get_from_info(devlink, info); if (IS_ERR(linecard)) return PTR_ERR(linecard); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; mutex_lock(&linecard->state_lock); err = devlink_nl_linecard_fill(msg, devlink, linecard, DEVLINK_CMD_LINECARD_NEW, info->snd_portid, info->snd_seq, 0, info->extack); mutex_unlock(&linecard->state_lock); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_linecard_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_linecard *linecard; int idx = 0; int err = 0; list_for_each_entry(linecard, &devlink->linecard_list, list) { if (idx < state->idx) { idx++; continue; } mutex_lock(&linecard->state_lock); err = devlink_nl_linecard_fill(msg, devlink, linecard, DEVLINK_CMD_LINECARD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); mutex_unlock(&linecard->state_lock); if (err) { state->idx = idx; break; } idx++; } return err; } int devlink_nl_linecard_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one); } static struct devlink_linecard_type * devlink_linecard_type_lookup(struct devlink_linecard *linecard, const char *type) { struct devlink_linecard_type *linecard_type; int i; for (i = 0; i < linecard->types_count; i++) { linecard_type = &linecard->types[i]; if (!strcmp(type, linecard_type->type)) return linecard_type; } return NULL; } static int devlink_linecard_type_set(struct devlink_linecard *linecard, const char *type, struct netlink_ext_ack *extack) { const struct devlink_linecard_ops *ops = linecard->ops; struct devlink_linecard_type *linecard_type; int err; mutex_lock(&linecard->state_lock); if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being provisioned"); err = -EBUSY; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned"); err = -EBUSY; goto out; } linecard_type = devlink_linecard_type_lookup(linecard, type); if (!linecard_type) { NL_SET_ERR_MSG(extack, "Unsupported line card type provided"); err = -EINVAL; goto out; } if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED && linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { NL_SET_ERR_MSG(extack, "Line card already provisioned"); err = -EBUSY; /* Check if the line card is provisioned in the same * way the user asks. In case it is, make the operation * to return success. */ if (ops->same_provision && ops->same_provision(linecard, linecard->priv, linecard_type->type, linecard_type->priv)) err = 0; goto out; } linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING; linecard->type = linecard_type->type; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); err = ops->provision(linecard, linecard->priv, linecard_type->type, linecard_type->priv, extack); if (err) { /* Provisioning failed. Assume the linecard is unprovisioned * for future operations. */ mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } return err; out: mutex_unlock(&linecard->state_lock); return err; } static int devlink_linecard_type_unset(struct devlink_linecard *linecard, struct netlink_ext_ack *extack) { int err; mutex_lock(&linecard->state_lock); if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being provisioned"); err = -EBUSY; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned"); err = -EBUSY; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); err = 0; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) { NL_SET_ERR_MSG(extack, "Line card is not provisioned"); err = 0; goto out; } linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); err = linecard->ops->unprovision(linecard, linecard->priv, extack); if (err) { /* Unprovisioning failed. Assume the linecard is unprovisioned * for future operations. */ mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } return err; out: mutex_unlock(&linecard->state_lock); return err; } int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; struct devlink_linecard *linecard; int err; linecard = devlink_linecard_get_from_info(devlink, info); if (IS_ERR(linecard)) return PTR_ERR(linecard); if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) { const char *type; type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]); if (strcmp(type, "")) { err = devlink_linecard_type_set(linecard, type, extack); if (err) return err; } else { err = devlink_linecard_type_unset(linecard, extack); if (err) return err; } } return 0; } static int devlink_linecard_types_init(struct devlink_linecard *linecard) { struct devlink_linecard_type *linecard_type; unsigned int count; int i; count = linecard->ops->types_count(linecard, linecard->priv); linecard->types = kmalloc_array(count, sizeof(*linecard_type), GFP_KERNEL); if (!linecard->types) return -ENOMEM; linecard->types_count = count; for (i = 0; i < count; i++) { linecard_type = &linecard->types[i]; linecard->ops->types_get(linecard, linecard->priv, i, &linecard_type->type, &linecard_type->priv); } return 0; } static void devlink_linecard_types_fini(struct devlink_linecard *linecard) { kfree(linecard->types); } /** * devl_linecard_create - Create devlink linecard * * @devlink: devlink * @linecard_index: driver-specific numerical identifier of the linecard * @ops: linecards ops * @priv: user priv pointer * * Create devlink linecard instance with provided linecard index. * Caller can use any indexing, even hw-related one. * * Return: Line card structure or an ERR_PTR() encoded error code. */ struct devlink_linecard * devl_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv) { struct devlink_linecard *linecard; int err; if (WARN_ON(!ops || !ops->provision || !ops->unprovision || !ops->types_count || !ops->types_get)) return ERR_PTR(-EINVAL); if (devlink_linecard_index_exists(devlink, linecard_index)) return ERR_PTR(-EEXIST); linecard = kzalloc(sizeof(*linecard), GFP_KERNEL); if (!linecard) return ERR_PTR(-ENOMEM); linecard->devlink = devlink; linecard->index = linecard_index; linecard->ops = ops; linecard->priv = priv; linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; mutex_init(&linecard->state_lock); err = devlink_linecard_types_init(linecard); if (err) { mutex_destroy(&linecard->state_lock); kfree(linecard); return ERR_PTR(err); } list_add_tail(&linecard->list, &devlink->linecard_list); devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); return linecard; } EXPORT_SYMBOL_GPL(devl_linecard_create); /** * devl_linecard_destroy - Destroy devlink linecard * * @linecard: devlink linecard */ void devl_linecard_destroy(struct devlink_linecard *linecard) { devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); list_del(&linecard->list); devlink_linecard_types_fini(linecard); mutex_destroy(&linecard->state_lock); kfree(linecard); } EXPORT_SYMBOL_GPL(devl_linecard_destroy); /** * devlink_linecard_provision_set - Set provisioning on linecard * * @linecard: devlink linecard * @type: linecard type * * This is either called directly from the provision() op call or * as a result of the provision() op call asynchronously. */ void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type) { mutex_lock(&linecard->state_lock); WARN_ON(linecard->type && strcmp(linecard->type, type)); linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; linecard->type = type; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_provision_set); /** * devlink_linecard_provision_clear - Clear provisioning on linecard * * @linecard: devlink linecard * * This is either called directly from the unprovision() op call or * as a result of the unprovision() op call asynchronously. */ void devlink_linecard_provision_clear(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear); /** * devlink_linecard_provision_fail - Fail provisioning on linecard * * @linecard: devlink linecard * * This is either called directly from the provision() op call or * as a result of the provision() op call asynchronously. */ void devlink_linecard_provision_fail(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail); /** * devlink_linecard_activate - Set linecard active * * @linecard: devlink linecard */ void devlink_linecard_activate(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED); linecard->state = DEVLINK_LINECARD_STATE_ACTIVE; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_activate); /** * devlink_linecard_deactivate - Set linecard inactive * * @linecard: devlink linecard */ void devlink_linecard_deactivate(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); switch (linecard->state) { case DEVLINK_LINECARD_STATE_ACTIVE: linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); break; case DEVLINK_LINECARD_STATE_UNPROVISIONING: /* Line card is being deactivated as part * of unprovisioning flow. */ break; default: WARN_ON(1); break; } mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_deactivate); static void devlink_linecard_rel_notify_cb(struct devlink *devlink, u32 linecard_index) { struct devlink_linecard *linecard; linecard = devlink_linecard_get_by_index(devlink, linecard_index); if (!linecard) return; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); } static void devlink_linecard_rel_cleanup_cb(struct devlink *devlink, u32 linecard_index, u32 rel_index) { struct devlink_linecard *linecard; linecard = devlink_linecard_get_by_index(devlink, linecard_index); if (linecard && linecard->rel_index == rel_index) linecard->rel_index = 0; } /** * devlink_linecard_nested_dl_set - Attach/detach nested devlink * instance to linecard. * * @linecard: devlink linecard * @nested_devlink: devlink instance to attach or NULL to detach */ int devlink_linecard_nested_dl_set(struct devlink_linecard *linecard, struct devlink *nested_devlink) { return devlink_rel_nested_in_add(&linecard->rel_index, linecard->devlink->index, linecard->index, devlink_linecard_rel_notify_cb, devlink_linecard_rel_cleanup_cb, nested_devlink); } EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set); |
| 360 627 286 287 287 278 277 270 347 627 277 278 279 278 286 286 286 285 10 10 872 1456 872 3 3 3 3 279 280 280 279 279 280 280 278 280 277 279 279 279 280 278 280 279 278 277 278 277 278 277 278 279 141 141 141 141 140 141 141 141 141 141 1 1 2 1 3 3 3 3 3 3 3 287 284 287 286 47 280 279 280 280 279 46 47 47 61 15 47 280 279 277 10 10 10 16 16 280 278 278 280 280 21 258 279 48 239 280 278 280 279 213 212 213 278 50 2 63 15 15 213 213 291 1 1 3 286 287 1 285 1 283 285 286 287 285 285 287 283 10 279 280 279 280 3 256 11 245 198 1 215 214 215 2 17 196 213 213 198 20 213 213 212 197 18 2 33 44 47 11 293 289 1 45 24 228 17 213 172 43 198 16 213 213 198 16 16 292 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) # ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static bool try_release_thread_stack_to_cache(struct vm_struct *vm) { unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm)) return true; } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_stack); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm) { int i; int ret; int nr_charged = 0; BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Reset stack metadata. */ kasan_unpoison_range(s->addr, THREAD_SIZE); stack = kasan_reset_tag(s->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); if (memcg_charge_kernel_stack(s)) { vfree(s->addr); return -ENOMEM; } tsk->stack_vm_area = s; tsk->stack = stack; return 0; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP & ~__GFP_ACCOUNT, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm = find_vm_area(stack); if (memcg_charge_kernel_stack(vm)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } # else /* !CONFIG_VMAP_STACK */ static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } # endif /* CONFIG_VMAP_STACK */ # else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!vma) return NULL; vma_init(vma, mm); return vma; } static void vm_area_init_from(const struct vm_area_struct *src, struct vm_area_struct *dest) { dest->vm_mm = src->vm_mm; dest->vm_ops = src->vm_ops; dest->vm_start = src->vm_start; dest->vm_end = src->vm_end; dest->anon_vma = src->anon_vma; dest->vm_pgoff = src->vm_pgoff; dest->vm_file = src->vm_file; dest->vm_private_data = src->vm_private_data; vm_flags_init(dest, src->vm_flags); memcpy(&dest->vm_page_prot, &src->vm_page_prot, sizeof(dest->vm_page_prot)); /* * src->shared.rb may be modified concurrently when called from * dup_mmap(), but the clone will reinitialize it. */ data_race(memcpy(&dest->shared, &src->shared, sizeof(dest->shared))); memcpy(&dest->vm_userfaultfd_ctx, &src->vm_userfaultfd_ctx, sizeof(dest->vm_userfaultfd_ctx)); #ifdef CONFIG_ANON_VMA_NAME dest->anon_name = src->anon_name; #endif #ifdef CONFIG_SWAP memcpy(&dest->swap_readahead_info, &src->swap_readahead_info, sizeof(dest->swap_readahead_info)); #endif #ifndef CONFIG_MMU dest->vm_region = src->vm_region; #endif #ifdef CONFIG_NUMA dest->vm_policy = src->vm_policy; #endif } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) return NULL; ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); vm_area_init_from(orig, new); vma_lock_init(new, true); INIT_LIST_HEAD(&new->anon_vma_chain); vma_numab_state_init(new); dup_anon_vma_name(orig, new); /* track_pfn_copy() will later take care of copying internal state. */ if (unlikely(new->vm_flags & VM_PFNMAP)) untrack_pfn_clear(new); return new; } void vm_area_free(struct vm_area_struct *vma) { /* The vma should be detached while being destroyed. */ vma_assert_detached(vma); vma_numab_state_free(vma); free_anon_vma_name(vma); kmem_cache_free(vm_area_cachep, vma); } static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm; int i; vm = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && exe_file_deny_write_access(exe_file)) pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); if (mmap_write_lock_killable(oldmm)) return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, mpnt->vm_end, GFP_KERNEL); if (retval) goto loop_out; vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto loop_out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ vma_iter_bulk_store(&vmi, tmp); mm->map_count++; if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (vma_is_shared_maywrite(tmp)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (retval) { mpnt = vma_next(&vmi); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); } else { /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, * stop releasing VMAs that have not been duplicated after this * point. */ if (mpnt) { mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store(&vmi.mas, XA_ZERO_ENTRY); /* Avoid OOM iterating a broken tree */ set_bit(MMF_OOM_SKIP, &mm->flags); } /* * The mm_struct is going to exit, but the locks will be dropped * first. Set the mm_struct as unstable is advisable as it is * not fully initialised. */ set_bit(MMF_UNSTABLE, &mm->flags); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); if (!retval) dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ #ifdef CONFIG_MM_ID static DEFINE_IDA(mm_ida); static inline int mm_alloc_id(struct mm_struct *mm) { int ret; ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL); if (ret < 0) return ret; mm->mm_id = ret; return 0; } static inline void mm_free_id(struct mm_struct *mm) { const mm_id_t id = mm->mm_id; mm->mm_id = MM_ID_DUMMY; if (id == MM_ID_DUMMY) return; if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX)) return; ida_free(&mm_ida, id); } #else /* !CONFIG_MM_ID */ static inline int mm_alloc_id(struct mm_struct *mm) { return 0; } static inline void mm_free_id(struct mm_struct *mm) {} #endif /* CONFIG_MM_ID */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = percpu_counter_sum(&mm->rss_stat[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); mm_free_id(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = memblock_estimated_nr_free_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } void __init fork_init(void) { int i; #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid = -1; tsk->last_mm_cid = -1; tsk->mm_cid_active = 0; tsk->migrate_from_cpu = -1; #endif return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; #endif } static void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); mm_lock_seqcount_init(mm); #ifdef CONFIG_PER_VMA_LOCK rcuwait_init(&mm->vma_writer_wait); #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = mmf_init_flags(current->mm->flags); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (mm_alloc_pgd(mm)) goto fail_nopgd; if (mm_alloc_id(mm)) goto fail_noid; if (init_new_context(p, mm)) goto fail_nocontext; if (mm_alloc_cid(mm, p)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(mm); fail_nocontext: mm_free_id(mm); fail_noid: mm_free_pgd(mm); fail_nopgd: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve it happens before * the new mm is made visible to anyone. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) exe_file = get_mm_exe_file(mm); task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * @task: The task. * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) mmget(mm); task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); static bool may_access_mm(struct mm_struct *mm, struct task_struct *task, unsigned int mode) { if (mm == current->mm) return true; if (ptrace_may_access(task, mode)) return true; if ((mode & PTRACE_MODE_READ) && perfmon_capable()) return true; return false; } struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (!mm) { mm = ERR_PTR(-ESRCH); } else if (!may_access_mm(mm, task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); if (err) uprobe_end_dup_mmap(); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; sched_mm_cid_fork(tsk); return 0; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (no_files) { tsk->files = NULL; return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL); #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the file for the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper doesn't perform checks on @pid which makes it useful for pidfds * created via CLONE_PIDFD where @pid has no task attached when the pidfd and * pidfd file are prepared. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { struct file *pidfd_file; CLASS(get_unused_fd, pidfd)(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfd_file)) return PTR_ERR(pidfd_file); *ret = pidfd_file; return take_fd(pidfd); } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is still in use, without PIDFD_THREAD the * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { bool thread = flags & PIDFD_THREAD; if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { int i; for (i = 0; i < RV_PER_TASK_MONITORS; i++) p->rv[i].da_mon.monitoring = false; } #else #define rv_task_fork(p) do {} while (0) #endif /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ retval = __pidfd_prepare(pid, flags | PIDFD_CLONE, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_sched_cancel_fork: sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .io_thread = 1, .user_worker = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .name = name, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * sys_clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; #ifdef __ARCH_BROKEN_SYS_CLONE3 #warning clone3() entry point is missing, please fix return -ENOSYS; #endif kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { struct kmem_cache_args args = { .use_freeptr_offset = true, .freeptr_offset = offsetof(struct vm_area_struct, vm_freeptr), }; sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); vm_area_cachep = kmem_cache_create("vm_area_struct", sizeof(struct vm_area_struct), &args, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; spin_unlock(&fs->lock); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } |
| 40 40 40 40 40 42 42 40 40 4 2 2 7 7 5 7 7 1009 1009 144 143 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/netprio_cgroup.c Priority Control Group * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/cgroup.h> #include <linux/rcupdate.h> #include <linux/atomic.h> #include <linux/sched/task.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/netprio_cgroup.h> #include <linux/fdtable.h> /* * netprio allocates per-net_device priomap array which is indexed by * css->id. Limiting css ID to 16bits doesn't lose anything. */ #define NETPRIO_ID_MAX USHRT_MAX #define PRIOMAP_MIN_SZ 128 /* * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ static int extend_netdev_table(struct net_device *dev, u32 target_idx) { struct netprio_map *old, *new; size_t new_sz, new_len; /* is the existing priomap large enough? */ old = rtnl_dereference(dev->priomap); if (old && old->priomap_len > target_idx) return 0; /* * Determine the new size. Let's keep it power-of-two. We start * from PRIOMAP_MIN_SZ and double it until it's large enough to * accommodate @target_idx. */ new_sz = PRIOMAP_MIN_SZ; while (true) { new_len = (new_sz - offsetof(struct netprio_map, priomap)) / sizeof(new->priomap[0]); if (new_len > target_idx) break; new_sz *= 2; /* overflowed? */ if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) return -ENOSPC; } /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); if (!new) return -ENOMEM; if (old) memcpy(new->priomap, old->priomap, old->priomap_len * sizeof(old->priomap[0])); new->priomap_len = new_len; /* install the new priomap */ rcu_assign_pointer(dev->priomap, new); if (old) kfree_rcu(old, rcu); return 0; } /** * netprio_prio - return the effective netprio of a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * * Should be called under RCU read or rtnl lock. */ static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; return 0; } /** * netprio_set_prio - set netprio on a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * @prio: prio to set * * Set netprio to @prio on @css-@dev pair. Should be called under rtnl * lock and may fail under memory pressure for non-zero @prio. */ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; int id = css->id; int ret; /* avoid extending priomap for zero writes */ map = rtnl_dereference(dev->priomap); if (!prio && (!map || map->priomap_len <= id)) return 0; ret = extend_netdev_table(dev, id); if (ret) return ret; map = rtnl_dereference(dev->priomap); map->priomap[id] = prio; return 0; } static struct cgroup_subsys_state * cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css; css = kzalloc(sizeof(*css), GFP_KERNEL); if (!css) return ERR_PTR(-ENOMEM); return css; } static int cgrp_css_online(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *parent_css = css->parent; struct net_device *dev; int ret = 0; if (css->id > NETPRIO_ID_MAX) return -ENOSPC; if (!parent_css) return 0; rtnl_lock(); /* * Inherit prios from the parent. As all prios are set during * onlining, there is no need to clear them on offline. */ for_each_netdev(&init_net, dev) { u32 prio = netprio_prio(parent_css, dev); ret = netprio_set_prio(css, dev, prio); if (ret) break; } rtnl_unlock(); return ret; } static void cgrp_css_free(struct cgroup_subsys_state *css) { kfree(css); } static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { return css->id; } static int read_priomap(struct seq_file *sf, void *v) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) seq_printf(sf, "%s %u\n", dev->name, netprio_prio(seq_css(sf), dev)); rcu_read_unlock(); return 0; } static ssize_t write_priomap(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { char devname[IFNAMSIZ + 1]; struct net_device *dev; u32 prio; int ret; if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) return -EINVAL; dev = dev_get_by_name(&init_net, devname); if (!dev) return -ENODEV; rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); rtnl_unlock(); dev_put(dev); return ret ?: nbytes; } static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); return 0; } static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); } } static struct cftype ss_files[] = { { .name = "prioidx", .read_u64 = read_prioidx, }, { .name = "ifpriomap", .seq_show = read_priomap, .write = write_priomap, }, { } /* terminate */ }; struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, .legacy_cftypes = ss_files, }; static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* * Note this is called with rtnl_lock held so we have update side * protection on our rcu assignments */ switch (event) { case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); if (old) kfree_rcu(old, rcu); break; } return NOTIFY_DONE; } static struct notifier_block netprio_device_notifier = { .notifier_call = netprio_device_event }; static int __init init_cgroup_netprio(void) { register_netdevice_notifier(&netprio_device_notifier); return 0; } subsys_initcall(init_cgroup_netprio); |
| 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | // SPDX-License-Identifier: GPL-2.0 /* RTT/RTO calculation. * * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com) * * https://tools.ietf.org/html/rfc6298 * https://tools.ietf.org/html/rfc1122#section-4.2.3.1 * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf */ #include <linux/net.h> #include "ar-internal.h" #define RXRPC_RTO_MAX (120 * USEC_PER_SEC) #define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * USEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ static u32 rxrpc_rto_min_us(struct rxrpc_call *call) { return 200; } static u32 __rxrpc_set_rto(const struct rxrpc_call *call) { return (call->srtt_us >> 3) + call->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) { return clamp(200000, rto + 100000, RXRPC_RTO_MAX); } /* * Called to compute a smoothed rtt estimate. The data fed to this * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88 * piece by Van Jacobson. * NOTE: the next three routines used to be one big routine. * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ static void rxrpc_rtt_estimator(struct rxrpc_call *call, long sample_rtt_us) { long m = sample_rtt_us; /* RTT */ u32 srtt = call->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev * are scaled versions of rtt and mean deviation. * This is designed to be as fast as possible * m stands for "measurement". * * On a 1990 paper the rto value is changed to: * RTO = rtt + 4 * mdev * * Funny. This algorithm seems to be very broken. * These formulae increase RTO, when it should be decreased, increase * too slowly, when it should be increased quickly, decrease too quickly * etc. I guess in BSD RTO takes ONE value, so that it is absolutely * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ if (srtt != 0) { m -= (srtt >> 3); /* m is now error in rtt est */ srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ m -= (call->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain * for mdev in this case (alpha*beta). * Like Eifel it also prevents growth of rto, * but also it limits too fast rto decreases, * happening in pure Eifel. */ if (m > 0) m >>= 3; } else { m -= (call->mdev_us >> 2); /* similar update on mdev */ } call->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ if (call->mdev_us > call->mdev_max_us) { call->mdev_max_us = call->mdev_us; if (call->mdev_max_us > call->rttvar_us) call->rttvar_us = call->mdev_max_us; } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ call->mdev_us = m << 1; /* make sure rto = 3*rtt */ call->rttvar_us = umax(call->mdev_us, rxrpc_rto_min_us(call)); call->mdev_max_us = call->rttvar_us; } call->srtt_us = umax(srtt, 1); } /* * Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ static void rxrpc_set_rto(struct rxrpc_call *call) { u32 rto; /* 1. If rtt variance happened to be less 50msec, it is hallucination. * It cannot be less due to utterly erratic ACK generation made * at least by solaris and freebsd. "Erratic ACKs" has _nothing_ * to do with delayed acks, because at cwnd>2 true delack timeout * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances. */ rto = __rxrpc_set_rto(call); /* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, * all the algo is pure shit and should be replaced * with correct one. It is exactly, which we pretend to do. */ /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ call->rto_us = rxrpc_bound_rto(rto); } static void rxrpc_update_rtt_min(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) { /* Window size 5mins in approx usec (ipv4.sysctl_tcp_min_rtt_wlen) */ u32 wlen_us = 5ULL * NSEC_PER_SEC / 1024; minmax_running_min(&call->min_rtt, wlen_us, resp_time / 1024, (u32)rtt_us ? : jiffies_to_usecs(1)); } static void rxrpc_ack_update_rtt(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) { if (rtt_us < 0) return; /* Update RACK min RTT [RFC8985 6.1 Step 1]. */ rxrpc_update_rtt_min(call, resp_time, rtt_us); rxrpc_rtt_estimator(call, rtt_us); rxrpc_set_rto(call); /* Only reset backoff on valid RTT measurement [RFC6298]. */ call->backoff = 0; } /* * Add RTT information to cache. This is called in softirq mode and has * exclusive access to the call RTT data. */ void rxrpc_call_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { s64 rtt_us; rtt_us = ktime_to_us(ktime_sub(resp_time, send_time)); if (rtt_us < 0) return; rxrpc_ack_update_rtt(call, resp_time, rtt_us); if (call->rtt_count < 3) call->rtt_count++; call->rtt_taken++; WRITE_ONCE(call->peer->recent_srtt_us, call->srtt_us / 8); WRITE_ONCE(call->peer->recent_rto_us, call->rto_us); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, rtt_us, call->srtt_us, call->rto_us); } /* * Get the retransmission timeout to set in nanoseconds, backing it off each * time we retransmit. */ ktime_t rxrpc_get_rto_backoff(struct rxrpc_call *call, bool retrans) { u64 timo_us; u32 backoff = READ_ONCE(call->backoff); timo_us = call->rto_us; timo_us <<= backoff; if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) WRITE_ONCE(call->backoff, backoff + 1); if (timo_us < 1) timo_us = 1; return ns_to_ktime(timo_us * NSEC_PER_USEC); } void rxrpc_call_init_rtt(struct rxrpc_call *call) { call->rtt_last_req = KTIME_MIN; call->rto_us = RXRPC_TIMEOUT_INIT; call->mdev_us = RXRPC_TIMEOUT_INIT; call->backoff = 0; //minmax_reset(&call->rtt_min, rxrpc_jiffies32, ~0U); } |
| 500 487 500 500 17 501 500 501 500 500 17 500 500 499 501 500 500 500 500 501 500 487 501 499 500 500 499 501 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008 IBM Corporation * Author: Mimi Zohar <zohar@us.ibm.com> * * ima_policy.c * - initialize default measure policy rules */ #include <linux/init.h> #include <linux/list.h> #include <linux/kernel_read_file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/magic.h> #include <linux/parser.h> #include <linux/slab.h> #include <linux/rculist.h> #include <linux/seq_file.h> #include <linux/ima.h> #include "ima.h" /* flags definitions */ #define IMA_FUNC 0x0001 #define IMA_MASK 0x0002 #define IMA_FSMAGIC 0x0004 #define IMA_UID 0x0008 #define IMA_FOWNER 0x0010 #define IMA_FSUUID 0x0020 #define IMA_INMASK 0x0040 #define IMA_EUID 0x0080 #define IMA_PCR 0x0100 #define IMA_FSNAME 0x0200 #define IMA_KEYRINGS 0x0400 #define IMA_LABEL 0x0800 #define IMA_VALIDATE_ALGOS 0x1000 #define IMA_GID 0x2000 #define IMA_EGID 0x4000 #define IMA_FGROUP 0x8000 #define UNKNOWN 0 #define MEASURE 0x0001 /* same as IMA_MEASURE */ #define DONT_MEASURE 0x0002 #define APPRAISE 0x0004 /* same as IMA_APPRAISE */ #define DONT_APPRAISE 0x0008 #define AUDIT 0x0040 #define HASH 0x0100 #define DONT_HASH 0x0200 #define INVALID_PCR(a) (((a) < 0) || \ (a) >= (sizeof_field(struct ima_iint_cache, measured_pcrs) * 8)) int ima_policy_flag; static int temp_ima_appraise; static int build_ima_appraise __ro_after_init; atomic_t ima_setxattr_allowed_hash_algorithms; #define MAX_LSM_RULES 6 enum lsm_rule_types { LSM_OBJ_USER, LSM_OBJ_ROLE, LSM_OBJ_TYPE, LSM_SUBJ_USER, LSM_SUBJ_ROLE, LSM_SUBJ_TYPE }; enum policy_types { ORIGINAL_TCB = 1, DEFAULT_TCB }; enum policy_rule_list { IMA_DEFAULT_POLICY = 1, IMA_CUSTOM_POLICY }; struct ima_rule_opt_list { size_t count; char *items[] __counted_by(count); }; /* * These comparators are needed nowhere outside of ima so just define them here. * This pattern should hopefully never be needed outside of ima. */ static inline bool vfsuid_gt_kuid(vfsuid_t vfsuid, kuid_t kuid) { return __vfsuid_val(vfsuid) > __kuid_val(kuid); } static inline bool vfsgid_gt_kgid(vfsgid_t vfsgid, kgid_t kgid) { return __vfsgid_val(vfsgid) > __kgid_val(kgid); } static inline bool vfsuid_lt_kuid(vfsuid_t vfsuid, kuid_t kuid) { return __vfsuid_val(vfsuid) < __kuid_val(kuid); } static inline bool vfsgid_lt_kgid(vfsgid_t vfsgid, kgid_t kgid) { return __vfsgid_val(vfsgid) < __kgid_val(kgid); } struct ima_rule_entry { struct list_head list; int action; unsigned int flags; enum ima_hooks func; int mask; unsigned long fsmagic; uuid_t fsuuid; kuid_t uid; kgid_t gid; kuid_t fowner; kgid_t fgroup; bool (*uid_op)(kuid_t cred_uid, kuid_t rule_uid); /* Handlers for operators */ bool (*gid_op)(kgid_t cred_gid, kgid_t rule_gid); bool (*fowner_op)(vfsuid_t vfsuid, kuid_t rule_uid); /* vfsuid_eq_kuid(), vfsuid_gt_kuid(), vfsuid_lt_kuid() */ bool (*fgroup_op)(vfsgid_t vfsgid, kgid_t rule_gid); /* vfsgid_eq_kgid(), vfsgid_gt_kgid(), vfsgid_lt_kgid() */ int pcr; unsigned int allowed_algos; /* bitfield of allowed hash algorithms */ struct { void *rule; /* LSM file metadata specific */ char *args_p; /* audit value */ int type; /* audit type */ } lsm[MAX_LSM_RULES]; char *fsname; struct ima_rule_opt_list *keyrings; /* Measure keys added to these keyrings */ struct ima_rule_opt_list *label; /* Measure data grouped under this label */ struct ima_template_desc *template; }; /* * sanity check in case the kernels gains more hash algorithms that can * fit in an unsigned int */ static_assert( 8 * sizeof(unsigned int) >= HASH_ALGO__LAST, "The bitfield allowed_algos in ima_rule_entry is too small to contain all the supported hash algorithms, consider using a bigger type"); /* * Without LSM specific knowledge, the default policy can only be * written in terms of .action, .func, .mask, .fsmagic, .uid, .gid, * .fowner, and .fgroup */ /* * The minimum rule set to allow for full TCB coverage. Measures all files * opened or mmap for exec and everything read by root. Dangerous because * normal users can easily run the machine out of memory simply building * and running executables. */ static struct ima_rule_entry dont_measure_rules[] __ro_after_init = { {.action = DONT_MEASURE, .fsmagic = PROC_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = SYSFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = DEBUGFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = TMPFS_MAGIC, .func = FILE_CHECK, .flags = IMA_FSMAGIC | IMA_FUNC}, {.action = DONT_MEASURE, .fsmagic = DEVPTS_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = BINFMTFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = SECURITYFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = SELINUX_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = SMACK_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = CGROUP_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC} }; static struct ima_rule_entry original_measurement_rules[] __ro_after_init = { {.action = MEASURE, .func = MMAP_CHECK, .mask = MAY_EXEC, .flags = IMA_FUNC | IMA_MASK}, {.action = MEASURE, .func = BPRM_CHECK, .mask = MAY_EXEC, .flags = IMA_FUNC | IMA_MASK}, {.action = MEASURE, .func = FILE_CHECK, .mask = MAY_READ, .uid = GLOBAL_ROOT_UID, .uid_op = &uid_eq, .flags = IMA_FUNC | IMA_MASK | IMA_UID}, {.action = MEASURE, .func = MODULE_CHECK, .flags = IMA_FUNC}, {.action = MEASURE, .func = FIRMWARE_CHECK, .flags = IMA_FUNC}, }; static struct ima_rule_entry default_measurement_rules[] __ro_after_init = { {.action = MEASURE, .func = MMAP_CHECK, .mask = MAY_EXEC, .flags = IMA_FUNC | IMA_MASK}, {.action = MEASURE, .func = BPRM_CHECK, .mask = MAY_EXEC, .flags = IMA_FUNC | IMA_MASK}, {.action = MEASURE, .func = FILE_CHECK, .mask = MAY_READ, .uid = GLOBAL_ROOT_UID, .uid_op = &uid_eq, .flags = IMA_FUNC | IMA_INMASK | IMA_EUID}, {.action = MEASURE, .func = FILE_CHECK, .mask = MAY_READ, .uid = GLOBAL_ROOT_UID, .uid_op = &uid_eq, .flags = IMA_FUNC | IMA_INMASK | IMA_UID}, {.action = MEASURE, .func = MODULE_CHECK, .flags = IMA_FUNC}, {.action = MEASURE, .func = FIRMWARE_CHECK, .flags = IMA_FUNC}, {.action = MEASURE, .func = POLICY_CHECK, .flags = IMA_FUNC}, }; static struct ima_rule_entry default_appraise_rules[] __ro_after_init = { {.action = DONT_APPRAISE, .fsmagic = PROC_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = SYSFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = DEBUGFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = TMPFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = RAMFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = DEVPTS_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = BINFMTFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = SECURITYFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = SELINUX_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = SMACK_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, #ifdef CONFIG_IMA_WRITE_POLICY {.action = APPRAISE, .func = POLICY_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, #endif #ifndef CONFIG_IMA_APPRAISE_SIGNED_INIT {.action = APPRAISE, .fowner = GLOBAL_ROOT_UID, .fowner_op = &vfsuid_eq_kuid, .flags = IMA_FOWNER}, #else /* force signature */ {.action = APPRAISE, .fowner = GLOBAL_ROOT_UID, .fowner_op = &vfsuid_eq_kuid, .flags = IMA_FOWNER | IMA_DIGSIG_REQUIRED}, #endif }; static struct ima_rule_entry build_appraise_rules[] __ro_after_init = { #ifdef CONFIG_IMA_APPRAISE_REQUIRE_MODULE_SIGS {.action = APPRAISE, .func = MODULE_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, #endif #ifdef CONFIG_IMA_APPRAISE_REQUIRE_FIRMWARE_SIGS {.action = APPRAISE, .func = FIRMWARE_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, #endif #ifdef CONFIG_IMA_APPRAISE_REQUIRE_KEXEC_SIGS {.action = APPRAISE, .func = KEXEC_KERNEL_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, #endif #ifdef CONFIG_IMA_APPRAISE_REQUIRE_POLICY_SIGS {.action = APPRAISE, .func = POLICY_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, #endif }; static struct ima_rule_entry secure_boot_rules[] __ro_after_init = { {.action = APPRAISE, .func = MODULE_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, {.action = APPRAISE, .func = FIRMWARE_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, {.action = APPRAISE, .func = KEXEC_KERNEL_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, {.action = APPRAISE, .func = POLICY_CHECK, .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, }; static struct ima_rule_entry critical_data_rules[] __ro_after_init = { {.action = MEASURE, .func = CRITICAL_DATA, .flags = IMA_FUNC}, }; /* An array of architecture specific rules */ static struct ima_rule_entry *arch_policy_entry __ro_after_init; static LIST_HEAD(ima_default_rules); static LIST_HEAD(ima_policy_rules); static LIST_HEAD(ima_temp_rules); static struct list_head __rcu *ima_rules = (struct list_head __rcu *)(&ima_default_rules); static int ima_policy __initdata; static int __init default_measure_policy_setup(char *str) { if (ima_policy) return 1; ima_policy = ORIGINAL_TCB; return 1; } __setup("ima_tcb", default_measure_policy_setup); static bool ima_use_appraise_tcb __initdata; static bool ima_use_secure_boot __initdata; static bool ima_use_critical_data __initdata; static bool ima_fail_unverifiable_sigs __ro_after_init; static int __init policy_setup(char *str) { char *p; while ((p = strsep(&str, " |\n")) != NULL) { if (*p == ' ') continue; if ((strcmp(p, "tcb") == 0) && !ima_policy) ima_policy = DEFAULT_TCB; else if (strcmp(p, "appraise_tcb") == 0) ima_use_appraise_tcb = true; else if (strcmp(p, "secure_boot") == 0) ima_use_secure_boot = true; else if (strcmp(p, "critical_data") == 0) ima_use_critical_data = true; else if (strcmp(p, "fail_securely") == 0) ima_fail_unverifiable_sigs = true; else pr_err("policy \"%s\" not found", p); } return 1; } __setup("ima_policy=", policy_setup); static int __init default_appraise_policy_setup(char *str) { ima_use_appraise_tcb = true; return 1; } __setup("ima_appraise_tcb", default_appraise_policy_setup); static struct ima_rule_opt_list *ima_alloc_rule_opt_list(const substring_t *src) { struct ima_rule_opt_list *opt_list; size_t count = 0; char *src_copy; char *cur, *next; size_t i; src_copy = match_strdup(src); if (!src_copy) return ERR_PTR(-ENOMEM); next = src_copy; while ((cur = strsep(&next, "|"))) { /* Don't accept an empty list item */ if (!(*cur)) { kfree(src_copy); return ERR_PTR(-EINVAL); } count++; } /* Don't accept an empty list */ if (!count) { kfree(src_copy); return ERR_PTR(-EINVAL); } opt_list = kzalloc(struct_size(opt_list, items, count), GFP_KERNEL); if (!opt_list) { kfree(src_copy); return ERR_PTR(-ENOMEM); } opt_list->count = count; /* * strsep() has already replaced all instances of '|' with '\0', * leaving a byte sequence of NUL-terminated strings. Reference each * string with the array of items. * * IMPORTANT: Ownership of the allocated buffer is transferred from * src_copy to the first element in the items array. To free the * buffer, kfree() must only be called on the first element of the * array. */ for (i = 0, cur = src_copy; i < count; i++) { opt_list->items[i] = cur; cur = strchr(cur, '\0') + 1; } return opt_list; } static void ima_free_rule_opt_list(struct ima_rule_opt_list *opt_list) { if (!opt_list) return; if (opt_list->count) { kfree(opt_list->items[0]); opt_list->count = 0; } kfree(opt_list); } static void ima_lsm_free_rule(struct ima_rule_entry *entry) { int i; for (i = 0; i < MAX_LSM_RULES; i++) { ima_filter_rule_free(entry->lsm[i].rule); kfree(entry->lsm[i].args_p); } } static void ima_free_rule(struct ima_rule_entry *entry) { if (!entry) return; /* * entry->template->fields may be allocated in ima_parse_rule() but that * reference is owned by the corresponding ima_template_desc element in * the defined_templates list and cannot be freed here */ kfree(entry->fsname); ima_free_rule_opt_list(entry->keyrings); ima_lsm_free_rule(entry); kfree(entry); } static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry, gfp_t gfp) { struct ima_rule_entry *nentry; int i; /* * Immutable elements are copied over as pointers and data; only * lsm rules can change */ nentry = kmemdup(entry, sizeof(*nentry), gfp); if (!nentry) return NULL; memset(nentry->lsm, 0, sizeof_field(struct ima_rule_entry, lsm)); for (i = 0; i < MAX_LSM_RULES; i++) { if (!entry->lsm[i].args_p) continue; nentry->lsm[i].type = entry->lsm[i].type; nentry->lsm[i].args_p = entry->lsm[i].args_p; ima_filter_rule_init(nentry->lsm[i].type, Audit_equal, nentry->lsm[i].args_p, &nentry->lsm[i].rule, gfp); if (!nentry->lsm[i].rule) pr_warn("rule for LSM \'%s\' is undefined\n", nentry->lsm[i].args_p); } return nentry; } static int ima_lsm_update_rule(struct ima_rule_entry *entry) { int i; struct ima_rule_entry *nentry; nentry = ima_lsm_copy_rule(entry, GFP_KERNEL); if (!nentry) return -ENOMEM; list_replace_rcu(&entry->list, &nentry->list); synchronize_rcu(); /* * ima_lsm_copy_rule() shallow copied all references, except for the * LSM references, from entry to nentry so we only want to free the LSM * references and the entry itself. All other memory references will now * be owned by nentry. */ for (i = 0; i < MAX_LSM_RULES; i++) ima_filter_rule_free(entry->lsm[i].rule); kfree(entry); return 0; } static bool ima_rule_contains_lsm_cond(struct ima_rule_entry *entry) { int i; for (i = 0; i < MAX_LSM_RULES; i++) if (entry->lsm[i].args_p) return true; return false; } /* * The LSM policy can be reloaded, leaving the IMA LSM based rules referring * to the old, stale LSM policy. Update the IMA LSM based rules to reflect * the reloaded LSM policy. */ static void ima_lsm_update_rules(void) { struct ima_rule_entry *entry, *e; int result; list_for_each_entry_safe(entry, e, &ima_policy_rules, list) { if (!ima_rule_contains_lsm_cond(entry)) continue; result = ima_lsm_update_rule(entry); if (result) { pr_err("lsm rule update error %d\n", result); return; } } } int ima_lsm_policy_change(struct notifier_block *nb, unsigned long event, void *lsm_data) { if (event != LSM_POLICY_CHANGE) return NOTIFY_DONE; ima_lsm_update_rules(); return NOTIFY_OK; } /** * ima_match_rule_data - determine whether func_data matches the policy rule * @rule: a pointer to a rule * @func_data: data to match against the measure rule data * @cred: a pointer to a credentials structure for user validation * * Returns true if func_data matches one in the rule, false otherwise. */ static bool ima_match_rule_data(struct ima_rule_entry *rule, const char *func_data, const struct cred *cred) { const struct ima_rule_opt_list *opt_list = NULL; bool matched = false; size_t i; if ((rule->flags & IMA_UID) && !rule->uid_op(cred->uid, rule->uid)) return false; switch (rule->func) { case KEY_CHECK: if (!rule->keyrings) return true; opt_list = rule->keyrings; break; case CRITICAL_DATA: if (!rule->label) return true; opt_list = rule->label; break; default: return false; } if (!func_data) return false; for (i = 0; i < opt_list->count; i++) { if (!strcmp(opt_list->items[i], func_data)) { matched = true; break; } } return matched; } /** * ima_match_rules - determine whether an inode matches the policy rule. * @rule: a pointer to a rule * @idmap: idmap of the mount the inode was found from * @inode: a pointer to an inode * @cred: a pointer to a credentials structure for user validation * @prop: LSM properties of the task to be validated * @func: LIM hook identifier * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC) * @func_data: func specific data, may be NULL * * Returns true on rule match, false on failure. */ static bool ima_match_rules(struct ima_rule_entry *rule, struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, struct lsm_prop *prop, enum ima_hooks func, int mask, const char *func_data) { int i; bool result = false; struct ima_rule_entry *lsm_rule = rule; bool rule_reinitialized = false; if ((rule->flags & IMA_FUNC) && (rule->func != func && func != POST_SETATTR)) return false; switch (func) { case KEY_CHECK: case CRITICAL_DATA: return ((rule->func == func) && ima_match_rule_data(rule, func_data, cred)); default: break; } if ((rule->flags & IMA_MASK) && (rule->mask != mask && func != POST_SETATTR)) return false; if ((rule->flags & IMA_INMASK) && (!(rule->mask & mask) && func != POST_SETATTR)) return false; if ((rule->flags & IMA_FSMAGIC) && rule->fsmagic != inode->i_sb->s_magic) return false; if ((rule->flags & IMA_FSNAME) && strcmp(rule->fsname, inode->i_sb->s_type->name)) return false; if ((rule->flags & IMA_FSUUID) && !uuid_equal(&rule->fsuuid, &inode->i_sb->s_uuid)) return false; if ((rule->flags & IMA_UID) && !rule->uid_op(cred->uid, rule->uid)) return false; if (rule->flags & IMA_EUID) { if (has_capability_noaudit(current, CAP_SETUID)) { if (!rule->uid_op(cred->euid, rule->uid) && !rule->uid_op(cred->suid, rule->uid) && !rule->uid_op(cred->uid, rule->uid)) return false; } else if (!rule->uid_op(cred->euid, rule->uid)) return false; } if ((rule->flags & IMA_GID) && !rule->gid_op(cred->gid, rule->gid)) return false; if (rule->flags & IMA_EGID) { if (has_capability_noaudit(current, CAP_SETGID)) { if (!rule->gid_op(cred->egid, rule->gid) && !rule->gid_op(cred->sgid, rule->gid) && !rule->gid_op(cred->gid, rule->gid)) return false; } else if (!rule->gid_op(cred->egid, rule->gid)) return false; } if ((rule->flags & IMA_FOWNER) && !rule->fowner_op(i_uid_into_vfsuid(idmap, inode), rule->fowner)) return false; if ((rule->flags & IMA_FGROUP) && !rule->fgroup_op(i_gid_into_vfsgid(idmap, inode), rule->fgroup)) return false; for (i = 0; i < MAX_LSM_RULES; i++) { int rc = 0; struct lsm_prop inode_prop = { }; if (!lsm_rule->lsm[i].rule) { if (!lsm_rule->lsm[i].args_p) continue; else return false; } retry: switch (i) { case LSM_OBJ_USER: case LSM_OBJ_ROLE: case LSM_OBJ_TYPE: security_inode_getlsmprop(inode, &inode_prop); rc = ima_filter_rule_match(&inode_prop, lsm_rule->lsm[i].type, Audit_equal, lsm_rule->lsm[i].rule); break; case LSM_SUBJ_USER: case LSM_SUBJ_ROLE: case LSM_SUBJ_TYPE: rc = ima_filter_rule_match(prop, lsm_rule->lsm[i].type, Audit_equal, lsm_rule->lsm[i].rule); break; default: break; } if (rc == -ESTALE && !rule_reinitialized) { lsm_rule = ima_lsm_copy_rule(rule, GFP_ATOMIC); if (lsm_rule) { rule_reinitialized = true; goto retry; } } if (!rc) { result = false; goto out; } } result = true; out: if (rule_reinitialized) { for (i = 0; i < MAX_LSM_RULES; i++) ima_filter_rule_free(lsm_rule->lsm[i].rule); kfree(lsm_rule); } return result; } /* * In addition to knowing that we need to appraise the file in general, * we need to differentiate between calling hooks, for hook specific rules. */ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) { if (!(rule->flags & IMA_FUNC)) return IMA_FILE_APPRAISE; switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: return IMA_MMAP_APPRAISE; case BPRM_CHECK: return IMA_BPRM_APPRAISE; case CREDS_CHECK: return IMA_CREDS_APPRAISE; case FILE_CHECK: case POST_SETATTR: return IMA_FILE_APPRAISE; case MODULE_CHECK ... MAX_CHECK - 1: default: return IMA_READ_APPRAISE; } } /** * ima_match_policy - decision based on LSM and other conditions * @idmap: idmap of the mount the inode was found from * @inode: pointer to an inode for which the policy decision is being made * @cred: pointer to a credentials structure for which the policy decision is * being made * @prop: LSM properties of the task to be validated * @func: IMA hook identifier * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC) * @flags: IMA actions to consider (e.g. IMA_MEASURE | IMA_APPRAISE) * @pcr: set the pcr to extend * @template_desc: the template that should be used for this rule * @func_data: func specific data, may be NULL * @allowed_algos: allowlist of hash algorithms for the IMA xattr * * Measure decision based on func/mask/fsmagic and LSM(subj/obj/type) * conditions. * * Since the IMA policy may be updated multiple times we need to lock the * list when walking it. Reads are many orders of magnitude more numerous * than writes so ima_match_policy() is classical RCU candidate. */ int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, struct lsm_prop *prop, enum ima_hooks func, int mask, int flags, int *pcr, struct ima_template_desc **template_desc, const char *func_data, unsigned int *allowed_algos) { struct ima_rule_entry *entry; int action = 0, actmask = flags | (flags << 1); struct list_head *ima_rules_tmp; if (template_desc && !*template_desc) *template_desc = ima_template_desc_current(); rcu_read_lock(); ima_rules_tmp = rcu_dereference(ima_rules); list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!(entry->action & actmask)) continue; if (!ima_match_rules(entry, idmap, inode, cred, prop, func, mask, func_data)) continue; action |= entry->flags & IMA_NONACTION_FLAGS; action |= entry->action & IMA_DO_MASK; if (entry->action & IMA_APPRAISE) { action |= get_subaction(entry, func); action &= ~IMA_HASH; if (ima_fail_unverifiable_sigs) action |= IMA_FAIL_UNVERIFIABLE_SIGS; if (allowed_algos && entry->flags & IMA_VALIDATE_ALGOS) *allowed_algos = entry->allowed_algos; } if (entry->action & IMA_DO_MASK) actmask &= ~(entry->action | entry->action << 1); else actmask &= ~(entry->action | entry->action >> 1); if ((pcr) && (entry->flags & IMA_PCR)) *pcr = entry->pcr; if (template_desc && entry->template) *template_desc = entry->template; if (!actmask) break; } rcu_read_unlock(); return action; } /** * ima_update_policy_flags() - Update global IMA variables * * Update ima_policy_flag and ima_setxattr_allowed_hash_algorithms * based on the currently loaded policy. * * With ima_policy_flag, the decision to short circuit out of a function * or not call the function in the first place can be made earlier. * * With ima_setxattr_allowed_hash_algorithms, the policy can restrict the * set of hash algorithms accepted when updating the security.ima xattr of * a file. * * Context: called after a policy update and at system initialization. */ void ima_update_policy_flags(void) { struct ima_rule_entry *entry; int new_policy_flag = 0; struct list_head *ima_rules_tmp; rcu_read_lock(); ima_rules_tmp = rcu_dereference(ima_rules); list_for_each_entry_rcu(entry, ima_rules_tmp, list) { /* * SETXATTR_CHECK rules do not implement a full policy check * because rule checking would probably have an important * performance impact on setxattr(). As a consequence, only one * SETXATTR_CHECK can be active at a given time. * Because we want to preserve that property, we set out to use * atomic_cmpxchg. Either: * - the atomic was non-zero: a setxattr hash policy is * already enforced, we do nothing * - the atomic was zero: no setxattr policy was set, enable * the setxattr hash policy */ if (entry->func == SETXATTR_CHECK) { atomic_cmpxchg(&ima_setxattr_allowed_hash_algorithms, 0, entry->allowed_algos); /* SETXATTR_CHECK doesn't impact ima_policy_flag */ continue; } if (entry->action & IMA_DO_MASK) new_policy_flag |= entry->action; } rcu_read_unlock(); ima_appraise |= (build_ima_appraise | temp_ima_appraise); if (!ima_appraise) new_policy_flag &= ~IMA_APPRAISE; ima_policy_flag = new_policy_flag; } static int ima_appraise_flag(enum ima_hooks func) { if (func == MODULE_CHECK) return IMA_APPRAISE_MODULES; else if (func == FIRMWARE_CHECK) return IMA_APPRAISE_FIRMWARE; else if (func == POLICY_CHECK) return IMA_APPRAISE_POLICY; else if (func == KEXEC_KERNEL_CHECK) return IMA_APPRAISE_KEXEC; return 0; } static void add_rules(struct ima_rule_entry *entries, int count, enum policy_rule_list policy_rule) { int i = 0; for (i = 0; i < count; i++) { struct ima_rule_entry *entry; if (policy_rule & IMA_DEFAULT_POLICY) list_add_tail(&entries[i].list, &ima_default_rules); if (policy_rule & IMA_CUSTOM_POLICY) { entry = kmemdup(&entries[i], sizeof(*entry), GFP_KERNEL); if (!entry) continue; list_add_tail(&entry->list, &ima_policy_rules); } if (entries[i].action == APPRAISE) { if (entries != build_appraise_rules) temp_ima_appraise |= ima_appraise_flag(entries[i].func); else build_ima_appraise |= ima_appraise_flag(entries[i].func); } } } static int ima_parse_rule(char *rule, struct ima_rule_entry *entry); static int __init ima_init_arch_policy(void) { const char * const *arch_rules; const char * const *rules; int arch_entries = 0; int i = 0; arch_rules = arch_get_ima_policy(); if (!arch_rules) return arch_entries; /* Get number of rules */ for (rules = arch_rules; *rules != NULL; rules++) arch_entries++; arch_policy_entry = kcalloc(arch_entries + 1, sizeof(*arch_policy_entry), GFP_KERNEL); if (!arch_policy_entry) return 0; /* Convert each policy string rules to struct ima_rule_entry format */ for (rules = arch_rules, i = 0; *rules != NULL; rules++) { char rule[255]; int result; result = strscpy(rule, *rules, sizeof(rule)); INIT_LIST_HEAD(&arch_policy_entry[i].list); result = ima_parse_rule(rule, &arch_policy_entry[i]); if (result) { pr_warn("Skipping unknown architecture policy rule: %s\n", rule); memset(&arch_policy_entry[i], 0, sizeof(*arch_policy_entry)); continue; } i++; } return i; } /** * ima_init_policy - initialize the default measure rules. * * ima_rules points to either the ima_default_rules or the new ima_policy_rules. */ void __init ima_init_policy(void) { int build_appraise_entries, arch_entries; /* if !ima_policy, we load NO default rules */ if (ima_policy) add_rules(dont_measure_rules, ARRAY_SIZE(dont_measure_rules), IMA_DEFAULT_POLICY); switch (ima_policy) { case ORIGINAL_TCB: add_rules(original_measurement_rules, ARRAY_SIZE(original_measurement_rules), IMA_DEFAULT_POLICY); break; case DEFAULT_TCB: add_rules(default_measurement_rules, ARRAY_SIZE(default_measurement_rules), IMA_DEFAULT_POLICY); break; default: break; } /* * Based on runtime secure boot flags, insert arch specific measurement * and appraise rules requiring file signatures for both the initial * and custom policies, prior to other appraise rules. * (Highest priority) */ arch_entries = ima_init_arch_policy(); if (!arch_entries) pr_info("No architecture policies found\n"); else add_rules(arch_policy_entry, arch_entries, IMA_DEFAULT_POLICY | IMA_CUSTOM_POLICY); /* * Insert the builtin "secure_boot" policy rules requiring file * signatures, prior to other appraise rules. */ if (ima_use_secure_boot) add_rules(secure_boot_rules, ARRAY_SIZE(secure_boot_rules), IMA_DEFAULT_POLICY); /* * Insert the build time appraise rules requiring file signatures * for both the initial and custom policies, prior to other appraise * rules. As the secure boot rules includes all of the build time * rules, include either one or the other set of rules, but not both. */ build_appraise_entries = ARRAY_SIZE(build_appraise_rules); if (build_appraise_entries) { if (ima_use_secure_boot) add_rules(build_appraise_rules, build_appraise_entries, IMA_CUSTOM_POLICY); else add_rules(build_appraise_rules, build_appraise_entries, IMA_DEFAULT_POLICY | IMA_CUSTOM_POLICY); } if (ima_use_appraise_tcb) add_rules(default_appraise_rules, ARRAY_SIZE(default_appraise_rules), IMA_DEFAULT_POLICY); if (ima_use_critical_data) add_rules(critical_data_rules, ARRAY_SIZE(critical_data_rules), IMA_DEFAULT_POLICY); atomic_set(&ima_setxattr_allowed_hash_algorithms, 0); ima_update_policy_flags(); } /* Make sure we have a valid policy, at least containing some rules. */ int ima_check_policy(void) { if (list_empty(&ima_temp_rules)) return -EINVAL; return 0; } /** * ima_update_policy - update default_rules with new measure rules * * Called on file .release to update the default rules with a complete new * policy. What we do here is to splice ima_policy_rules and ima_temp_rules so * they make a queue. The policy may be updated multiple times and this is the * RCU updater. * * Policy rules are never deleted so ima_policy_flag gets zeroed only once when * we switch from the default policy to user defined. */ void ima_update_policy(void) { struct list_head *policy = &ima_policy_rules; list_splice_tail_init_rcu(&ima_temp_rules, policy, synchronize_rcu); if (ima_rules != (struct list_head __rcu *)policy) { ima_policy_flag = 0; rcu_assign_pointer(ima_rules, policy); /* * IMA architecture specific policy rules are specified * as strings and converted to an array of ima_entry_rules * on boot. After loading a custom policy, free the * architecture specific rules stored as an array. */ kfree(arch_policy_entry); } ima_update_policy_flags(); /* Custom IMA policy has been loaded */ ima_process_queued_keys(); } /* Keep the enumeration in sync with the policy_tokens! */ enum policy_opt { Opt_measure, Opt_dont_measure, Opt_appraise, Opt_dont_appraise, Opt_audit, Opt_hash, Opt_dont_hash, Opt_obj_user, Opt_obj_role, Opt_obj_type, Opt_subj_user, Opt_subj_role, Opt_subj_type, Opt_func, Opt_mask, Opt_fsmagic, Opt_fsname, Opt_fsuuid, Opt_uid_eq, Opt_euid_eq, Opt_gid_eq, Opt_egid_eq, Opt_fowner_eq, Opt_fgroup_eq, Opt_uid_gt, Opt_euid_gt, Opt_gid_gt, Opt_egid_gt, Opt_fowner_gt, Opt_fgroup_gt, Opt_uid_lt, Opt_euid_lt, Opt_gid_lt, Opt_egid_lt, Opt_fowner_lt, Opt_fgroup_lt, Opt_digest_type, Opt_appraise_type, Opt_appraise_flag, Opt_appraise_algos, Opt_permit_directio, Opt_pcr, Opt_template, Opt_keyrings, Opt_label, Opt_err }; static const match_table_t policy_tokens = { {Opt_measure, "measure"}, {Opt_dont_measure, "dont_measure"}, {Opt_appraise, "appraise"}, {Opt_dont_appraise, "dont_appraise"}, {Opt_audit, "audit"}, {Opt_hash, "hash"}, {Opt_dont_hash, "dont_hash"}, {Opt_obj_user, "obj_user=%s"}, {Opt_obj_role, "obj_role=%s"}, {Opt_obj_type, "obj_type=%s"}, {Opt_subj_user, "subj_user=%s"}, {Opt_subj_role, "subj_role=%s"}, {Opt_subj_type, "subj_type=%s"}, {Opt_func, "func=%s"}, {Opt_mask, "mask=%s"}, {Opt_fsmagic, "fsmagic=%s"}, {Opt_fsname, "fsname=%s"}, {Opt_fsuuid, "fsuuid=%s"}, {Opt_uid_eq, "uid=%s"}, {Opt_euid_eq, "euid=%s"}, {Opt_gid_eq, "gid=%s"}, {Opt_egid_eq, "egid=%s"}, {Opt_fowner_eq, "fowner=%s"}, {Opt_fgroup_eq, "fgroup=%s"}, {Opt_uid_gt, "uid>%s"}, {Opt_euid_gt, "euid>%s"}, {Opt_gid_gt, "gid>%s"}, {Opt_egid_gt, "egid>%s"}, {Opt_fowner_gt, "fowner>%s"}, {Opt_fgroup_gt, "fgroup>%s"}, {Opt_uid_lt, "uid<%s"}, {Opt_euid_lt, "euid<%s"}, {Opt_gid_lt, "gid<%s"}, {Opt_egid_lt, "egid<%s"}, {Opt_fowner_lt, "fowner<%s"}, {Opt_fgroup_lt, "fgroup<%s"}, {Opt_digest_type, "digest_type=%s"}, {Opt_appraise_type, "appraise_type=%s"}, {Opt_appraise_flag, "appraise_flag=%s"}, {Opt_appraise_algos, "appraise_algos=%s"}, {Opt_permit_directio, "permit_directio"}, {Opt_pcr, "pcr=%s"}, {Opt_template, "template=%s"}, {Opt_keyrings, "keyrings=%s"}, {Opt_label, "label=%s"}, {Opt_err, NULL} }; static int ima_lsm_rule_init(struct ima_rule_entry *entry, substring_t *args, int lsm_rule, int audit_type) { int result; if (entry->lsm[lsm_rule].rule) return -EINVAL; entry->lsm[lsm_rule].args_p = match_strdup(args); if (!entry->lsm[lsm_rule].args_p) return -ENOMEM; entry->lsm[lsm_rule].type = audit_type; result = ima_filter_rule_init(entry->lsm[lsm_rule].type, Audit_equal, entry->lsm[lsm_rule].args_p, &entry->lsm[lsm_rule].rule, GFP_KERNEL); if (!entry->lsm[lsm_rule].rule) { pr_warn("rule for LSM \'%s\' is undefined\n", entry->lsm[lsm_rule].args_p); if (ima_rules == (struct list_head __rcu *)(&ima_default_rules)) { kfree(entry->lsm[lsm_rule].args_p); entry->lsm[lsm_rule].args_p = NULL; result = -EINVAL; } else result = 0; } return result; } static void ima_log_string_op(struct audit_buffer *ab, char *key, char *value, enum policy_opt rule_operator) { if (!ab) return; switch (rule_operator) { case Opt_uid_gt: case Opt_euid_gt: case Opt_gid_gt: case Opt_egid_gt: case Opt_fowner_gt: case Opt_fgroup_gt: audit_log_format(ab, "%s>", key); break; case Opt_uid_lt: case Opt_euid_lt: case Opt_gid_lt: case Opt_egid_lt: case Opt_fowner_lt: case Opt_fgroup_lt: audit_log_format(ab, "%s<", key); break; default: audit_log_format(ab, "%s=", key); } audit_log_format(ab, "%s ", value); } static void ima_log_string(struct audit_buffer *ab, char *key, char *value) { ima_log_string_op(ab, key, value, Opt_err); } /* * Validating the appended signature included in the measurement list requires * the file hash calculated without the appended signature (i.e., the 'd-modsig' * field). Therefore, notify the user if they have the 'modsig' field but not * the 'd-modsig' field in the template. */ static void check_template_modsig(const struct ima_template_desc *template) { #define MSG "template with 'modsig' field also needs 'd-modsig' field\n" bool has_modsig, has_dmodsig; static bool checked; int i; /* We only need to notify the user once. */ if (checked) return; has_modsig = has_dmodsig = false; for (i = 0; i < template->num_fields; i++) { if (!strcmp(template->fields[i]->field_id, "modsig")) has_modsig = true; else if (!strcmp(template->fields[i]->field_id, "d-modsig")) has_dmodsig = true; } if (has_modsig && !has_dmodsig) pr_notice(MSG); checked = true; #undef MSG } /* * Warn if the template does not contain the given field. */ static void check_template_field(const struct ima_template_desc *template, const char *field, const char *msg) { int i; for (i = 0; i < template->num_fields; i++) if (!strcmp(template->fields[i]->field_id, field)) return; pr_notice_once("%s", msg); } static bool ima_validate_rule(struct ima_rule_entry *entry) { /* Ensure that the action is set and is compatible with the flags */ if (entry->action == UNKNOWN) return false; if (entry->action != MEASURE && entry->flags & IMA_PCR) return false; if (entry->action != APPRAISE && entry->flags & (IMA_DIGSIG_REQUIRED | IMA_MODSIG_ALLOWED | IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS)) return false; /* * The IMA_FUNC bit must be set if and only if there's a valid hook * function specified, and vice versa. Enforcing this property allows * for the NONE case below to validate a rule without an explicit hook * function. */ if (((entry->flags & IMA_FUNC) && entry->func == NONE) || (!(entry->flags & IMA_FUNC) && entry->func != NONE)) return false; /* * Ensure that the hook function is compatible with the other * components of the rule */ switch (entry->func) { case NONE: case FILE_CHECK: case MMAP_CHECK: case MMAP_CHECK_REQPROT: case BPRM_CHECK: case CREDS_CHECK: case POST_SETATTR: case FIRMWARE_CHECK: case POLICY_CHECK: if (entry->flags & ~(IMA_FUNC | IMA_MASK | IMA_FSMAGIC | IMA_UID | IMA_FOWNER | IMA_FSUUID | IMA_INMASK | IMA_EUID | IMA_PCR | IMA_FSNAME | IMA_GID | IMA_EGID | IMA_FGROUP | IMA_DIGSIG_REQUIRED | IMA_PERMIT_DIRECTIO | IMA_VALIDATE_ALGOS | IMA_CHECK_BLACKLIST | IMA_VERITY_REQUIRED)) return false; break; case MODULE_CHECK: case KEXEC_KERNEL_CHECK: case KEXEC_INITRAMFS_CHECK: if (entry->flags & ~(IMA_FUNC | IMA_MASK | IMA_FSMAGIC | IMA_UID | IMA_FOWNER | IMA_FSUUID | IMA_INMASK | IMA_EUID | IMA_PCR | IMA_FSNAME | IMA_GID | IMA_EGID | IMA_FGROUP | IMA_DIGSIG_REQUIRED | IMA_PERMIT_DIRECTIO | IMA_MODSIG_ALLOWED | IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS)) return false; break; case KEXEC_CMDLINE: if (entry->action & ~(MEASURE | DONT_MEASURE)) return false; if (entry->flags & ~(IMA_FUNC | IMA_FSMAGIC | IMA_UID | IMA_FOWNER | IMA_FSUUID | IMA_EUID | IMA_PCR | IMA_FSNAME | IMA_GID | IMA_EGID | IMA_FGROUP)) return false; break; case KEY_CHECK: if (entry->action & ~(MEASURE | DONT_MEASURE)) return false; if (entry->flags & ~(IMA_FUNC | IMA_UID | IMA_GID | IMA_PCR | IMA_KEYRINGS)) return false; if (ima_rule_contains_lsm_cond(entry)) return false; break; case CRITICAL_DATA: if (entry->action & ~(MEASURE | DONT_MEASURE)) return false; if (entry->flags & ~(IMA_FUNC | IMA_UID | IMA_GID | IMA_PCR | IMA_LABEL)) return false; if (ima_rule_contains_lsm_cond(entry)) return false; break; case SETXATTR_CHECK: /* any action other than APPRAISE is unsupported */ if (entry->action != APPRAISE) return false; /* SETXATTR_CHECK requires an appraise_algos parameter */ if (!(entry->flags & IMA_VALIDATE_ALGOS)) return false; /* * full policies are not supported, they would have too * much of a performance impact */ if (entry->flags & ~(IMA_FUNC | IMA_VALIDATE_ALGOS)) return false; break; default: return false; } /* Ensure that combinations of flags are compatible with each other */ if (entry->flags & IMA_CHECK_BLACKLIST && !(entry->flags & IMA_DIGSIG_REQUIRED)) return false; /* * Unlike for regular IMA 'appraise' policy rules where security.ima * xattr may contain either a file hash or signature, the security.ima * xattr for fsverity must contain a file signature (sigv3). Ensure * that 'appraise' rules for fsverity require file signatures by * checking the IMA_DIGSIG_REQUIRED flag is set. */ if (entry->action == APPRAISE && (entry->flags & IMA_VERITY_REQUIRED) && !(entry->flags & IMA_DIGSIG_REQUIRED)) return false; return true; } static unsigned int ima_parse_appraise_algos(char *arg) { unsigned int res = 0; int idx; char *token; while ((token = strsep(&arg, ",")) != NULL) { idx = match_string(hash_algo_name, HASH_ALGO__LAST, token); if (idx < 0) { pr_err("unknown hash algorithm \"%s\"", token); return 0; } if (!crypto_has_alg(hash_algo_name[idx], 0, 0)) { pr_err("unavailable hash algorithm \"%s\", check your kernel configuration", token); return 0; } /* Add the hash algorithm to the 'allowed' bitfield */ res |= (1U << idx); } return res; } static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) { struct audit_buffer *ab; char *from; char *p; bool eid_token; /* either euid or egid */ struct ima_template_desc *template_desc; int result = 0; ab = integrity_audit_log_start(audit_context(), GFP_KERNEL, AUDIT_INTEGRITY_POLICY_RULE); entry->uid = INVALID_UID; entry->gid = INVALID_GID; entry->fowner = INVALID_UID; entry->fgroup = INVALID_GID; entry->uid_op = &uid_eq; entry->gid_op = &gid_eq; entry->fowner_op = &vfsuid_eq_kuid; entry->fgroup_op = &vfsgid_eq_kgid; entry->action = UNKNOWN; while ((p = strsep(&rule, " \t")) != NULL) { substring_t args[MAX_OPT_ARGS]; int token; unsigned long lnum; if (result < 0 || *p == '#') /* ignore suffixed comment */ break; if ((*p == '\0') || (*p == ' ') || (*p == '\t')) continue; token = match_token(p, policy_tokens, args); switch (token) { case Opt_measure: ima_log_string(ab, "action", "measure"); if (entry->action != UNKNOWN) result = -EINVAL; entry->action = MEASURE; break; case Opt_dont_measure: ima_log_string(ab, "action", "dont_measure"); if (entry->action != UNKNOWN) result = -EINVAL; entry->action = DONT_MEASURE; break; case Opt_appraise: ima_log_string(ab, "action", "appraise"); if (entry->action != UNKNOWN) result = -EINVAL; entry->action = APPRAISE; break; case Opt_dont_appraise: ima_log_string(ab, "action", "dont_appraise"); if (entry->action != UNKNOWN) result = -EINVAL; entry->action = DONT_APPRAISE; break; case Opt_audit: ima_log_string(ab, "action", "audit"); if (entry->action != UNKNOWN) result = -EINVAL; entry->action = AUDIT; break; case Opt_hash: ima_log_string(ab, "action", "hash"); if (entry->action != UNKNOWN) result = -EINVAL; entry->action = HASH; break; case Opt_dont_hash: ima_log_string(ab, "action", "dont_hash"); if (entry->action != UNKNOWN) result = -EINVAL; entry->action = DONT_HASH; break; case Opt_func: ima_log_string(ab, "func", args[0].from); if (entry->func) result = -EINVAL; if (strcmp(args[0].from, "FILE_CHECK") == 0) entry->func = FILE_CHECK; /* PATH_CHECK is for backwards compat */ else if (strcmp(args[0].from, "PATH_CHECK") == 0) entry->func = FILE_CHECK; else if (strcmp(args[0].from, "MODULE_CHECK") == 0) entry->func = MODULE_CHECK; else if (strcmp(args[0].from, "FIRMWARE_CHECK") == 0) entry->func = FIRMWARE_CHECK; else if ((strcmp(args[0].from, "FILE_MMAP") == 0) || (strcmp(args[0].from, "MMAP_CHECK") == 0)) entry->func = MMAP_CHECK; else if ((strcmp(args[0].from, "MMAP_CHECK_REQPROT") == 0)) entry->func = MMAP_CHECK_REQPROT; else if (strcmp(args[0].from, "BPRM_CHECK") == 0) entry->func = BPRM_CHECK; else if (strcmp(args[0].from, "CREDS_CHECK") == 0) entry->func = CREDS_CHECK; else if (strcmp(args[0].from, "KEXEC_KERNEL_CHECK") == 0) entry->func = KEXEC_KERNEL_CHECK; else if (strcmp(args[0].from, "KEXEC_INITRAMFS_CHECK") == 0) entry->func = KEXEC_INITRAMFS_CHECK; else if (strcmp(args[0].from, "POLICY_CHECK") == 0) entry->func = POLICY_CHECK; else if (strcmp(args[0].from, "KEXEC_CMDLINE") == 0) entry->func = KEXEC_CMDLINE; else if (IS_ENABLED(CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS) && strcmp(args[0].from, "KEY_CHECK") == 0) entry->func = KEY_CHECK; else if (strcmp(args[0].from, "CRITICAL_DATA") == 0) entry->func = CRITICAL_DATA; else if (strcmp(args[0].from, "SETXATTR_CHECK") == 0) entry->func = SETXATTR_CHECK; else result = -EINVAL; if (!result) entry->flags |= IMA_FUNC; break; case Opt_mask: ima_log_string(ab, "mask", args[0].from); if (entry->mask) result = -EINVAL; from = args[0].from; if (*from == '^') from++; if ((strcmp(from, "MAY_EXEC")) == 0) entry->mask = MAY_EXEC; else if (strcmp(from, "MAY_WRITE") == 0) entry->mask = MAY_WRITE; else if (strcmp(from, "MAY_READ") == 0) entry->mask = MAY_READ; else if (strcmp(from, "MAY_APPEND") == 0) entry->mask = MAY_APPEND; else result = -EINVAL; if (!result) entry->flags |= (*args[0].from == '^') ? IMA_INMASK : IMA_MASK; break; case Opt_fsmagic: ima_log_string(ab, "fsmagic", args[0].from); if (entry->fsmagic) { result = -EINVAL; break; } result = kstrtoul(args[0].from, 16, &entry->fsmagic); if (!result) entry->flags |= IMA_FSMAGIC; break; case Opt_fsname: ima_log_string(ab, "fsname", args[0].from); entry->fsname = kstrdup(args[0].from, GFP_KERNEL); if (!entry->fsname) { result = -ENOMEM; break; } result = 0; entry->flags |= IMA_FSNAME; break; case Opt_keyrings: ima_log_string(ab, "keyrings", args[0].from); if (!IS_ENABLED(CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS) || entry->keyrings) { result = -EINVAL; break; } entry->keyrings = ima_alloc_rule_opt_list(args); if (IS_ERR(entry->keyrings)) { result = PTR_ERR(entry->keyrings); entry->keyrings = NULL; break; } entry->flags |= IMA_KEYRINGS; break; case Opt_label: ima_log_string(ab, "label", args[0].from); if (entry->label) { result = -EINVAL; break; } entry->label = ima_alloc_rule_opt_list(args); if (IS_ERR(entry->label)) { result = PTR_ERR(entry->label); entry->label = NULL; break; } entry->flags |= IMA_LABEL; break; case Opt_fsuuid: ima_log_string(ab, "fsuuid", args[0].from); if (!uuid_is_null(&entry->fsuuid)) { result = -EINVAL; break; } result = uuid_parse(args[0].from, &entry->fsuuid); if (!result) entry->flags |= IMA_FSUUID; break; case Opt_uid_gt: case Opt_euid_gt: entry->uid_op = &uid_gt; fallthrough; case Opt_uid_lt: case Opt_euid_lt: if ((token == Opt_uid_lt) || (token == Opt_euid_lt)) entry->uid_op = &uid_lt; fallthrough; case Opt_uid_eq: case Opt_euid_eq: eid_token = (token == Opt_euid_eq) || (token == Opt_euid_gt) || (token == Opt_euid_lt); ima_log_string_op(ab, eid_token ? "euid" : "uid", args[0].from, token); if (uid_valid(entry->uid)) { result = -EINVAL; break; } result = kstrtoul(args[0].from, 10, &lnum); if (!result) { entry->uid = make_kuid(current_user_ns(), (uid_t) lnum); if (!uid_valid(entry->uid) || (uid_t)lnum != lnum) result = -EINVAL; else entry->flags |= eid_token ? IMA_EUID : IMA_UID; } break; case Opt_gid_gt: case Opt_egid_gt: entry->gid_op = &gid_gt; fallthrough; case Opt_gid_lt: case Opt_egid_lt: if ((token == Opt_gid_lt) || (token == Opt_egid_lt)) entry->gid_op = &gid_lt; fallthrough; case Opt_gid_eq: case Opt_egid_eq: eid_token = (token == Opt_egid_eq) || (token == Opt_egid_gt) || (token == Opt_egid_lt); ima_log_string_op(ab, eid_token ? "egid" : "gid", args[0].from, token); if (gid_valid(entry->gid)) { result = -EINVAL; break; } result = kstrtoul(args[0].from, 10, &lnum); if (!result) { entry->gid = make_kgid(current_user_ns(), (gid_t)lnum); if (!gid_valid(entry->gid) || (((gid_t)lnum) != lnum)) result = -EINVAL; else entry->flags |= eid_token ? IMA_EGID : IMA_GID; } break; case Opt_fowner_gt: entry->fowner_op = &vfsuid_gt_kuid; fallthrough; case Opt_fowner_lt: if (token == Opt_fowner_lt) entry->fowner_op = &vfsuid_lt_kuid; fallthrough; case Opt_fowner_eq: ima_log_string_op(ab, "fowner", args[0].from, token); if (uid_valid(entry->fowner)) { result = -EINVAL; break; } result = kstrtoul(args[0].from, 10, &lnum); if (!result) { entry->fowner = make_kuid(current_user_ns(), (uid_t)lnum); if (!uid_valid(entry->fowner) || (((uid_t)lnum) != lnum)) result = -EINVAL; else entry->flags |= IMA_FOWNER; } break; case Opt_fgroup_gt: entry->fgroup_op = &vfsgid_gt_kgid; fallthrough; case Opt_fgroup_lt: if (token == Opt_fgroup_lt) entry->fgroup_op = &vfsgid_lt_kgid; fallthrough; case Opt_fgroup_eq: ima_log_string_op(ab, "fgroup", args[0].from, token); if (gid_valid(entry->fgroup)) { result = -EINVAL; break; } result = kstrtoul(args[0].from, 10, &lnum); if (!result) { entry->fgroup = make_kgid(current_user_ns(), (gid_t)lnum); if (!gid_valid(entry->fgroup) || (((gid_t)lnum) != lnum)) result = -EINVAL; else entry->flags |= IMA_FGROUP; } break; case Opt_obj_user: ima_log_string(ab, "obj_user", args[0].from); result = ima_lsm_rule_init(entry, args, LSM_OBJ_USER, AUDIT_OBJ_USER); break; case Opt_obj_role: ima_log_string(ab, "obj_role", args[0].from); result = ima_lsm_rule_init(entry, args, LSM_OBJ_ROLE, AUDIT_OBJ_ROLE); break; case Opt_obj_type: ima_log_string(ab, "obj_type", args[0].from); result = ima_lsm_rule_init(entry, args, LSM_OBJ_TYPE, AUDIT_OBJ_TYPE); break; case Opt_subj_user: ima_log_string(ab, "subj_user", args[0].from); result = ima_lsm_rule_init(entry, args, LSM_SUBJ_USER, AUDIT_SUBJ_USER); break; case Opt_subj_role: ima_log_string(ab, "subj_role", args[0].from); result = ima_lsm_rule_init(entry, args, LSM_SUBJ_ROLE, AUDIT_SUBJ_ROLE); break; case Opt_subj_type: ima_log_string(ab, "subj_type", args[0].from); result = ima_lsm_rule_init(entry, args, LSM_SUBJ_TYPE, AUDIT_SUBJ_TYPE); break; case Opt_digest_type: ima_log_string(ab, "digest_type", args[0].from); if (entry->flags & IMA_DIGSIG_REQUIRED) result = -EINVAL; else if ((strcmp(args[0].from, "verity")) == 0) entry->flags |= IMA_VERITY_REQUIRED; else result = -EINVAL; break; case Opt_appraise_type: ima_log_string(ab, "appraise_type", args[0].from); if ((strcmp(args[0].from, "imasig")) == 0) { if (entry->flags & IMA_VERITY_REQUIRED) result = -EINVAL; else entry->flags |= IMA_DIGSIG_REQUIRED | IMA_CHECK_BLACKLIST; } else if (strcmp(args[0].from, "sigv3") == 0) { /* Only fsverity supports sigv3 for now */ if (entry->flags & IMA_VERITY_REQUIRED) entry->flags |= IMA_DIGSIG_REQUIRED | IMA_CHECK_BLACKLIST; else result = -EINVAL; } else if (IS_ENABLED(CONFIG_IMA_APPRAISE_MODSIG) && strcmp(args[0].from, "imasig|modsig") == 0) { if (entry->flags & IMA_VERITY_REQUIRED) result = -EINVAL; else entry->flags |= IMA_DIGSIG_REQUIRED | IMA_MODSIG_ALLOWED | IMA_CHECK_BLACKLIST; } else { result = -EINVAL; } break; case Opt_appraise_flag: ima_log_string(ab, "appraise_flag", args[0].from); break; case Opt_appraise_algos: ima_log_string(ab, "appraise_algos", args[0].from); if (entry->allowed_algos) { result = -EINVAL; break; } entry->allowed_algos = ima_parse_appraise_algos(args[0].from); /* invalid or empty list of algorithms */ if (!entry->allowed_algos) { result = -EINVAL; break; } entry->flags |= IMA_VALIDATE_ALGOS; break; case Opt_permit_directio: entry->flags |= IMA_PERMIT_DIRECTIO; break; case Opt_pcr: ima_log_string(ab, "pcr", args[0].from); result = kstrtoint(args[0].from, 10, &entry->pcr); if (result || INVALID_PCR(entry->pcr)) result = -EINVAL; else entry->flags |= IMA_PCR; break; case Opt_template: ima_log_string(ab, "template", args[0].from); if (entry->action != MEASURE) { result = -EINVAL; break; } template_desc = lookup_template_desc(args[0].from); if (!template_desc || entry->template) { result = -EINVAL; break; } /* * template_desc_init_fields() does nothing if * the template is already initialised, so * it's safe to do this unconditionally */ template_desc_init_fields(template_desc->fmt, &(template_desc->fields), &(template_desc->num_fields)); entry->template = template_desc; break; case Opt_err: ima_log_string(ab, "UNKNOWN", p); result = -EINVAL; break; } } if (!result && !ima_validate_rule(entry)) result = -EINVAL; else if (entry->action == APPRAISE) temp_ima_appraise |= ima_appraise_flag(entry->func); if (!result && entry->flags & IMA_MODSIG_ALLOWED) { template_desc = entry->template ? entry->template : ima_template_desc_current(); check_template_modsig(template_desc); } /* d-ngv2 template field recommended for unsigned fs-verity digests */ if (!result && entry->action == MEASURE && entry->flags & IMA_VERITY_REQUIRED) { template_desc = entry->template ? entry->template : ima_template_desc_current(); check_template_field(template_desc, "d-ngv2", "verity rules should include d-ngv2"); } audit_log_format(ab, "res=%d", !result); audit_log_end(ab); return result; } /** * ima_parse_add_rule - add a rule to ima_policy_rules * @rule: ima measurement policy rule * * Avoid locking by allowing just one writer at a time in ima_write_policy() * Returns the length of the rule parsed, an error code on failure */ ssize_t ima_parse_add_rule(char *rule) { static const char op[] = "update_policy"; char *p; struct ima_rule_entry *entry; ssize_t result, len; int audit_info = 0; p = strsep(&rule, "\n"); len = strlen(p) + 1; p += strspn(p, " \t"); if (*p == '#' || *p == '\0') return len; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL, op, "-ENOMEM", -ENOMEM, audit_info); return -ENOMEM; } INIT_LIST_HEAD(&entry->list); result = ima_parse_rule(p, entry); if (result) { ima_free_rule(entry); integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL, op, "invalid-policy", result, audit_info); return result; } list_add_tail(&entry->list, &ima_temp_rules); return len; } /** * ima_delete_rules() - called to cleanup invalid in-flight policy. * * We don't need locking as we operate on the temp list, which is * different from the active one. There is also only one user of * ima_delete_rules() at a time. */ void ima_delete_rules(void) { struct ima_rule_entry *entry, *tmp; temp_ima_appraise = 0; list_for_each_entry_safe(entry, tmp, &ima_temp_rules, list) { list_del(&entry->list); ima_free_rule(entry); } } #define __ima_hook_stringify(func, str) (#func), const char *const func_tokens[] = { __ima_hooks(__ima_hook_stringify) }; #ifdef CONFIG_IMA_READ_POLICY enum { mask_exec = 0, mask_write, mask_read, mask_append }; static const char *const mask_tokens[] = { "^MAY_EXEC", "^MAY_WRITE", "^MAY_READ", "^MAY_APPEND" }; void *ima_policy_start(struct seq_file *m, loff_t *pos) { loff_t l = *pos; struct ima_rule_entry *entry; struct list_head *ima_rules_tmp; rcu_read_lock(); ima_rules_tmp = rcu_dereference(ima_rules); list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!l--) { rcu_read_unlock(); return entry; } } rcu_read_unlock(); return NULL; } void *ima_policy_next(struct seq_file *m, void *v, loff_t *pos) { struct ima_rule_entry *entry = v; rcu_read_lock(); entry = list_entry_rcu(entry->list.next, struct ima_rule_entry, list); rcu_read_unlock(); (*pos)++; return (&entry->list == &ima_default_rules || &entry->list == &ima_policy_rules) ? NULL : entry; } void ima_policy_stop(struct seq_file *m, void *v) { } #define pt(token) policy_tokens[token].pattern #define mt(token) mask_tokens[token] /* * policy_func_show - display the ima_hooks policy rule */ static void policy_func_show(struct seq_file *m, enum ima_hooks func) { if (func > 0 && func < MAX_CHECK) seq_printf(m, "func=%s ", func_tokens[func]); else seq_printf(m, "func=%d ", func); } static void ima_show_rule_opt_list(struct seq_file *m, const struct ima_rule_opt_list *opt_list) { size_t i; for (i = 0; i < opt_list->count; i++) seq_printf(m, "%s%s", i ? "|" : "", opt_list->items[i]); } static void ima_policy_show_appraise_algos(struct seq_file *m, unsigned int allowed_hashes) { int idx, list_size = 0; for (idx = 0; idx < HASH_ALGO__LAST; idx++) { if (!(allowed_hashes & (1U << idx))) continue; /* only add commas if the list contains multiple entries */ if (list_size++) seq_puts(m, ","); seq_puts(m, hash_algo_name[idx]); } } int ima_policy_show(struct seq_file *m, void *v) { struct ima_rule_entry *entry = v; int i; char tbuf[64] = {0,}; int offset = 0; rcu_read_lock(); /* Do not print rules with inactive LSM labels */ for (i = 0; i < MAX_LSM_RULES; i++) { if (entry->lsm[i].args_p && !entry->lsm[i].rule) { rcu_read_unlock(); return 0; } } if (entry->action & MEASURE) seq_puts(m, pt(Opt_measure)); if (entry->action & DONT_MEASURE) seq_puts(m, pt(Opt_dont_measure)); if (entry->action & APPRAISE) seq_puts(m, pt(Opt_appraise)); if (entry->action & DONT_APPRAISE) seq_puts(m, pt(Opt_dont_appraise)); if (entry->action & AUDIT) seq_puts(m, pt(Opt_audit)); if (entry->action & HASH) seq_puts(m, pt(Opt_hash)); if (entry->action & DONT_HASH) seq_puts(m, pt(Opt_dont_hash)); seq_puts(m, " "); if (entry->flags & IMA_FUNC) policy_func_show(m, entry->func); if ((entry->flags & IMA_MASK) || (entry->flags & IMA_INMASK)) { if (entry->flags & IMA_MASK) offset = 1; if (entry->mask & MAY_EXEC) seq_printf(m, pt(Opt_mask), mt(mask_exec) + offset); if (entry->mask & MAY_WRITE) seq_printf(m, pt(Opt_mask), mt(mask_write) + offset); if (entry->mask & MAY_READ) seq_printf(m, pt(Opt_mask), mt(mask_read) + offset); if (entry->mask & MAY_APPEND) seq_printf(m, pt(Opt_mask), mt(mask_append) + offset); seq_puts(m, " "); } if (entry->flags & IMA_FSMAGIC) { snprintf(tbuf, sizeof(tbuf), "0x%lx", entry->fsmagic); seq_printf(m, pt(Opt_fsmagic), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_FSNAME) { snprintf(tbuf, sizeof(tbuf), "%s", entry->fsname); seq_printf(m, pt(Opt_fsname), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_KEYRINGS) { seq_puts(m, "keyrings="); ima_show_rule_opt_list(m, entry->keyrings); seq_puts(m, " "); } if (entry->flags & IMA_LABEL) { seq_puts(m, "label="); ima_show_rule_opt_list(m, entry->label); seq_puts(m, " "); } if (entry->flags & IMA_PCR) { snprintf(tbuf, sizeof(tbuf), "%d", entry->pcr); seq_printf(m, pt(Opt_pcr), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_FSUUID) { seq_printf(m, "fsuuid=%pU", &entry->fsuuid); seq_puts(m, " "); } if (entry->flags & IMA_UID) { snprintf(tbuf, sizeof(tbuf), "%d", __kuid_val(entry->uid)); if (entry->uid_op == &uid_gt) seq_printf(m, pt(Opt_uid_gt), tbuf); else if (entry->uid_op == &uid_lt) seq_printf(m, pt(Opt_uid_lt), tbuf); else seq_printf(m, pt(Opt_uid_eq), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_EUID) { snprintf(tbuf, sizeof(tbuf), "%d", __kuid_val(entry->uid)); if (entry->uid_op == &uid_gt) seq_printf(m, pt(Opt_euid_gt), tbuf); else if (entry->uid_op == &uid_lt) seq_printf(m, pt(Opt_euid_lt), tbuf); else seq_printf(m, pt(Opt_euid_eq), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_GID) { snprintf(tbuf, sizeof(tbuf), "%d", __kgid_val(entry->gid)); if (entry->gid_op == &gid_gt) seq_printf(m, pt(Opt_gid_gt), tbuf); else if (entry->gid_op == &gid_lt) seq_printf(m, pt(Opt_gid_lt), tbuf); else seq_printf(m, pt(Opt_gid_eq), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_EGID) { snprintf(tbuf, sizeof(tbuf), "%d", __kgid_val(entry->gid)); if (entry->gid_op == &gid_gt) seq_printf(m, pt(Opt_egid_gt), tbuf); else if (entry->gid_op == &gid_lt) seq_printf(m, pt(Opt_egid_lt), tbuf); else seq_printf(m, pt(Opt_egid_eq), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_FOWNER) { snprintf(tbuf, sizeof(tbuf), "%d", __kuid_val(entry->fowner)); if (entry->fowner_op == &vfsuid_gt_kuid) seq_printf(m, pt(Opt_fowner_gt), tbuf); else if (entry->fowner_op == &vfsuid_lt_kuid) seq_printf(m, pt(Opt_fowner_lt), tbuf); else seq_printf(m, pt(Opt_fowner_eq), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_FGROUP) { snprintf(tbuf, sizeof(tbuf), "%d", __kgid_val(entry->fgroup)); if (entry->fgroup_op == &vfsgid_gt_kgid) seq_printf(m, pt(Opt_fgroup_gt), tbuf); else if (entry->fgroup_op == &vfsgid_lt_kgid) seq_printf(m, pt(Opt_fgroup_lt), tbuf); else seq_printf(m, pt(Opt_fgroup_eq), tbuf); seq_puts(m, " "); } if (entry->flags & IMA_VALIDATE_ALGOS) { seq_puts(m, "appraise_algos="); ima_policy_show_appraise_algos(m, entry->allowed_algos); seq_puts(m, " "); } for (i = 0; i < MAX_LSM_RULES; i++) { if (entry->lsm[i].rule) { switch (i) { case LSM_OBJ_USER: seq_printf(m, pt(Opt_obj_user), entry->lsm[i].args_p); break; case LSM_OBJ_ROLE: seq_printf(m, pt(Opt_obj_role), entry->lsm[i].args_p); break; case LSM_OBJ_TYPE: seq_printf(m, pt(Opt_obj_type), entry->lsm[i].args_p); break; case LSM_SUBJ_USER: seq_printf(m, pt(Opt_subj_user), entry->lsm[i].args_p); break; case LSM_SUBJ_ROLE: seq_printf(m, pt(Opt_subj_role), entry->lsm[i].args_p); break; case LSM_SUBJ_TYPE: seq_printf(m, pt(Opt_subj_type), entry->lsm[i].args_p); break; } seq_puts(m, " "); } } if (entry->template) seq_printf(m, "template=%s ", entry->template->name); if (entry->flags & IMA_DIGSIG_REQUIRED) { if (entry->flags & IMA_VERITY_REQUIRED) seq_puts(m, "appraise_type=sigv3 "); else if (entry->flags & IMA_MODSIG_ALLOWED) seq_puts(m, "appraise_type=imasig|modsig "); else seq_puts(m, "appraise_type=imasig "); } if (entry->flags & IMA_VERITY_REQUIRED) seq_puts(m, "digest_type=verity "); if (entry->flags & IMA_PERMIT_DIRECTIO) seq_puts(m, "permit_directio "); rcu_read_unlock(); seq_puts(m, "\n"); return 0; } #endif /* CONFIG_IMA_READ_POLICY */ #if defined(CONFIG_IMA_APPRAISE) && defined(CONFIG_INTEGRITY_TRUSTED_KEYRING) /* * ima_appraise_signature: whether IMA will appraise a given function using * an IMA digital signature. This is restricted to cases where the kernel * has a set of built-in trusted keys in order to avoid an attacker simply * loading additional keys. */ bool ima_appraise_signature(enum kernel_read_file_id id) { struct ima_rule_entry *entry; bool found = false; enum ima_hooks func; struct list_head *ima_rules_tmp; if (id >= READING_MAX_ID) return false; if (id == READING_KEXEC_IMAGE && !(ima_appraise & IMA_APPRAISE_ENFORCE) && security_locked_down(LOCKDOWN_KEXEC)) return false; func = read_idmap[id] ?: FILE_CHECK; rcu_read_lock(); ima_rules_tmp = rcu_dereference(ima_rules); list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action != APPRAISE) continue; /* * A generic entry will match, but otherwise require that it * match the func we're looking for */ if (entry->func && entry->func != func) continue; /* * We require this to be a digital signature, not a raw IMA * hash. */ if (entry->flags & IMA_DIGSIG_REQUIRED) found = true; /* * We've found a rule that matches, so break now even if it * didn't require a digital signature - a later rule that does * won't override it, so would be a false positive. */ break; } rcu_read_unlock(); return found; } #endif /* CONFIG_IMA_APPRAISE && CONFIG_INTEGRITY_TRUSTED_KEYRING */ |
| 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 | /* 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; }; struct parsed_desc { u32 mb; u32 valid; }; /* 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 addr = desc->addr - pool->tx_metadata_len; u64 len = desc->len + pool->tx_metadata_len; u64 offset = addr & (pool->chunk_size - 1); if (!desc->len) return false; if (offset + 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 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len; u64 len = desc->len + pool->tx_metadata_len; if (!desc->len) return false; if (len > pool->chunk_size) return false; if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt || 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 u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, u32 max) { u32 cached_cons = q->cached_cons, nb_entries = 0; struct xdp_desc *descs = pool->tx_descs; u32 total_descs = 0, nr_frags = 0; /* track first entry, if stumble upon *any* invalid descriptor, rewind * current packet that consists of frags and stop the processing */ 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)) break; if (likely(!parsed.mb)) { total_descs += (nr_frags + 1); nr_frags = 0; } else { nr_frags++; if (nr_frags == pool->xdp_zc_max_segs) { nr_frags = 0; break; } } nb_entries++; } cached_cons -= nr_frags; /* Release valid plus any invalid entries */ xskq_cons_release_n(q, cached_cons - q->cached_cons); return total_descs; } /* 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_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_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 int 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; if (xskq_prod_is_full(q)) return -ENOBUFS; /* 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; 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 */ |
| 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* - * net/sched/act_ct.c Connection Tracking action * * Authors: Paul Blakey <paulb@mellanox.com> * Yossi Kuperman <yossiku@mellanox.com> * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/pkt_cls.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/rhashtable.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/act_api.h> #include <net/ip.h> #include <net/ipv6_frag.h> #include <uapi/linux/tc_act/tc_ct.h> #include <net/tc_act/tc_ct.h> #include <net/tc_wrapper.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_conntrack_act_ct.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <uapi/linux/netfilter/nf_nat.h> static struct workqueue_struct *act_ct_wq; static struct rhashtable zones_ht; static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; }; struct tcf_ct_flow_table { struct rhash_head node; /* In zones tables */ struct rcu_work rwork; struct nf_flowtable nf_ft; refcount_t ref; struct zones_ht_key key; bool dying; }; static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), .key_len = offsetofend(struct zones_ht_key, zone), .automatic_shrinking = true, }; static struct flow_action_entry * tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action) { int i = flow_action->num_entries++; return &flow_action->entries[i]; } static void tcf_ct_add_mangle_action(struct flow_action *action, enum flow_action_mangle_base htype, u32 offset, u32 mask, u32 val) { struct flow_action_entry *entry; entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_MANGLE; entry->mangle.htype = htype; entry->mangle.mask = ~mask; entry->mangle.offset = offset; entry->mangle.val = val; } /* The following nat helper functions check if the inverted reverse tuple * (target) is different then the current dir tuple - meaning nat for ports * and/or ip is needed, and add the relevant mangle actions. */ static void tcf_ct_flow_table_add_action_nat_ipv4(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offsetof(struct iphdr, saddr), 0xFFFFFFFF, be32_to_cpu(target.src.u3.ip)); if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offsetof(struct iphdr, daddr), 0xFFFFFFFF, be32_to_cpu(target.dst.u3.ip)); } static void tcf_ct_add_ipv6_addr_mangle_action(struct flow_action *action, union nf_inet_addr *addr, u32 offset) { int i; for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP6, i * sizeof(u32) + offset, 0xFFFFFFFF, be32_to_cpu(addr->ip6[i])); } static void tcf_ct_flow_table_add_action_nat_ipv6(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) tcf_ct_add_ipv6_addr_mangle_action(action, &target.src.u3, offsetof(struct ipv6hdr, saddr)); if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) tcf_ct_add_ipv6_addr_mangle_action(action, &target.dst.u3, offsetof(struct ipv6hdr, daddr)); } static void tcf_ct_flow_table_add_action_nat_tcp(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { __be16 target_src = target.src.u.tcp.port; __be16 target_dst = target.dst.u.tcp.port; if (target_src != tuple->src.u.tcp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, offsetof(struct tcphdr, source), 0xFFFF, be16_to_cpu(target_src)); if (target_dst != tuple->dst.u.tcp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, offsetof(struct tcphdr, dest), 0xFFFF, be16_to_cpu(target_dst)); } static void tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { __be16 target_src = target.src.u.udp.port; __be16 target_dst = target.dst.u.udp.port; if (target_src != tuple->src.u.udp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, source), 0xFFFF, be16_to_cpu(target_src)); if (target_dst != tuple->dst.u.udp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, dest), 0xFFFF, be16_to_cpu(target_dst)); } static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, enum ip_conntrack_dir dir, enum ip_conntrack_info ctinfo, struct flow_action *action) { struct nf_conn_labels *ct_labels; struct flow_action_entry *entry; u32 *act_ct_labels; entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif /* aligns with the CT reference on the SKB nf_ct_set */ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; act_ct_labels = entry->ct_metadata.labels; ct_labels = nf_ct_labels_find(ct); if (ct_labels) memcpy(act_ct_labels, ct_labels->bits, NF_CT_LABELS_MAX_SIZE); else memset(act_ct_labels, 0, NF_CT_LABELS_MAX_SIZE); } static int tcf_ct_flow_table_add_action_nat(struct net *net, struct nf_conn *ct, enum ip_conntrack_dir dir, struct flow_action *action) { const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; struct nf_conntrack_tuple target; if (!(ct->status & IPS_NAT_MASK)) return 0; nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (tuple->src.l3num) { case NFPROTO_IPV4: tcf_ct_flow_table_add_action_nat_ipv4(tuple, target, action); break; case NFPROTO_IPV6: tcf_ct_flow_table_add_action_nat_ipv6(tuple, target, action); break; default: return -EOPNOTSUPP; } switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: tcf_ct_flow_table_add_action_nat_tcp(tuple, target, action); break; case IPPROTO_UDP: tcf_ct_flow_table_add_action_nat_udp(tuple, target, action); break; default: return -EOPNOTSUPP; } return 0; } static int tcf_ct_flow_table_fill_actions(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir tdir, struct nf_flow_rule *flow_rule) { struct flow_action *action = &flow_rule->rule->action; int num_entries = action->num_entries; struct nf_conn *ct = flow->ct; enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; int i, err; switch (tdir) { case FLOW_OFFLOAD_DIR_ORIGINAL: dir = IP_CT_DIR_ORIGINAL; ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? IP_CT_ESTABLISHED : IP_CT_NEW; if (ctinfo == IP_CT_ESTABLISHED) set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); break; case FLOW_OFFLOAD_DIR_REPLY: dir = IP_CT_DIR_REPLY; ctinfo = IP_CT_ESTABLISHED_REPLY; break; default: return -EOPNOTSUPP; } err = tcf_ct_flow_table_add_action_nat(net, ct, dir, action); if (err) goto err_nat; tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action); return 0; err_nat: /* Clear filled actions */ for (i = num_entries; i < action->num_entries; i++) memset(&action->entries[i], 0, sizeof(action->entries[i])); action->num_entries = num_entries; return err; } static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) { return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); } static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); static void tcf_ct_nf_get(struct nf_flowtable *ft) { struct tcf_ct_flow_table *ct_ft = container_of(ft, struct tcf_ct_flow_table, nf_ft); tcf_ct_flow_table_get_ref(ct_ft); } static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); static void tcf_ct_nf_put(struct nf_flowtable *ft) { struct tcf_ct_flow_table *ct_ft = container_of(ft, struct tcf_ct_flow_table, nf_ft); tcf_ct_flow_table_put(ct_ft); } static struct nf_flowtable_type flowtable_ct = { .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, .get = tcf_ct_nf_get, .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) { struct zones_ht_key key = { .net = net, .zone = params->zone }; struct tcf_ct_flow_table *ct_ft; int err = -ENOMEM; mutex_lock(&zones_mutex); ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) goto out_unlock; ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL); if (!ct_ft) goto err_alloc; refcount_set(&ct_ft->ref, 1); ct_ft->key = key; err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params); if (err) goto err_insert; ct_ft->nf_ft.type = &flowtable_ct; ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD | NF_FLOWTABLE_COUNTER; err = nf_flow_table_init(&ct_ft->nf_ft); if (err) goto err_init; write_pnet(&ct_ft->nf_ft.net, net); __module_get(THIS_MODULE); out_unlock: params->ct_ft = ct_ft; params->nf_ft = &ct_ft->nf_ft; mutex_unlock(&zones_mutex); return 0; err_init: rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); err_insert: kfree(ct_ft); err_alloc: mutex_unlock(&zones_mutex); return err; } static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) { refcount_inc(&ct_ft->ref); } static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { struct tcf_ct_flow_table *ct_ft; struct flow_block *block; ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, rwork); nf_flow_table_free(&ct_ft->nf_ft); block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); module_put(THIS_MODULE); } static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) { if (refcount_dec_and_test(&ct_ft->ref)) { rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); queue_rcu_work(act_ct_wq, &ct_ft->rwork); } } static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, struct nf_conn_act_ct_ext *act_ct_ext, u8 dir) { entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC; entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; } static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry) { struct nf_conn_act_ct_ext *act_ct_ext; act_ct_ext = nf_conn_act_ct_ext_find(entry->ct); if (act_ct_ext) { tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); } } static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, bool tcp, bool bidirectional) { struct nf_conn_act_ct_ext *act_ct_ext; struct flow_offload *entry; int err; if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) return; entry = flow_offload_alloc(ct); if (!entry) { WARN_ON_ONCE(1); goto err_alloc; } if (tcp) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } if (bidirectional) __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags); act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); } err = flow_offload_add(&ct_ft->nf_ft, entry); if (err) goto err_add; return; err_add: flow_offload_free(entry); err_alloc: clear_bit(IPS_OFFLOAD_BIT, &ct->status); } static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { bool tcp = false, bidirectional = true; switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || !test_bit(IPS_ASSURED_BIT, &ct->status) || ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) return; tcp = true; break; case IPPROTO_UDP: if (!nf_ct_is_confirmed(ct)) return; if (!test_bit(IPS_ASSURED_BIT, &ct->status)) bidirectional = false; break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || !test_bit(IPS_ASSURED_BIT, &ct->status) || ct->status & IPS_NAT_MASK) return; tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) return; break; } #endif default: return; } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || ct->status & IPS_SEQ_ADJUST) return; tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional); } static bool tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb, struct flow_offload_tuple *tuple, struct tcphdr **tcph) { struct flow_ports *ports; unsigned int thoff; struct iphdr *iph; size_t hdrsize; u8 ipproto; if (!pskb_network_may_pull(skb, sizeof(*iph))) return false; iph = ip_hdr(skb); thoff = iph->ihl * 4; if (ip_is_fragment(iph) || unlikely(thoff != sizeof(struct iphdr))) return false; ipproto = iph->protocol; switch (ipproto) { case IPPROTO_TCP: hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: hdrsize = sizeof(*ports); break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: hdrsize = sizeof(struct gre_base_hdr); break; #endif default: return false; } if (iph->ttl <= 1) return false; if (!pskb_network_may_pull(skb, thoff + hdrsize)) return false; switch (ipproto) { case IPPROTO_TCP: *tcph = (void *)(skb_network_header(skb) + thoff); fallthrough; case IPPROTO_UDP: ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_port = ports->source; tuple->dst_port = ports->dest; break; case IPPROTO_GRE: { struct gre_base_hdr *greh; greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff); if ((greh->flags & GRE_VERSION) != GRE_VERSION_0) return false; break; } } iph = ip_hdr(skb); tuple->src_v4.s_addr = iph->saddr; tuple->dst_v4.s_addr = iph->daddr; tuple->l3proto = AF_INET; tuple->l4proto = ipproto; return true; } static bool tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb, struct flow_offload_tuple *tuple, struct tcphdr **tcph) { struct flow_ports *ports; struct ipv6hdr *ip6h; unsigned int thoff; size_t hdrsize; u8 nexthdr; if (!pskb_network_may_pull(skb, sizeof(*ip6h))) return false; ip6h = ipv6_hdr(skb); thoff = sizeof(*ip6h); nexthdr = ip6h->nexthdr; switch (nexthdr) { case IPPROTO_TCP: hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: hdrsize = sizeof(*ports); break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: hdrsize = sizeof(struct gre_base_hdr); break; #endif default: return false; } if (ip6h->hop_limit <= 1) return false; if (!pskb_network_may_pull(skb, thoff + hdrsize)) return false; switch (nexthdr) { case IPPROTO_TCP: *tcph = (void *)(skb_network_header(skb) + thoff); fallthrough; case IPPROTO_UDP: ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_port = ports->source; tuple->dst_port = ports->dest; break; case IPPROTO_GRE: { struct gre_base_hdr *greh; greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff); if ((greh->flags & GRE_VERSION) != GRE_VERSION_0) return false; break; } } ip6h = ipv6_hdr(skb); tuple->src_v6 = ip6h->saddr; tuple->dst_v6 = ip6h->daddr; tuple->l3proto = AF_INET6; tuple->l4proto = nexthdr; return true; } static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, struct sk_buff *skb, u8 family) { struct nf_flowtable *nf_ft = &p->ct_ft->nf_ft; struct flow_offload_tuple_rhash *tuplehash; struct flow_offload_tuple tuple = {}; enum ip_conntrack_info ctinfo; struct tcphdr *tcph = NULL; bool force_refresh = false; struct flow_offload *flow; struct nf_conn *ct; u8 dir; switch (family) { case NFPROTO_IPV4: if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph)) return false; break; case NFPROTO_IPV6: if (!tcf_ct_flow_table_fill_tuple_ipv6(skb, &tuple, &tcph)) return false; break; default: return false; } tuplehash = flow_offload_lookup(nf_ft, &tuple); if (!tuplehash) return false; dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); ct = flow->ct; if (dir == FLOW_OFFLOAD_DIR_REPLY && !test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) { /* Only offload reply direction after connection became * assured. */ if (test_bit(IPS_ASSURED_BIT, &ct->status)) set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags)) /* If flow_table flow has already been updated to the * established state, then don't refresh. */ return false; force_refresh = true; } if (tcph && (unlikely(tcph->fin || tcph->rst))) { flow_offload_teardown(flow); return false; } if (dir == FLOW_OFFLOAD_DIR_ORIGINAL) ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? IP_CT_ESTABLISHED : IP_CT_NEW; else ctinfo = IP_CT_ESTABLISHED_REPLY; nf_conn_act_ct_ext_fill(skb, ct, ctinfo); tcf_ct_flow_ct_ext_ifidx_update(flow); flow_offload_refresh(nf_ft, flow, force_refresh); if (!test_bit(IPS_ASSURED_BIT, &ct->status)) { /* Process this flow in SW to allow promoting to ASSURED */ return false; } nf_conntrack_get(&ct->ct_general); nf_ct_set(skb, ct, ctinfo); if (nf_ft->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(ct, dir, skb->len); return true; } static int tcf_ct_flow_tables_init(void) { return rhashtable_init(&zones_ht, &zones_params); } static void tcf_ct_flow_tables_uninit(void) { rhashtable_destroy(&zones_ht); } static struct tc_action_ops act_ct_ops; struct tc_ct_action_net { struct tc_action_net tn; /* Must be first */ }; /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, struct tcf_ct_params *p) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); if (!ct) return false; if (!net_eq(net, read_pnet(&ct->ct_net))) goto drop_ct; if (nf_ct_zone(ct)->id != p->zone) goto drop_ct; if (p->helper) { struct nf_conn_help *help; help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); if (help && rcu_access_pointer(help->helper) != p->helper) goto drop_ct; } /* Force conntrack entry direction. */ if ((p->ct_action & TCA_CT_ACT_FORCE) && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { if (nf_ct_is_confirmed(ct)) nf_ct_kill(ct); goto drop_ct; } return true; drop_ct: nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); return false; } static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): family = NFPROTO_IPV4; break; case htons(ETH_P_IPV6): family = NFPROTO_IPV6; break; default: break; } return family; } static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag) { unsigned int len; len = skb_network_offset(skb) + sizeof(struct iphdr); if (unlikely(skb->len < len)) return -EINVAL; if (unlikely(!pskb_may_pull(skb, len))) return -ENOMEM; *frag = ip_is_fragment(ip_hdr(skb)); return 0; } static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag) { unsigned int flags = 0, len, payload_ofs = 0; unsigned short frag_off; int nexthdr; len = skb_network_offset(skb) + sizeof(struct ipv6hdr); if (unlikely(skb->len < len)) return -EINVAL; if (unlikely(!pskb_may_pull(skb, len))) return -ENOMEM; nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); if (unlikely(nexthdr < 0)) return -EPROTO; *frag = flags & IP6_FH_F_FRAG; return 0; } static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, u8 family, u16 zone, bool *defrag) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; int err = 0; bool frag; u8 proto; u16 mru; /* Previously seen (loopback)? Ignore. */ ct = nf_ct_get(skb, &ctinfo); if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED) return 0; if (family == NFPROTO_IPV4) err = tcf_ct_ipv4_is_fragment(skb, &frag); else err = tcf_ct_ipv6_is_fragment(skb, &frag); if (err || !frag) return err; err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru); if (err) return err; *defrag = true; tc_skb_cb(skb)->mru = mru; return 0; } static void tcf_ct_params_free(struct tcf_ct_params *params) { if (params->helper) { #if IS_ENABLED(CONFIG_NF_NAT) if (params->ct_action & TCA_CT_ACT_NAT) nf_nat_helper_put(params->helper); #endif nf_conntrack_helper_put(params->helper); } if (params->ct_ft) tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) { if (params->put_labels) nf_connlabels_put(nf_ct_net(params->tmpl)); nf_ct_put(params->tmpl); } kfree(params); } static void tcf_ct_params_free_rcu(struct rcu_head *head) { struct tcf_ct_params *params; params = container_of(head, struct tcf_ct_params, rcu); tcf_ct_params_free(params); } static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; if (!mask) return; new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); if (READ_ONCE(ct->mark) != new_mark) { WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } #endif } static void tcf_ct_act_set_labels(struct nf_conn *ct, u32 *labels, u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); if (!memchr_inv(labels_m, 0, labels_sz)) return; nf_connlabels_replace(ct, labels, labels_m, 4); #endif } static int tcf_ct_act_nat(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int ct_action, struct nf_nat_range2 *range, bool commit) { #if IS_ENABLED(CONFIG_NF_NAT) int err, action = 0; if (!(ct_action & TCA_CT_ACT_NAT)) return NF_ACCEPT; if (ct_action & TCA_CT_ACT_NAT_SRC) action |= BIT(NF_NAT_MANIP_SRC); if (ct_action & TCA_CT_ACT_NAT_DST) action |= BIT(NF_NAT_MANIP_DST); err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit); if (err != NF_ACCEPT) return err & NF_VERDICT_MASK; if (action & BIT(NF_NAT_MANIP_SRC)) tc_skb_cb(skb)->post_ct_snat = 1; if (action & BIT(NF_NAT_MANIP_DST)) tc_skb_cb(skb)->post_ct_dnat = 1; return err; #else return NF_ACCEPT; #endif } TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct net *net = dev_net(skb->dev); enum ip_conntrack_info ctinfo; struct tcf_ct *c = to_ct(a); struct nf_conn *tmpl = NULL; struct nf_hook_state state; bool cached, commit, clear; int nh_ofs, err, retval; struct tcf_ct_params *p; bool add_helper = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; u8 family; p = rcu_dereference_bh(c->params); retval = READ_ONCE(c->tcf_action); commit = p->ct_action & TCA_CT_ACT_COMMIT; clear = p->ct_action & TCA_CT_ACT_CLEAR; tmpl = p->tmpl; tcf_lastuse_update(&c->tcf_tm); tcf_action_update_bstats(&c->common, skb); if (clear) { tc_skb_cb(skb)->post_ct = false; ct = nf_ct_get(skb, &ctinfo); if (ct) { nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } goto out_clear; } family = tcf_ct_skb_nf_family(skb); if (family == NFPROTO_UNSPEC) goto drop; /* The conntrack module expects to be working at L3. * We also try to pull the IPv4/6 header to linear area */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); if (err) goto out_frag; err = nf_ct_skb_network_trim(skb, family); if (err) goto drop; /* If we are recirculating packets to match on ct fields and * committing with a separate ct action, then we don't need to * actually run the packet through conntrack twice unless it's for a * different zone. */ cached = tcf_ct_skb_nfct_cached(net, skb, p); if (!cached) { if (tcf_ct_flow_table_lookup(p, skb, family)) { skip_add = true; goto do_nat; } /* Associate skb with specified zone. */ if (tmpl) { nf_conntrack_put(skb_nfct(skb)); nf_conntrack_get(&tmpl->ct_general); nf_ct_set(skb, tmpl, IP_CT_NEW); } state.hook = NF_INET_PRE_ROUTING; state.net = net; state.pf = family; err = nf_conntrack_in(skb, &state); if (err != NF_ACCEPT) goto nf_error; } do_nat: ct = nf_ct_get(skb, &ctinfo); if (!ct) goto out_push; nf_ct_deliver_cached_events(ct); nf_conn_act_ct_ext_fill(skb, ct, ctinfo); err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit); if (err != NF_ACCEPT) goto nf_error; if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); if (err) goto drop; add_helper = true; if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) { if (!nfct_seqadj_ext_add(ct)) goto drop; } } if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { err = nf_ct_helper(skb, ct, ctinfo, family); if (err != NF_ACCEPT) goto nf_error; } if (commit) { tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); if (!nf_ct_is_confirmed(ct)) nf_conn_act_ct_ext_add(skb, ct, ctinfo); /* This will take care of sending queued events * even if the connection is already confirmed. */ err = nf_conntrack_confirm(skb); if (err != NF_ACCEPT) goto nf_error; /* The ct may be dropped if a clash has been resolved, * so it's necessary to retrieve it from skb again to * prevent UAF. */ ct = nf_ct_get(skb, &ctinfo); if (!ct) skip_add = true; } if (!skip_add) tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo); out_push: skb_push_rcsum(skb, nh_ofs); tc_skb_cb(skb)->post_ct = true; tc_skb_cb(skb)->zone = p->zone; out_clear: if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; out_frag: if (err != -EINPROGRESS) tcf_action_inc_drop_qstats(&c->common); return TC_ACT_CONSUMED; drop: tcf_action_inc_drop_qstats(&c->common); return TC_ACT_SHOT; nf_error: /* some verdicts store extra data in upper bits, such * as errno or queue number. */ switch (err & NF_VERDICT_MASK) { case NF_DROP: goto drop; case NF_STOLEN: tcf_action_inc_drop_qstats(&c->common); return TC_ACT_CONSUMED; default: DEBUG_NET_WARN_ON_ONCE(1); goto drop; } } static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_ACTION] = { .type = NLA_U16 }, [TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)), [TCA_CT_ZONE] = { .type = NLA_U16 }, [TCA_CT_MARK] = { .type = NLA_U32 }, [TCA_CT_MARK_MASK] = { .type = NLA_U32 }, [TCA_CT_LABELS] = { .type = NLA_BINARY, .len = 128 / BITS_PER_BYTE }, [TCA_CT_LABELS_MASK] = { .type = NLA_BINARY, .len = 128 / BITS_PER_BYTE }, [TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 }, [TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 }, [TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN }, [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 }, [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 }, }; static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, struct tc_ct *parm, struct nlattr **tb, struct netlink_ext_ack *extack) { struct nf_nat_range2 *range; if (!(p->ct_action & TCA_CT_ACT_NAT)) return 0; if (!IS_ENABLED(CONFIG_NF_NAT)) { NL_SET_ERR_MSG_MOD(extack, "Netfilter nat isn't enabled in kernel"); return -EOPNOTSUPP; } if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) return 0; if ((p->ct_action & TCA_CT_ACT_NAT_SRC) && (p->ct_action & TCA_CT_ACT_NAT_DST)) { NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time"); return -EOPNOTSUPP; } range = &p->range; if (tb[TCA_CT_NAT_IPV4_MIN]) { struct nlattr *max_attr = tb[TCA_CT_NAT_IPV4_MAX]; p->ipv4_range = true; range->flags |= NF_NAT_RANGE_MAP_IPS; range->min_addr.ip = nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]); range->max_addr.ip = nla_get_in_addr_default(max_attr, range->min_addr.ip); } else if (tb[TCA_CT_NAT_IPV6_MIN]) { struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX]; p->ipv4_range = false; range->flags |= NF_NAT_RANGE_MAP_IPS; range->min_addr.in6 = nla_get_in6_addr(tb[TCA_CT_NAT_IPV6_MIN]); range->max_addr.in6 = max_attr ? nla_get_in6_addr(max_attr) : range->min_addr.in6; } if (tb[TCA_CT_NAT_PORT_MIN]) { range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; range->min_proto.all = nla_get_be16(tb[TCA_CT_NAT_PORT_MIN]); range->max_proto.all = tb[TCA_CT_NAT_PORT_MAX] ? nla_get_be16(tb[TCA_CT_NAT_PORT_MAX]) : range->min_proto.all; } return 0; } static void tcf_ct_set_key_val(struct nlattr **tb, void *val, int val_type, void *mask, int mask_type, int len) { if (!tb[val_type]) return; nla_memcpy(val, tb[val_type], len); if (!mask) return; if (mask_type == TCA_CT_UNSPEC || !tb[mask_type]) memset(mask, 0xff, len); else nla_memcpy(mask, tb[mask_type], len); } static int tcf_ct_fill_params(struct net *net, struct tcf_ct_params *p, struct tc_ct *parm, struct nlattr **tb, struct netlink_ext_ack *extack) { struct nf_conntrack_zone zone; int err, family, proto, len; bool put_labels = false; struct nf_conn *tmpl; char *name; p->zone = NF_CT_DEFAULT_ZONE_ID; tcf_ct_set_key_val(tb, &p->ct_action, TCA_CT_ACTION, NULL, TCA_CT_UNSPEC, sizeof(p->ct_action)); if (p->ct_action & TCA_CT_ACT_CLEAR) return 0; err = tcf_ct_fill_params_nat(p, parm, tb, extack); if (err) return err; if (tb[TCA_CT_MARK]) { if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack mark isn't enabled."); return -EOPNOTSUPP; } tcf_ct_set_key_val(tb, &p->mark, TCA_CT_MARK, &p->mark_mask, TCA_CT_MARK_MASK, sizeof(p->mark)); } if (tb[TCA_CT_LABELS]) { unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled."); return -EOPNOTSUPP; } if (nf_connlabels_get(net, n_bits - 1)) { NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length"); return -EOPNOTSUPP; } else { put_labels = true; } tcf_ct_set_key_val(tb, p->labels, TCA_CT_LABELS, p->labels_mask, TCA_CT_LABELS_MASK, sizeof(p->labels)); } if (tb[TCA_CT_ZONE]) { if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled."); return -EOPNOTSUPP; } tcf_ct_set_key_val(tb, &p->zone, TCA_CT_ZONE, NULL, TCA_CT_UNSPEC, sizeof(p->zone)); } nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0); tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL); if (!tmpl) { NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template"); return -ENOMEM; } p->tmpl = tmpl; if (tb[TCA_CT_HELPER_NAME]) { name = nla_data(tb[TCA_CT_HELPER_NAME]); len = nla_len(tb[TCA_CT_HELPER_NAME]); if (len > 16 || name[len - 1] != '\0') { NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name."); err = -EINVAL; goto err; } family = nla_get_u8_default(tb[TCA_CT_HELPER_FAMILY], AF_INET); proto = nla_get_u8_default(tb[TCA_CT_HELPER_PROTO], IPPROTO_TCP); err = nf_ct_add_helper(tmpl, name, family, proto, p->ct_action & TCA_CT_ACT_NAT, &p->helper); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to add helper"); goto err; } } p->put_labels = put_labels; if (p->ct_action & TCA_CT_ACT_COMMIT) __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; err: if (put_labels) nf_connlabels_put(net); nf_ct_put(p->tmpl); p->tmpl = NULL; return err; } static int tcf_ct_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_ct_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_ct_params *params = NULL; struct nlattr *tb[TCA_CT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_ct *parm; struct tcf_ct *c; int err, res = 0; u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed"); return -EINVAL; } err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack); if (err < 0) return err; if (!tb[TCA_CT_PARMS]) { NL_SET_ERR_MSG_MOD(extack, "Missing required ct parameters"); return -EINVAL; } parm = nla_data(tb[TCA_CT_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; if (!err) { err = tcf_idr_create_from_flags(tn, index, est, a, &act_ct_ops, bind, flags); if (err) { tcf_idr_cleanup(tn, index); return err; } res = ACT_P_CREATED; } else { if (bind) return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto cleanup; c = to_ct(*a); params = kzalloc(sizeof(*params), GFP_KERNEL); if (unlikely(!params)) { err = -ENOMEM; goto cleanup; } err = tcf_ct_fill_params(net, params, parm, tb, extack); if (err) goto cleanup; err = tcf_ct_flow_table_get(net, params); if (err) goto cleanup; spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params = rcu_replace_pointer(c->params, params, lockdep_is_held(&c->tcf_lock)); spin_unlock_bh(&c->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); return res; cleanup: if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) tcf_ct_params_free(params); tcf_idr_release(*a, bind); return err; } static void tcf_ct_cleanup(struct tc_action *a) { struct tcf_ct_params *params; struct tcf_ct *c = to_ct(a); params = rcu_dereference_protected(c->params, 1); if (params) call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); } static int tcf_ct_dump_key_val(struct sk_buff *skb, void *val, int val_type, void *mask, int mask_type, int len) { int err; if (mask && !memchr_inv(mask, 0, len)) return 0; err = nla_put(skb, val_type, len, val); if (err) return err; if (mask_type != TCA_CT_UNSPEC) { err = nla_put(skb, mask_type, len, mask); if (err) return err; } return 0; } static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p) { struct nf_nat_range2 *range = &p->range; if (!(p->ct_action & TCA_CT_ACT_NAT)) return 0; if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) return 0; if (range->flags & NF_NAT_RANGE_MAP_IPS) { if (p->ipv4_range) { if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MIN, range->min_addr.ip)) return -1; if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MAX, range->max_addr.ip)) return -1; } else { if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MIN, &range->min_addr.in6)) return -1; if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MAX, &range->max_addr.in6)) return -1; } } if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { if (nla_put_be16(skb, TCA_CT_NAT_PORT_MIN, range->min_proto.all)) return -1; if (nla_put_be16(skb, TCA_CT_NAT_PORT_MAX, range->max_proto.all)) return -1; } return 0; } static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper) { if (!helper) return 0; if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) || nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) || nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum)) return -1; return 0; } static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_ct *c = to_ct(a); struct tcf_ct_params *p; struct tc_ct opt = { .index = c->tcf_index, .refcnt = refcount_read(&c->tcf_refcnt) - ref, .bindcnt = atomic_read(&c->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&c->tcf_lock); p = rcu_dereference_protected(c->params, lockdep_is_held(&c->tcf_lock)); opt.action = c->tcf_action; if (tcf_ct_dump_key_val(skb, &p->ct_action, TCA_CT_ACTION, NULL, TCA_CT_UNSPEC, sizeof(p->ct_action))) goto nla_put_failure; if (p->ct_action & TCA_CT_ACT_CLEAR) goto skip_dump; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && tcf_ct_dump_key_val(skb, &p->mark, TCA_CT_MARK, &p->mark_mask, TCA_CT_MARK_MASK, sizeof(p->mark))) goto nla_put_failure; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && tcf_ct_dump_key_val(skb, p->labels, TCA_CT_LABELS, p->labels_mask, TCA_CT_LABELS_MASK, sizeof(p->labels))) goto nla_put_failure; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && tcf_ct_dump_key_val(skb, &p->zone, TCA_CT_ZONE, NULL, TCA_CT_UNSPEC, sizeof(p->zone))) goto nla_put_failure; if (tcf_ct_dump_nat(skb, p)) goto nla_put_failure; if (tcf_ct_dump_helper(skb, p->helper)) goto nla_put_failure; skip_dump: if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &c->tcf_tm); if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD)) goto nla_put_failure; spin_unlock_bh(&c->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&c->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_ct *c = to_ct(a); tcf_action_update_stats(a, bytes, packets, drops, hw); c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse); } static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; if (tcf_ct_helper(act)) return -EOPNOTSUPP; entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); entry->ct.zone = tcf_ct_zone(act); entry->ct.flow_table = tcf_ct_ft(act); *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_CT; } return 0; } static struct tc_action_ops act_ct_ops = { .kind = "ct", .id = TCA_ID_CT, .owner = THIS_MODULE, .act = tcf_ct_act, .dump = tcf_ct_dump, .init = tcf_ct_init, .cleanup = tcf_ct_cleanup, .stats_update = tcf_stats_update, .offload_act_setup = tcf_ct_offload_act_setup, .size = sizeof(struct tcf_ct), }; MODULE_ALIAS_NET_ACT("ct"); static __net_init int ct_init_net(struct net *net) { struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); return tc_action_net_init(net, &tn->tn, &act_ct_ops); } static void __net_exit ct_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_ct_ops.net_id); } static struct pernet_operations ct_net_ops = { .init = ct_init_net, .exit_batch = ct_exit_net, .id = &act_ct_ops.net_id, .size = sizeof(struct tc_ct_action_net), }; static int __init ct_init_module(void) { int err; act_ct_wq = alloc_ordered_workqueue("act_ct_workqueue", 0); if (!act_ct_wq) return -ENOMEM; err = tcf_ct_flow_tables_init(); if (err) goto err_tbl_init; err = tcf_register_action(&act_ct_ops, &ct_net_ops); if (err) goto err_register; static_branch_inc(&tcf_frag_xmit_count); return 0; err_register: tcf_ct_flow_tables_uninit(); err_tbl_init: destroy_workqueue(act_ct_wq); return err; } static void __exit ct_cleanup_module(void) { static_branch_dec(&tcf_frag_xmit_count); tcf_unregister_action(&act_ct_ops, &ct_net_ops); tcf_ct_flow_tables_uninit(); destroy_workqueue(act_ct_wq); } module_init(ct_init_module); module_exit(ct_cleanup_module); MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>"); MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>"); MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>"); MODULE_DESCRIPTION("Connection tracking action"); MODULE_LICENSE("GPL v2"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * taskstats.c - Export per-task statistics to userland * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 * (C) Balbir Singh, IBM Corp. 2006 */ #include <linux/kernel.h> #include <linux/taskstats_kern.h> #include <linux/tsacct_kern.h> #include <linux/acct.h> #include <linux/delayacct.h> #include <linux/cpumask.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/cgroupstats.h> #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/pid_namespace.h> #include <net/genetlink.h> #include <linux/atomic.h> #include <linux/sched/cputime.h> /* * Maximum length of a cpumask that can be specified in * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute */ #define TASKSTATS_CPUMASK_MAXLEN (100+6*NR_CPUS) static DEFINE_PER_CPU(__u32, taskstats_seqnum); static int family_registered; struct kmem_cache *taskstats_cache; static struct genl_family family; static const struct nla_policy taskstats_cmd_get_policy[] = { [TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; static const struct nla_policy cgroupstats_cmd_get_policy[] = { [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, }; struct listener { struct list_head list; pid_t pid; char valid; }; struct listener_list { struct rw_semaphore sem; struct list_head list; }; static DEFINE_PER_CPU(struct listener_list, listener_array); enum actions { REGISTER, DEREGISTER, CPU_DONT_CARE }; static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, size_t size) { struct sk_buff *skb; void *reply; /* * If new attributes are added, please revisit this allocation */ skb = genlmsg_new(size, GFP_KERNEL); if (!skb) return -ENOMEM; if (!info) { int seq = this_cpu_inc_return(taskstats_seqnum) - 1; reply = genlmsg_put(skb, 0, seq, &family, 0, cmd); } else reply = genlmsg_put_reply(skb, info, &family, 0, cmd); if (reply == NULL) { nlmsg_free(skb); return -EINVAL; } *skbp = skb; return 0; } /* * Send taskstats data in @skb to listener with nl_pid @pid */ static int send_reply(struct sk_buff *skb, struct genl_info *info) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); genlmsg_end(skb, reply); return genlmsg_reply(skb, info); } /* * Send taskstats data in @skb to listeners registered for @cpu's exit data */ static void send_cpu_listeners(struct sk_buff *skb, struct listener_list *listeners) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); struct listener *s, *tmp; struct sk_buff *skb_next, *skb_cur = skb; void *reply = genlmsg_data(genlhdr); int delcount = 0; genlmsg_end(skb, reply); down_read(&listeners->sem); list_for_each_entry(s, &listeners->list, list) { int rc; skb_next = NULL; if (!list_is_last(&s->list, &listeners->list)) { skb_next = skb_clone(skb_cur, GFP_KERNEL); if (!skb_next) break; } rc = genlmsg_unicast(&init_net, skb_cur, s->pid); if (rc == -ECONNREFUSED) { s->valid = 0; delcount++; } skb_cur = skb_next; } up_read(&listeners->sem); if (skb_cur) nlmsg_free(skb_cur); if (!delcount) return; /* Delete invalidated entries */ down_write(&listeners->sem); list_for_each_entry_safe(s, tmp, &listeners->list, list) { if (!s->valid) { list_del(&s->list); kfree(s); } } up_write(&listeners->sem); } static void exe_add_tsk(struct taskstats *stats, struct task_struct *tsk) { /* No idea if I'm allowed to access that here, now. */ struct file *exe_file = get_task_exe_file(tsk); if (exe_file) { /* Following cp_new_stat64() in stat.c . */ stats->ac_exe_dev = huge_encode_dev(exe_file->f_inode->i_sb->s_dev); stats->ac_exe_inode = exe_file->f_inode->i_ino; fput(exe_file); } else { stats->ac_exe_dev = 0; stats->ac_exe_inode = 0; } } static void fill_stats(struct user_namespace *user_ns, struct pid_namespace *pid_ns, struct task_struct *tsk, struct taskstats *stats) { memset(stats, 0, sizeof(*stats)); /* * Each accounting subsystem adds calls to its functions to * fill in relevant parts of struct taskstsats as follows * * per-task-foo(stats, tsk); */ delayacct_add_tsk(stats, tsk); /* fill in basic acct fields */ stats->version = TASKSTATS_VERSION; stats->nvcsw = tsk->nvcsw; stats->nivcsw = tsk->nivcsw; bacct_add_tsk(user_ns, pid_ns, stats, tsk); /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); /* add executable info */ exe_add_tsk(stats, tsk); } static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) { struct task_struct *tsk; tsk = find_get_task_by_vpid(pid); if (!tsk) return -ESRCH; fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); put_task_struct(tsk); return 0; } static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) { struct task_struct *tsk, *first; unsigned long flags; int rc = -ESRCH; u64 delta, utime, stime; u64 start_time; /* * Add additional stats from live tasks except zombie thread group * leaders who are already counted with the dead tasks */ rcu_read_lock(); first = find_task_by_vpid(tgid); if (!first || !lock_task_sighand(first, &flags)) goto out; if (first->signal->stats) memcpy(stats, first->signal->stats, sizeof(*stats)); else memset(stats, 0, sizeof(*stats)); start_time = ktime_get_ns(); for_each_thread(first, tsk) { if (tsk->exit_state) continue; /* * Accounting subsystem can call its functions here to * fill in relevant parts of struct taskstsats as follows * * per-task-foo(stats, tsk); */ delayacct_add_tsk(stats, tsk); /* calculate task elapsed time in nsec */ delta = start_time - tsk->start_time; /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); stats->ac_etime += delta; task_cputime(tsk, &utime, &stime); stats->ac_utime += div_u64(utime, NSEC_PER_USEC); stats->ac_stime += div_u64(stime, NSEC_PER_USEC); stats->nvcsw += tsk->nvcsw; stats->nivcsw += tsk->nivcsw; } unlock_task_sighand(first, &flags); rc = 0; out: rcu_read_unlock(); stats->version = TASKSTATS_VERSION; /* * Accounting subsystems can also add calls here to modify * fields of taskstats. */ return rc; } static void fill_tgid_exit(struct task_struct *tsk) { unsigned long flags; spin_lock_irqsave(&tsk->sighand->siglock, flags); if (!tsk->signal->stats) goto ret; /* * Each accounting subsystem calls its functions here to * accumalate its per-task stats for tsk, into the per-tgid structure * * per-task-foo(tsk->signal->stats, tsk); */ delayacct_add_tsk(tsk->signal->stats, tsk); ret: spin_unlock_irqrestore(&tsk->sighand->siglock, flags); return; } static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; struct listener *s, *tmp, *s2; unsigned int cpu; int ret = 0; if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; if (current_user_ns() != &init_user_ns) return -EINVAL; if (task_active_pid_ns(current) != &init_pid_ns) return -EINVAL; if (isadd == REGISTER) { for_each_cpu(cpu, mask) { s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, cpu_to_node(cpu)); if (!s) { ret = -ENOMEM; goto cleanup; } s->pid = pid; s->valid = 1; listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); list_for_each_entry(s2, &listeners->list, list) { if (s2->pid == pid && s2->valid) goto exists; } list_add(&s->list, &listeners->list); s = NULL; exists: up_write(&listeners->sem); kfree(s); /* nop if NULL */ } return 0; } /* Deregister or cleanup */ cleanup: for_each_cpu(cpu, mask) { listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); list_for_each_entry_safe(s, tmp, &listeners->list, list) { if (s->pid == pid) { list_del(&s->list); kfree(s); break; } } up_write(&listeners->sem); } return ret; } static int parse(struct nlattr *na, struct cpumask *mask) { char *data; int len; int ret; if (na == NULL) return 1; len = nla_len(na); if (len > TASKSTATS_CPUMASK_MAXLEN) return -E2BIG; if (len < 1) return -EINVAL; data = kmalloc(len, GFP_KERNEL); if (!data) return -ENOMEM; nla_strscpy(data, na, len); ret = cpulist_parse(data, mask); kfree(data); return ret; } static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) { struct nlattr *na, *ret; int aggr; aggr = (type == TASKSTATS_TYPE_PID) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; na = nla_nest_start_noflag(skb, aggr); if (!na) goto err; if (nla_put(skb, type, sizeof(pid), &pid) < 0) { nla_nest_cancel(skb, na); goto err; } ret = nla_reserve_64bit(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats), TASKSTATS_TYPE_NULL); if (!ret) { nla_nest_cancel(skb, na); goto err; } nla_nest_end(skb, na); return nla_data(ret); err: return NULL; } static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) { int rc = 0; struct sk_buff *rep_skb; struct cgroupstats *stats; struct nlattr *na; size_t size; u32 fd; na = info->attrs[CGROUPSTATS_CMD_ATTR_FD]; if (!na) return -EINVAL; fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); CLASS(fd, f)(fd); if (fd_empty(f)) return 0; size = nla_total_size(sizeof(struct cgroupstats)); rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, sizeof(struct cgroupstats)); if (na == NULL) { nlmsg_free(rep_skb); return -EMSGSIZE; } stats = nla_data(na); memset(stats, 0, sizeof(*stats)); rc = cgroupstats_build(stats, fd_file(f)->f_path.dentry); if (rc < 0) { nlmsg_free(rep_skb); return rc; } return send_reply(rep_skb, info); } static int cmd_attr_register_cpumask(struct genl_info *info) { cpumask_var_t mask; int rc; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) goto out; rc = add_del_listener(info->snd_portid, mask, REGISTER); out: free_cpumask_var(mask); return rc; } static int cmd_attr_deregister_cpumask(struct genl_info *info) { cpumask_var_t mask; int rc; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); if (rc < 0) goto out; rc = add_del_listener(info->snd_portid, mask, DEREGISTER); out: free_cpumask_var(mask); return rc; } static size_t taskstats_packet_size(void) { size_t size; size = nla_total_size(sizeof(u32)) + nla_total_size_64bit(sizeof(struct taskstats)) + nla_total_size(0); return size; } static int cmd_attr_pid(struct genl_info *info) { struct taskstats *stats; struct sk_buff *rep_skb; size_t size; u32 pid; int rc; size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; rc = -EINVAL; pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); if (!stats) goto err; rc = fill_stats_for_pid(pid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } static int cmd_attr_tgid(struct genl_info *info) { struct taskstats *stats; struct sk_buff *rep_skb; size_t size; u32 tgid; int rc; size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; rc = -EINVAL; tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]); stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid); if (!stats) goto err; rc = fill_stats_for_tgid(tgid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) { if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK]) return cmd_attr_register_cpumask(info); else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK]) return cmd_attr_deregister_cpumask(info); else if (info->attrs[TASKSTATS_CMD_ATTR_PID]) return cmd_attr_pid(info); else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) return cmd_attr_tgid(info); else return -EINVAL; } static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct taskstats *stats_new, *stats; /* Pairs with smp_store_release() below. */ stats = smp_load_acquire(&sig->stats); if (stats || thread_group_empty(tsk)) return stats; /* No problem if kmem_cache_zalloc() fails */ stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); stats = sig->stats; if (!stats) { /* * Pairs with smp_store_release() above and order the * kmem_cache_zalloc(). */ smp_store_release(&sig->stats, stats_new); stats = stats_new; stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); if (stats_new) kmem_cache_free(taskstats_cache, stats_new); return stats; } /* Send pid data out on exit */ void taskstats_exit(struct task_struct *tsk, int group_dead) { int rc; struct listener_list *listeners; struct taskstats *stats; struct sk_buff *rep_skb; size_t size; int is_thread_group; if (!family_registered) return; /* * Size includes space for nested attributes */ size = taskstats_packet_size(); is_thread_group = !!taskstats_tgid_alloc(tsk); if (is_thread_group) { /* PID + STATS + TGID + STATS */ size = 2 * size; /* fill the tsk->signal->stats structure */ fill_tgid_exit(tsk); } listeners = raw_cpu_ptr(&listener_array); if (list_empty(&listeners->list)) return; rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return; stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, task_pid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); if (group_dead) stats->ac_flag |= AGROUP; /* * Doesn't matter if tsk is the leader or the last group member leaving */ if (!is_thread_group || !group_dead) goto send; stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, task_tgid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; memcpy(stats, tsk->signal->stats, sizeof(*stats)); send: send_cpu_listeners(rep_skb, listeners); return; err: nlmsg_free(rep_skb); } static const struct genl_ops taskstats_ops[] = { { .cmd = TASKSTATS_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = taskstats_user_cmd, .policy = taskstats_cmd_get_policy, .maxattr = ARRAY_SIZE(taskstats_cmd_get_policy) - 1, .flags = GENL_ADMIN_PERM, }, { .cmd = CGROUPSTATS_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = cgroupstats_user_cmd, .policy = cgroupstats_cmd_get_policy, .maxattr = ARRAY_SIZE(cgroupstats_cmd_get_policy) - 1, }, }; static struct genl_family family __ro_after_init = { .name = TASKSTATS_GENL_NAME, .version = TASKSTATS_GENL_VERSION, .module = THIS_MODULE, .ops = taskstats_ops, .n_ops = ARRAY_SIZE(taskstats_ops), .resv_start_op = CGROUPSTATS_CMD_GET + 1, .netnsok = true, }; /* Needed early in initialization */ void __init taskstats_init_early(void) { unsigned int i; taskstats_cache = KMEM_CACHE(taskstats, SLAB_PANIC); for_each_possible_cpu(i) { INIT_LIST_HEAD(&(per_cpu(listener_array, i).list)); init_rwsem(&(per_cpu(listener_array, i).sem)); } } static int __init taskstats_init(void) { int rc; rc = genl_register_family(&family); if (rc) return rc; family_registered = 1; pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION); return 0; } /* * late initcall ensures initialization of statistics collection * mechanisms precedes initialization of the taskstats interface */ late_initcall(taskstats_init); |
| 339 190 140 140 140 138 140 140 140 20 293 150 147 149 148 149 775 775 16 340 537 197 340 340 340 340 197 197 197 137 124 123 124 13 16 16 110 110 215 214 215 215 215 63 50 4 47 14 14 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* net/core/xdp.c * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> #include <linux/bug.h> #include <net/page_pool/helpers.h> #include <net/hotdata.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> #include <net/xdp_sock_drv.h> #define REG_STATE_NEW 0x0 #define REG_STATE_REGISTERED 0x1 #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 static DEFINE_IDA(mem_id_pool); static DEFINE_MUTEX(mem_id_lock); #define MEM_ID_MAX 0xFFFE #define MEM_ID_MIN 1 static int mem_id_next = MEM_ID_MIN; static bool mem_id_init; /* false */ static struct rhashtable *mem_id_ht; static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) { const u32 *k = data; const u32 key = *k; BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xdp_mem_allocator *xa = ptr; u32 mem_id = *(u32 *)arg->key; return xa->mem.id != mem_id; } static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, .hashfn = xdp_mem_id_hashfn, .obj_cmpfn = xdp_mem_id_cmp, }; static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) { struct xdp_mem_allocator *xa; xa = container_of(rcu, struct xdp_mem_allocator, rcu); /* Allow this ID to be reused */ ida_free(&mem_id_pool, xa->mem.id); kfree(xa); } static void mem_xa_remove(struct xdp_mem_allocator *xa) { trace_mem_disconnect(xa); if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); } static void mem_allocator_disconnect(void *allocator) { struct xdp_mem_allocator *xa; struct rhashtable_iter iter; mutex_lock(&mem_id_lock); rhashtable_walk_enter(mem_id_ht, &iter); do { rhashtable_walk_start(&iter); while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { if (xa->allocator == allocator) mem_xa_remove(xa); } rhashtable_walk_stop(&iter); } while (xa == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); mutex_unlock(&mem_id_lock); } void xdp_unreg_mem_model(struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; int type = mem->type; int id = mem->id; /* Reset mem info to defaults */ mem->id = 0; mem->type = 0; if (id == 0) return; if (type == MEM_TYPE_PAGE_POOL) { xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; } xdp_unreg_mem_model(&xdp_rxq->mem); } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ if (xdp_rxq->reg_state == REG_STATE_UNUSED) return; xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) { memset(xdp_rxq, 0, sizeof(*xdp_rxq)); } /* Returns 0 on success, negative on failure */ int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size) { if (!dev) { WARN(1, "Missing net_device from driver"); return -ENODEV; } if (xdp_rxq->reg_state == REG_STATE_UNUSED) { WARN(1, "Driver promised not to register this"); return -EINVAL; } if (xdp_rxq->reg_state == REG_STATE_REGISTERED) { WARN(1, "Missing unregister, handled but fix driver"); xdp_rxq_info_unreg(xdp_rxq); } /* State either UNREGISTERED or NEW */ xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->reg_state = REG_STATE_UNUSED; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unused); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) { return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); static int __mem_id_init_hash_table(void) { struct rhashtable *rht; int ret; if (unlikely(mem_id_init)) return 0; rht = kzalloc(sizeof(*rht), GFP_KERNEL); if (!rht) return -ENOMEM; ret = rhashtable_init(rht, &mem_id_rht_params); if (ret < 0) { kfree(rht); return ret; } mem_id_ht = rht; smp_mb(); /* mutex lock should provide enough pairing */ mem_id_init = true; return 0; } /* Allocate a cyclic ID that maps to allocator pointer. * See: https://www.kernel.org/doc/html/latest/core-api/idr.html * * Caller must lock mem_id_lock. */ static int __mem_id_cyclic_get(gfp_t gfp) { int retries = 1; int id; again: id = ida_alloc_range(&mem_id_pool, mem_id_next, MEM_ID_MAX - 1, gfp); if (id < 0) { if (id == -ENOSPC) { /* Cyclic allocator, reset next id */ if (retries--) { mem_id_next = MEM_ID_MIN; goto again; } } return id; /* errno */ } mem_id_next = id + 1; return id; } static bool __is_supported_mem_type(enum xdp_mem_type type) { if (type == MEM_TYPE_PAGE_POOL) return is_page_pool_compiled_in(); if (type >= MEM_TYPE_MAX) return false; return true; } static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr; if (!__is_supported_mem_type(type)) return ERR_PTR(-EOPNOTSUPP); mem->type = type; if (!allocator) { if (type == MEM_TYPE_PAGE_POOL) return ERR_PTR(-EINVAL); /* Setup time check page_pool req */ return NULL; } /* Delay init of rhashtable to save memory if feature isn't used */ if (!mem_id_init) { mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); if (ret < 0) return ERR_PTR(ret); } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) return ERR_PTR(-ENOMEM); mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); if (id < 0) { errno = id; goto err; } mem->id = id; xdp_alloc->mem = *mem; xdp_alloc->allocator = allocator; /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { ida_free(&mem_id_pool, mem->id); mem->id = 0; errno = PTR_ERR(ptr); goto err; } if (type == MEM_TYPE_PAGE_POOL) page_pool_use_xdp_mem(allocator, mem_allocator_disconnect, mem); mutex_unlock(&mem_id_lock); return xdp_alloc; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); return ERR_PTR(errno); } int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; xdp_alloc = __xdp_reg_mem_model(mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); return 0; } EXPORT_SYMBOL_GPL(xdp_reg_mem_model); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return -EFAULT; } xdp_alloc = __xdp_reg_mem_model(&xdp_rxq->mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); if (type == MEM_TYPE_XSK_BUFF_POOL && allocator) xsk_pool_set_rxq_info(allocator, xdp_rxq); if (trace_mem_connect_enabled() && xdp_alloc) trace_mem_connect(xdp_alloc, xdp_rxq); return 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /** * xdp_reg_page_pool - register &page_pool as a memory provider for XDP * @pool: &page_pool to register * * Can be used to register pools manually without connecting to any XDP RxQ * info, so that the XDP layer will be aware of them. Then, they can be * attached to an RxQ info manually via xdp_rxq_info_attach_page_pool(). * * Return: %0 on success, -errno on error. */ int xdp_reg_page_pool(struct page_pool *pool) { struct xdp_mem_info mem; return xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pool); } EXPORT_SYMBOL_GPL(xdp_reg_page_pool); /** * xdp_unreg_page_pool - unregister &page_pool from the memory providers list * @pool: &page_pool to unregister * * A shorthand for manual unregistering page pools. If the pool was previously * attached to an RxQ info, it must be detached first. */ void xdp_unreg_page_pool(const struct page_pool *pool) { struct xdp_mem_info mem = { .type = MEM_TYPE_PAGE_POOL, .id = pool->xdp_mem_id, }; xdp_unreg_mem_model(&mem); } EXPORT_SYMBOL_GPL(xdp_unreg_page_pool); /** * xdp_rxq_info_attach_page_pool - attach registered pool to RxQ info * @xdp_rxq: XDP RxQ info to attach the pool to * @pool: pool to attach * * If the pool was registered manually, this function must be called instead * of xdp_rxq_info_reg_mem_model() to connect it to the RxQ info. */ void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, const struct page_pool *pool) { struct xdp_mem_info mem = { .type = MEM_TYPE_PAGE_POOL, .id = pool->xdp_mem_id, }; xdp_rxq_info_attach_mem_model(xdp_rxq, &mem); } EXPORT_SYMBOL_GPL(xdp_rxq_info_attach_page_pool); /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, bool napi_direct, struct xdp_buff *xdp) { switch (mem_type) { case MEM_TYPE_PAGE_POOL: netmem = netmem_compound_head(netmem); if (napi_direct && xdp_return_frame_no_direct()) napi_direct = false; /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) * as mem->type knows this a page_pool page */ page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, napi_direct); break; case MEM_TYPE_PAGE_SHARED: page_frag_free(__netmem_address(netmem)); break; case MEM_TYPE_PAGE_ORDER0: put_page(__netmem_to_page(netmem)); break; case MEM_TYPE_XSK_BUFF_POOL: /* NB! Only valid from an xdp_buff! */ xsk_buff_free(xdp); break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem_type); break; } } void xdp_return_frame(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, false, NULL); out: __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, true, NULL); out: __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); /* XDP bulk APIs introduce a defer/flush mechanism to return * pages belonging to the same xdp_mem_allocator object * (identified via the mem.id field) in bulk to optimize * I-cache and D-cache. * The bulk queue size is set to 16 to be aligned to how * XDP_REDIRECT bulking works. The bulk is flushed when * it is full or when mem.id changes. * xdp_frame_bulk is usually stored/allocated on the function * call-stack to avoid locking penalties. */ /* Must be called with rcu_read_lock held */ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq) { if (xdpf->mem_type != MEM_TYPE_PAGE_POOL) { xdp_return_frame(xdpf); return; } if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); if (unlikely(xdp_frame_has_frags(xdpf))) { struct skb_shared_info *sinfo; int i; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { skb_frag_t *frag = &sinfo->frags[i]; bq->q[bq->count++] = skb_frag_netmem(frag); if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); } } bq->q[bq->count++] = virt_to_netmem(xdpf->data); } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); /** * xdp_return_frag -- free one XDP frag or decrement its refcount * @netmem: network memory reference to release * @xdp: &xdp_buff to release the frag for */ void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp) { __xdp_return(netmem, xdp->rxq->mem.type, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frag); void xdp_return_buff(struct xdp_buff *xdp) { struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdp->rxq->mem.type, true, xdp); out: __xdp_return(virt_to_netmem(xdp->data), xdp->rxq->mem.type, true, xdp); } EXPORT_SYMBOL_GPL(xdp_return_buff); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { if (info->prog) bpf_prog_put(info->prog); info->prog = bpf->prog; info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) { unsigned int metasize, totsize; void *addr, *data_to_copy; struct xdp_frame *xdpf; struct page *page; /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ metasize = xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; totsize = xdp->data_end - xdp->data + metasize; if (sizeof(*xdpf) + totsize > PAGE_SIZE) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); xdpf = addr; memset(xdpf, 0, sizeof(*xdpf)); addr += sizeof(*xdpf); data_to_copy = metasize ? xdp->data_meta : xdp->data; memcpy(addr, data_to_copy, totsize); xdpf->data = addr + metasize; xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; xdpf->mem_type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); return xdpf; } EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); /* Used by XDP_WARN macro, to avoid inlining WARN() in fast-path */ void xdp_warn(const char *msg, const char *func, const int line) { WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg); }; EXPORT_SYMBOL_GPL(xdp_warn); /** * xdp_build_skb_from_buff - create an skb from &xdp_buff * @xdp: &xdp_buff to convert to an skb * * Perform common operations to create a new skb to pass up the stack from * &xdp_buff: allocate an skb head from the NAPI percpu cache, initialize * skb data pointers and offsets, set the recycle bit if the buff is * PP-backed, Rx queue index, protocol and update frags info. * * Return: new &sk_buff on success, %NULL on error. */ struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp) { const struct xdp_rxq_info *rxq = xdp->rxq; const struct skb_shared_info *sinfo; struct sk_buff *skb; u32 nr_frags = 0; int metalen; if (unlikely(xdp_buff_has_frags(xdp))) { sinfo = xdp_get_shared_info_from_buff(xdp); nr_frags = sinfo->nr_frags; } skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) return NULL; skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); metalen = xdp->data - xdp->data_meta; if (metalen > 0) skb_metadata_set(skb, metalen); if (rxq->mem.type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); skb_record_rx_queue(skb, rxq->queue_index); if (unlikely(nr_frags)) { u32 tsize; tsize = sinfo->xdp_frags_truesize ? : nr_frags * xdp->frame_sz; xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, tsize, xdp_buff_is_frag_pfmemalloc(xdp)); } skb->protocol = eth_type_trans(skb, rxq->dev); return skb; } EXPORT_SYMBOL_GPL(xdp_build_skb_from_buff); /** * xdp_copy_frags_from_zc - copy frags from XSk buff to skb * @skb: skb to copy frags to * @xdp: XSk &xdp_buff from which the frags will be copied * @pp: &page_pool backing page allocation, if available * * Copy all frags from XSk &xdp_buff to the skb to pass it up the stack. * Allocate a new buffer for each frag, copy it and attach to the skb. * * Return: true on success, false on netmem allocation fail. */ static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb, const struct xdp_buff *xdp, struct page_pool *pp) { struct skb_shared_info *sinfo = skb_shinfo(skb); const struct skb_shared_info *xinfo; u32 nr_frags, tsize = 0; bool pfmemalloc = false; xinfo = xdp_get_shared_info_from_buff(xdp); nr_frags = xinfo->nr_frags; for (u32 i = 0; i < nr_frags; i++) { u32 len = skb_frag_size(&xinfo->frags[i]); u32 offset, truesize = len; netmem_ref netmem; netmem = page_pool_dev_alloc_netmem(pp, &offset, &truesize); if (unlikely(!netmem)) { sinfo->nr_frags = i; return false; } memcpy(__netmem_address(netmem), __netmem_address(xinfo->frags[i].netmem), LARGEST_ALIGN(len)); __skb_fill_netmem_desc_noacc(sinfo, i, netmem, offset, len); tsize += truesize; pfmemalloc |= netmem_is_pfmemalloc(netmem); } xdp_update_skb_shared_info(skb, nr_frags, xinfo->xdp_frags_size, tsize, pfmemalloc); return true; } /** * xdp_build_skb_from_zc - create an skb from XSk &xdp_buff * @xdp: source XSk buff * * Similar to xdp_build_skb_from_buff(), but for XSk frames. Allocate an skb * head, new buffer for the head, copy the data and initialize the skb fields. * If there are frags, allocate new buffers for them and copy. * Buffers are allocated from the system percpu pools to try recycling them. * If new skb was built successfully, @xdp is returned to XSk pool's freelist. * On error, it remains untouched and the caller must take care of this. * * Return: new &sk_buff on success, %NULL on error. */ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp) { struct page_pool *pp = this_cpu_read(system_page_pool); const struct xdp_rxq_info *rxq = xdp->rxq; u32 len = xdp->data_end - xdp->data_meta; u32 truesize = xdp->frame_sz; struct sk_buff *skb; int metalen; void *data; if (!IS_ENABLED(CONFIG_PAGE_POOL)) return NULL; data = page_pool_dev_alloc_va(pp, &truesize); if (unlikely(!data)) return NULL; skb = napi_build_skb(data, truesize); if (unlikely(!skb)) { page_pool_free_va(pp, data, true); return NULL; } skb_mark_for_recycle(skb); skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); memcpy(__skb_put(skb, len), xdp->data_meta, LARGEST_ALIGN(len)); metalen = xdp->data - xdp->data_meta; if (metalen > 0) { skb_metadata_set(skb, metalen); __skb_pull(skb, metalen); } skb_record_rx_queue(skb, rxq->queue_index); if (unlikely(xdp_buff_has_frags(xdp)) && unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) { napi_consume_skb(skb, true); return NULL; } xsk_buff_free(xdp); skb->protocol = eth_type_trans(skb, rxq->dev); return skb; } EXPORT_SYMBOL_GPL(xdp_build_skb_from_zc); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); unsigned int headroom, frame_size; void *hard_start; u8 nr_frags; /* xdp frags frame */ if (unlikely(xdp_frame_has_frags(xdpf))) nr_frags = sinfo->nr_frags; /* Part of headroom was reserved to xdpf */ headroom = sizeof(*xdpf) + xdpf->headroom; /* Memory size backing xdp_frame data already have reserved * room for build_skb to place skb_shared_info in tailroom. */ frame_size = xdpf->frame_sz; hard_start = xdpf->data - headroom; skb = build_skb_around(skb, hard_start, frame_size); if (unlikely(!skb)) return NULL; skb_reserve(skb, headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); if (unlikely(xdp_frame_has_frags(xdpf))) xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, nr_frags * xdpf->frame_sz, xdp_frame_is_frag_pfmemalloc(xdpf)); /* Essential SKB info: protocol and skb->dev */ skb->protocol = eth_type_trans(skb, dev); /* Optional SKB info, currently missing: * - HW checksum info (skb->ip_summed) * - HW RX hash (skb_set_hash) * - RX ring dev queue index (skb_record_rx_queue) */ if (xdpf->mem_type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); /* Allow SKB to reuse area used by xdp_frame */ xdp_scrub_frame(xdpf); return skb; } EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev) { struct sk_buff *skb; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) { unsigned int headroom, totalsize; struct xdp_frame *nxdpf; struct page *page; void *addr; headroom = xdpf->headroom + sizeof(*xdpf); totalsize = headroom + xdpf->len; if (unlikely(totalsize > PAGE_SIZE)) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); memcpy(addr, xdpf, totalsize); nxdpf = addr; nxdpf->data = addr + headroom; nxdpf->frame_sz = PAGE_SIZE; nxdpf->mem_type = MEM_TYPE_PAGE_ORDER0; return nxdpf; } __bpf_kfunc_start_defs(); /** * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp. * @ctx: XDP context pointer. * @timestamp: Return value pointer. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc * * ``-ENODATA`` : means no RX-timestamp available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. * @rss_type: Return value pointer for RSS type. * * The RSS hash type (@rss_type) specifies what portion of packet headers NIC * hardware used when calculating RSS hash value. The RSS type can be decoded * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag * @ctx: XDP context pointer. * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID). * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP) * * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*, * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)** * and should be used as follows: * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();`` * * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag. * Driver is expected to provide those in **host byte order (usually LE)**, * so the bpf program should not perform byte conversion. * According to 802.1Q standard, *VLAN TCI (Tag control information)* * is a bit field that contains: * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``, * *Drop eligible indicator (DEI)* - 1 bit, * *Priority code point (PCP)* - 3 bits. * For detailed meaning of DEI and PCP, please refer to other sources. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc * * ``-ENODATA`` : VLAN tag was not stripped or is not available */ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { return -EOPNOTSUPP; } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(xdp_metadata_kfunc_ids) #define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC BTF_KFUNCS_END(xdp_metadata_kfunc_ids) static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = { .owner = THIS_MODULE, .set = &xdp_metadata_kfunc_ids, }; BTF_ID_LIST(xdp_metadata_kfunc_ids_unsorted) #define XDP_METADATA_KFUNC(name, _, str, __) BTF_ID(func, str) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC u32 bpf_xdp_metadata_kfunc_id(int id) { /* xdp_metadata_kfunc_ids is sorted and can't be used */ return xdp_metadata_kfunc_ids_unsorted[id]; } bool bpf_dev_bound_kfunc_id(u32 btf_id) { return btf_id_set8_contains(&xdp_metadata_kfunc_ids, btf_id); } static int __init xdp_metadata_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set); } late_initcall(xdp_metadata_init); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { val &= NETDEV_XDP_ACT_MASK; if (dev->xdp_features == val) return; dev->xdp_features = val; if (dev->reg_state == NETREG_REGISTERED) call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); } EXPORT_SYMBOL_GPL(xdp_set_features_flag); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT); if (support_sg) val |= NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); void xdp_features_clear_redirect_target(struct net_device *dev) { xdp_features_t val = dev->xdp_features; val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG); xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target); |
| 278 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 | // SPDX-License-Identifier: GPL-2.0 /* * Creating audit events from TTY input. * * Copyright (C) 2007 Red Hat, Inc. All rights reserved. * * Authors: Miloslav Trmac <mitr@redhat.com> */ #include <linux/audit.h> #include <linux/slab.h> #include <linux/tty.h> #include "tty.h" #define TTY_AUDIT_BUF_SIZE 4096 struct tty_audit_buf { struct mutex mutex; /* Protects all data below */ dev_t dev; /* The TTY which the data is from */ bool icanon; size_t valid; u8 *data; /* Allocated size TTY_AUDIT_BUF_SIZE */ }; static struct tty_audit_buf *tty_audit_buf_ref(void) { struct tty_audit_buf *buf; buf = current->signal->tty_audit_buf; WARN_ON(buf == ERR_PTR(-ESRCH)); return buf; } static struct tty_audit_buf *tty_audit_buf_alloc(void) { struct tty_audit_buf *buf; buf = kzalloc(sizeof(*buf), GFP_KERNEL); if (!buf) goto err; buf->data = kmalloc(TTY_AUDIT_BUF_SIZE, GFP_KERNEL); if (!buf->data) goto err_buf; mutex_init(&buf->mutex); return buf; err_buf: kfree(buf); err: return NULL; } static void tty_audit_buf_free(struct tty_audit_buf *buf) { WARN_ON(buf->valid != 0); kfree(buf->data); kfree(buf); } static void tty_audit_log(const char *description, dev_t dev, const u8 *data, size_t size) { struct audit_buffer *ab; pid_t pid = task_pid_nr(current); uid_t uid = from_kuid(&init_user_ns, task_uid(current)); uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current)); unsigned int sessionid = audit_get_sessionid(current); char name[TASK_COMM_LEN]; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_TTY); if (!ab) return; audit_log_format(ab, "%s pid=%u uid=%u auid=%u ses=%u major=%d minor=%d comm=", description, pid, uid, loginuid, sessionid, MAJOR(dev), MINOR(dev)); get_task_comm(name, current); audit_log_untrustedstring(ab, name); audit_log_format(ab, " data="); audit_log_n_hex(ab, data, size); audit_log_end(ab); } /* * tty_audit_buf_push - Push buffered data out * * Generate an audit message from the contents of @buf, which is owned by * the current task. @buf->mutex must be locked. */ static void tty_audit_buf_push(struct tty_audit_buf *buf) { if (buf->valid == 0) return; if (audit_enabled == AUDIT_OFF) { buf->valid = 0; return; } tty_audit_log("tty", buf->dev, buf->data, buf->valid); buf->valid = 0; } /** * tty_audit_exit - Handle a task exit * * Make sure all buffered data is written out and deallocate the buffer. * Only needs to be called if current->signal->tty_audit_buf != %NULL. * * The process is single-threaded at this point; no other threads share * current->signal. */ void tty_audit_exit(void) { struct tty_audit_buf *buf; buf = xchg(¤t->signal->tty_audit_buf, ERR_PTR(-ESRCH)); if (!buf) return; tty_audit_buf_push(buf); tty_audit_buf_free(buf); } /* * tty_audit_fork - Copy TTY audit state for a new task * * Set up TTY audit state in @sig from current. @sig needs no locking. */ void tty_audit_fork(struct signal_struct *sig) { sig->audit_tty = current->signal->audit_tty; } /* * tty_audit_tiocsti - Log TIOCSTI */ void tty_audit_tiocsti(const struct tty_struct *tty, u8 ch) { dev_t dev; dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; if (tty_audit_push()) return; if (audit_enabled) tty_audit_log("ioctl=TIOCSTI", dev, &ch, 1); } /* * tty_audit_push - Flush current's pending audit data * * Returns 0 if success, -EPERM if tty audit is disabled */ int tty_audit_push(void) { struct tty_audit_buf *buf; if (~current->signal->audit_tty & AUDIT_TTY_ENABLE) return -EPERM; buf = tty_audit_buf_ref(); if (!IS_ERR_OR_NULL(buf)) { mutex_lock(&buf->mutex); tty_audit_buf_push(buf); mutex_unlock(&buf->mutex); } return 0; } /* * tty_audit_buf_get - Get an audit buffer. * * Get an audit buffer, allocate it if necessary. Return %NULL * if out of memory or ERR_PTR(-ESRCH) if tty_audit_exit() has already * occurred. Otherwise, return a new reference to the buffer. */ static struct tty_audit_buf *tty_audit_buf_get(void) { struct tty_audit_buf *buf; buf = tty_audit_buf_ref(); if (buf) return buf; buf = tty_audit_buf_alloc(); if (buf == NULL) { audit_log_lost("out of memory in TTY auditing"); return NULL; } /* Race to use this buffer, free it if another wins */ if (cmpxchg(¤t->signal->tty_audit_buf, NULL, buf) != NULL) tty_audit_buf_free(buf); return tty_audit_buf_ref(); } /* * tty_audit_add_data - Add data for TTY auditing. * * Audit @data of @size from @tty, if necessary. */ void tty_audit_add_data(const struct tty_struct *tty, const void *data, size_t size) { struct tty_audit_buf *buf; unsigned int audit_tty; bool icanon = L_ICANON(tty); dev_t dev; audit_tty = READ_ONCE(current->signal->audit_tty); if (~audit_tty & AUDIT_TTY_ENABLE) return; if (unlikely(size == 0)) return; if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) return; if ((~audit_tty & AUDIT_TTY_LOG_PASSWD) && icanon && !L_ECHO(tty)) return; buf = tty_audit_buf_get(); if (IS_ERR_OR_NULL(buf)) return; mutex_lock(&buf->mutex); dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; if (buf->dev != dev || buf->icanon != icanon) { tty_audit_buf_push(buf); buf->dev = dev; buf->icanon = icanon; } do { size_t run; run = TTY_AUDIT_BUF_SIZE - buf->valid; if (run > size) run = size; memcpy(buf->data + buf->valid, data, run); buf->valid += run; data += run; size -= run; if (buf->valid == TTY_AUDIT_BUF_SIZE) tty_audit_buf_push(buf); } while (size != 0); mutex_unlock(&buf->mutex); } |
| 17 24 7 24 24 24 7 24 24 24 24 4 7 7 7 7 7 7 7 7 7 7 7 7 24 23 7 24 7 24 7 7 7 24 24 24 7 7 4 17 17 17 17 7 24 17 17 17 17 17 17 17 4 4 4 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Scatterlist Cryptographic API. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 David S. Miller (davem@redhat.com) * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> * * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no> * and Nettle, by Niels Möller. */ #include <linux/err.h> #include <linux/errno.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/module.h> #include <linux/param.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/completion.h> #include "internal.h" LIST_HEAD(crypto_alg_list); EXPORT_SYMBOL_GPL(crypto_alg_list); DECLARE_RWSEM(crypto_alg_sem); EXPORT_SYMBOL_GPL(crypto_alg_sem); BLOCKING_NOTIFIER_HEAD(crypto_chain); EXPORT_SYMBOL_GPL(crypto_chain); #if IS_BUILTIN(CONFIG_CRYPTO_ALGAPI) && \ !IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) DEFINE_STATIC_KEY_FALSE(__crypto_boot_test_finished); #endif static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg, u32 type, u32 mask); static struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, u32 mask); struct crypto_alg *crypto_mod_get(struct crypto_alg *alg) { return try_module_get(alg->cra_module) ? crypto_alg_get(alg) : NULL; } EXPORT_SYMBOL_GPL(crypto_mod_get); void crypto_mod_put(struct crypto_alg *alg) { struct module *module = alg->cra_module; crypto_alg_put(alg); module_put(module); } EXPORT_SYMBOL_GPL(crypto_mod_put); static struct crypto_alg *__crypto_alg_lookup(const char *name, u32 type, u32 mask) { struct crypto_alg *q, *alg = NULL; int best = -2; list_for_each_entry(q, &crypto_alg_list, cra_list) { int exact, fuzzy; if (crypto_is_moribund(q)) continue; if ((q->cra_flags ^ type) & mask) continue; exact = !strcmp(q->cra_driver_name, name); fuzzy = !strcmp(q->cra_name, name); if (!exact && !(fuzzy && q->cra_priority > best)) continue; if (unlikely(!crypto_mod_get(q))) continue; best = q->cra_priority; if (alg) crypto_mod_put(alg); alg = q; if (exact) break; } return alg; } static void crypto_larval_destroy(struct crypto_alg *alg) { struct crypto_larval *larval = (void *)alg; BUG_ON(!crypto_is_larval(alg)); if (!IS_ERR_OR_NULL(larval->adult)) crypto_mod_put(larval->adult); kfree(larval); } struct crypto_larval *crypto_larval_alloc(const char *name, u32 type, u32 mask) { struct crypto_larval *larval; larval = kzalloc(sizeof(*larval), GFP_KERNEL); if (!larval) return ERR_PTR(-ENOMEM); type &= ~CRYPTO_ALG_TYPE_MASK | (mask ?: CRYPTO_ALG_TYPE_MASK); larval->mask = mask; larval->alg.cra_flags = CRYPTO_ALG_LARVAL | type; larval->alg.cra_priority = -1; larval->alg.cra_destroy = crypto_larval_destroy; strscpy(larval->alg.cra_name, name, CRYPTO_MAX_ALG_NAME); init_completion(&larval->completion); return larval; } EXPORT_SYMBOL_GPL(crypto_larval_alloc); static struct crypto_alg *crypto_larval_add(const char *name, u32 type, u32 mask) { struct crypto_alg *alg; struct crypto_larval *larval; larval = crypto_larval_alloc(name, type, mask); if (IS_ERR(larval)) return ERR_CAST(larval); refcount_set(&larval->alg.cra_refcnt, 2); down_write(&crypto_alg_sem); alg = __crypto_alg_lookup(name, type, mask); if (!alg) { alg = &larval->alg; list_add(&alg->cra_list, &crypto_alg_list); } up_write(&crypto_alg_sem); if (alg != &larval->alg) { kfree(larval); if (crypto_is_larval(alg)) alg = crypto_larval_wait(alg, type, mask); } return alg; } static void crypto_larval_kill(struct crypto_larval *larval) { bool unlinked; down_write(&crypto_alg_sem); unlinked = list_empty(&larval->alg.cra_list); if (!unlinked) list_del_init(&larval->alg.cra_list); up_write(&crypto_alg_sem); if (unlinked) return; complete_all(&larval->completion); crypto_alg_put(&larval->alg); } void crypto_schedule_test(struct crypto_larval *larval) { int err; err = crypto_probing_notify(CRYPTO_MSG_ALG_REGISTER, larval->adult); WARN_ON_ONCE(err != NOTIFY_STOP); } EXPORT_SYMBOL_GPL(crypto_schedule_test); static void crypto_start_test(struct crypto_larval *larval) { if (!crypto_is_test_larval(larval)) return; if (larval->test_started) return; down_write(&crypto_alg_sem); if (larval->test_started) { up_write(&crypto_alg_sem); return; } larval->test_started = true; up_write(&crypto_alg_sem); crypto_schedule_test(larval); } static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg, u32 type, u32 mask) { struct crypto_larval *larval; long time_left; again: larval = container_of(alg, struct crypto_larval, alg); if (!crypto_boot_test_finished()) crypto_start_test(larval); time_left = wait_for_completion_killable_timeout( &larval->completion, 60 * HZ); alg = larval->adult; if (time_left < 0) alg = ERR_PTR(-EINTR); else if (!time_left) { if (crypto_is_test_larval(larval)) crypto_larval_kill(larval); alg = ERR_PTR(-ETIMEDOUT); } else if (!alg) { alg = &larval->alg; alg = crypto_alg_lookup(alg->cra_name, type, mask) ?: ERR_PTR(-EAGAIN); } else if (IS_ERR(alg)) ; else if (crypto_is_test_larval(larval) && !(alg->cra_flags & CRYPTO_ALG_TESTED)) alg = ERR_PTR(-EAGAIN); else if (alg->cra_flags & CRYPTO_ALG_FIPS_INTERNAL) alg = ERR_PTR(-EAGAIN); else if (!crypto_mod_get(alg)) alg = ERR_PTR(-EAGAIN); crypto_mod_put(&larval->alg); if (!IS_ERR(alg) && crypto_is_larval(alg)) goto again; return alg; } static struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, u32 mask) { const u32 fips = CRYPTO_ALG_FIPS_INTERNAL; struct crypto_alg *alg; u32 test = 0; if (!((type | mask) & CRYPTO_ALG_TESTED)) test |= CRYPTO_ALG_TESTED; down_read(&crypto_alg_sem); alg = __crypto_alg_lookup(name, (type | test) & ~fips, (mask | test) & ~fips); if (alg) { if (((type | mask) ^ fips) & fips) mask |= fips; mask &= fips; if (!crypto_is_larval(alg) && ((type ^ alg->cra_flags) & mask)) { /* Algorithm is disallowed in FIPS mode. */ crypto_mod_put(alg); alg = ERR_PTR(-ENOENT); } } else if (test) { alg = __crypto_alg_lookup(name, type, mask); if (alg && !crypto_is_larval(alg)) { /* Test failed */ crypto_mod_put(alg); alg = ERR_PTR(-ELIBBAD); } } up_read(&crypto_alg_sem); return alg; } static struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask) { struct crypto_alg *alg; if (!name) return ERR_PTR(-ENOENT); type &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD); mask &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD); alg = crypto_alg_lookup(name, type, mask); if (!alg && !(mask & CRYPTO_NOLOAD)) { request_module("crypto-%s", name); if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask & CRYPTO_ALG_NEED_FALLBACK)) request_module("crypto-%s-all", name); alg = crypto_alg_lookup(name, type, mask); } if (!IS_ERR_OR_NULL(alg) && crypto_is_larval(alg)) alg = crypto_larval_wait(alg, type, mask); else if (alg) ; else if (!(mask & CRYPTO_ALG_TESTED)) alg = crypto_larval_add(name, type, mask); else alg = ERR_PTR(-ENOENT); return alg; } int crypto_probing_notify(unsigned long val, void *v) { int ok; ok = blocking_notifier_call_chain(&crypto_chain, val, v); if (ok == NOTIFY_DONE) { request_module("cryptomgr"); ok = blocking_notifier_call_chain(&crypto_chain, val, v); } return ok; } EXPORT_SYMBOL_GPL(crypto_probing_notify); struct crypto_alg *crypto_alg_mod_lookup(const char *name, u32 type, u32 mask) { struct crypto_alg *alg; struct crypto_alg *larval; int ok; /* * If the internal flag is set for a cipher, require a caller to * invoke the cipher with the internal flag to use that cipher. * Also, if a caller wants to allocate a cipher that may or may * not be an internal cipher, use type | CRYPTO_ALG_INTERNAL and * !(mask & CRYPTO_ALG_INTERNAL). */ if (!((type | mask) & CRYPTO_ALG_INTERNAL)) mask |= CRYPTO_ALG_INTERNAL; larval = crypto_larval_lookup(name, type, mask); if (IS_ERR(larval) || !crypto_is_larval(larval)) return larval; ok = crypto_probing_notify(CRYPTO_MSG_ALG_REQUEST, larval); if (ok == NOTIFY_STOP) alg = crypto_larval_wait(larval, type, mask); else { crypto_mod_put(larval); alg = ERR_PTR(-ENOENT); } crypto_larval_kill(container_of(larval, struct crypto_larval, alg)); return alg; } EXPORT_SYMBOL_GPL(crypto_alg_mod_lookup); static void crypto_exit_ops(struct crypto_tfm *tfm) { const struct crypto_type *type = tfm->__crt_alg->cra_type; if (type && tfm->exit) tfm->exit(tfm); } static unsigned int crypto_ctxsize(struct crypto_alg *alg, u32 type, u32 mask) { const struct crypto_type *type_obj = alg->cra_type; unsigned int len; len = alg->cra_alignmask & ~(crypto_tfm_ctx_alignment() - 1); if (type_obj) return len + type_obj->ctxsize(alg, type, mask); switch (alg->cra_flags & CRYPTO_ALG_TYPE_MASK) { default: BUG(); case CRYPTO_ALG_TYPE_CIPHER: len += crypto_cipher_ctxsize(alg); break; } return len; } void crypto_shoot_alg(struct crypto_alg *alg) { down_write(&crypto_alg_sem); alg->cra_flags |= CRYPTO_ALG_DYING; up_write(&crypto_alg_sem); } EXPORT_SYMBOL_GPL(crypto_shoot_alg); struct crypto_tfm *__crypto_alloc_tfmgfp(struct crypto_alg *alg, u32 type, u32 mask, gfp_t gfp) { struct crypto_tfm *tfm; unsigned int tfm_size; int err = -ENOMEM; tfm_size = sizeof(*tfm) + crypto_ctxsize(alg, type, mask); tfm = kzalloc(tfm_size, gfp); if (tfm == NULL) goto out_err; tfm->__crt_alg = alg; refcount_set(&tfm->refcnt, 1); if (!tfm->exit && alg->cra_init && (err = alg->cra_init(tfm))) goto cra_init_failed; goto out; cra_init_failed: crypto_exit_ops(tfm); if (err == -EAGAIN) crypto_shoot_alg(alg); kfree(tfm); out_err: tfm = ERR_PTR(err); out: return tfm; } EXPORT_SYMBOL_GPL(__crypto_alloc_tfmgfp); struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type, u32 mask) { return __crypto_alloc_tfmgfp(alg, type, mask, GFP_KERNEL); } EXPORT_SYMBOL_GPL(__crypto_alloc_tfm); /* * crypto_alloc_base - Locate algorithm and allocate transform * @alg_name: Name of algorithm * @type: Type of algorithm * @mask: Mask for type comparison * * This function should not be used by new algorithm types. * Please use crypto_alloc_tfm instead. * * crypto_alloc_base() will first attempt to locate an already loaded * algorithm. If that fails and the kernel supports dynamically loadable * modules, it will then attempt to load a module of the same name or * alias. If that fails it will send a query to any loaded crypto manager * to construct an algorithm on the fly. A refcount is grabbed on the * algorithm which is then associated with the new transform. * * The returned transform is of a non-determinate type. Most people * should use one of the more specific allocation functions such as * crypto_alloc_skcipher(). * * In case of error the return value is an error pointer. */ struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask) { struct crypto_tfm *tfm; int err; for (;;) { struct crypto_alg *alg; alg = crypto_alg_mod_lookup(alg_name, type, mask); if (IS_ERR(alg)) { err = PTR_ERR(alg); goto err; } tfm = __crypto_alloc_tfm(alg, type, mask); if (!IS_ERR(tfm)) return tfm; crypto_mod_put(alg); err = PTR_ERR(tfm); err: if (err != -EAGAIN) break; if (fatal_signal_pending(current)) { err = -EINTR; break; } } return ERR_PTR(err); } EXPORT_SYMBOL_GPL(crypto_alloc_base); static void *crypto_alloc_tfmmem(struct crypto_alg *alg, const struct crypto_type *frontend, int node, gfp_t gfp) { struct crypto_tfm *tfm; unsigned int tfmsize; unsigned int total; char *mem; tfmsize = frontend->tfmsize; total = tfmsize + sizeof(*tfm) + frontend->extsize(alg); mem = kzalloc_node(total, gfp, node); if (mem == NULL) return ERR_PTR(-ENOMEM); tfm = (struct crypto_tfm *)(mem + tfmsize); tfm->__crt_alg = alg; tfm->node = node; refcount_set(&tfm->refcnt, 1); return mem; } void *crypto_create_tfm_node(struct crypto_alg *alg, const struct crypto_type *frontend, int node) { struct crypto_tfm *tfm; char *mem; int err; mem = crypto_alloc_tfmmem(alg, frontend, node, GFP_KERNEL); if (IS_ERR(mem)) goto out; tfm = (struct crypto_tfm *)(mem + frontend->tfmsize); err = frontend->init_tfm(tfm); if (err) goto out_free_tfm; if (!tfm->exit && alg->cra_init && (err = alg->cra_init(tfm))) goto cra_init_failed; goto out; cra_init_failed: crypto_exit_ops(tfm); out_free_tfm: if (err == -EAGAIN) crypto_shoot_alg(alg); kfree(mem); mem = ERR_PTR(err); out: return mem; } EXPORT_SYMBOL_GPL(crypto_create_tfm_node); void *crypto_clone_tfm(const struct crypto_type *frontend, struct crypto_tfm *otfm) { struct crypto_alg *alg = otfm->__crt_alg; struct crypto_tfm *tfm; char *mem; mem = ERR_PTR(-ESTALE); if (unlikely(!crypto_mod_get(alg))) goto out; mem = crypto_alloc_tfmmem(alg, frontend, otfm->node, GFP_ATOMIC); if (IS_ERR(mem)) { crypto_mod_put(alg); goto out; } tfm = (struct crypto_tfm *)(mem + frontend->tfmsize); tfm->crt_flags = otfm->crt_flags; tfm->exit = otfm->exit; out: return mem; } EXPORT_SYMBOL_GPL(crypto_clone_tfm); struct crypto_alg *crypto_find_alg(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask) { if (frontend) { type &= frontend->maskclear; mask &= frontend->maskclear; type |= frontend->type; mask |= frontend->maskset; } return crypto_alg_mod_lookup(alg_name, type, mask); } EXPORT_SYMBOL_GPL(crypto_find_alg); /* * crypto_alloc_tfm_node - Locate algorithm and allocate transform * @alg_name: Name of algorithm * @frontend: Frontend algorithm type * @type: Type of algorithm * @mask: Mask for type comparison * @node: NUMA node in which users desire to put requests, if node is * NUMA_NO_NODE, it means users have no special requirement. * * crypto_alloc_tfm() will first attempt to locate an already loaded * algorithm. If that fails and the kernel supports dynamically loadable * modules, it will then attempt to load a module of the same name or * alias. If that fails it will send a query to any loaded crypto manager * to construct an algorithm on the fly. A refcount is grabbed on the * algorithm which is then associated with the new transform. * * The returned transform is of a non-determinate type. Most people * should use one of the more specific allocation functions such as * crypto_alloc_skcipher(). * * In case of error the return value is an error pointer. */ void *crypto_alloc_tfm_node(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask, int node) { void *tfm; int err; for (;;) { struct crypto_alg *alg; alg = crypto_find_alg(alg_name, frontend, type, mask); if (IS_ERR(alg)) { err = PTR_ERR(alg); goto err; } tfm = crypto_create_tfm_node(alg, frontend, node); if (!IS_ERR(tfm)) return tfm; crypto_mod_put(alg); err = PTR_ERR(tfm); err: if (err != -EAGAIN) break; if (fatal_signal_pending(current)) { err = -EINTR; break; } } return ERR_PTR(err); } EXPORT_SYMBOL_GPL(crypto_alloc_tfm_node); /* * crypto_destroy_tfm - Free crypto transform * @mem: Start of tfm slab * @tfm: Transform to free * * This function frees up the transform and any associated resources, * then drops the refcount on the associated algorithm. */ void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm) { struct crypto_alg *alg; if (IS_ERR_OR_NULL(mem)) return; if (!refcount_dec_and_test(&tfm->refcnt)) return; alg = tfm->__crt_alg; if (!tfm->exit && alg->cra_exit) alg->cra_exit(tfm); crypto_exit_ops(tfm); crypto_mod_put(alg); kfree_sensitive(mem); } EXPORT_SYMBOL_GPL(crypto_destroy_tfm); int crypto_has_alg(const char *name, u32 type, u32 mask) { int ret = 0; struct crypto_alg *alg = crypto_alg_mod_lookup(name, type, mask); if (!IS_ERR(alg)) { crypto_mod_put(alg); ret = 1; } return ret; } EXPORT_SYMBOL_GPL(crypto_has_alg); void crypto_req_done(void *data, int err) { struct crypto_wait *wait = data; if (err == -EINPROGRESS) return; wait->err = err; complete(&wait->completion); } EXPORT_SYMBOL_GPL(crypto_req_done); void crypto_destroy_alg(struct crypto_alg *alg) { if (alg->cra_type && alg->cra_type->destroy) alg->cra_type->destroy(alg); if (alg->cra_destroy) alg->cra_destroy(alg); } EXPORT_SYMBOL_GPL(crypto_destroy_alg); MODULE_DESCRIPTION("Cryptographic core API"); MODULE_LICENSE("GPL"); |
| 44 57 4 15 16 82 16 67 106 39 16 58 38 38 38 38 16 99 21 86 26 105 104 101 5 86 86 106 106 95 13 43 46 1 86 4 81 76 2 13 71 189 189 189 189 189 189 108 18 26 71 43 6 107 12 106 7 63 39 16 96 14 86 85 189 39 5 5 5 5 5 5 5 5 5 5 66 19 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Internet Control Message Protocol (ICMPv6) * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on net/ipv4/icmp.c * * RFC 1885 */ /* * Changes: * * Andi Kleen : exception handling * Andi Kleen add rate limits. never reply to a icmp. * add more length checks and other fixes. * yoshfuji : ensure to sent parameter problem for * fragments. * YOSHIFUJI Hideaki @USAGI: added sysctl for icmp rate limit. * Randy Dunlap and * YOSHIFUJI Hideaki @USAGI: Per-interface statistics support * Kazunori MIYAZAWA @USAGI: change output process to use ip6_append_data */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/netfilter.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/icmpv6.h> #include <net/ip.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/ip6_checksum.h> #include <net/ping.h> #include <net/protocol.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/seg6.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/inet_common.h> #include <net/dsfield.h> #include <net/l3mdev.h> #include <linux/uaccess.h> static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk); static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */ struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset); struct net *net = dev_net_rcu(skb->dev); if (type == ICMPV6_PKT_TOOBIG) ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); if (!(type & ICMPV6_INFOMSG_MASK)) if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST) ping_err(skb, offset, ntohl(info)); return 0; } static int icmpv6_rcv(struct sk_buff *skb); static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, .err_handler = icmpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; /* Called with BH disabled */ static struct sock *icmpv6_xmit_lock(struct net *net) { struct sock *sk; sk = this_cpu_read(ipv6_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path (f.e. SIT or * ip6ip6 tunnel) signals dst_link_failure() for an * outgoing ICMP6 packet. */ return NULL; } sock_net_set(sk, net); return sk; } static void icmpv6_xmit_unlock(struct sock *sk) { sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } /* * Figure out, may we reply to this packet with icmp error. * * We do not reply, if: * - it was icmp error message. * - it is truncated, so that it is known, that protocol is ICMPV6 * (i.e. in the middle of some exthdr) * * --ANK (980726) */ static bool is_ineligible(const struct sk_buff *skb) { int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data; int len = skb->len - ptr; __u8 nexthdr = ipv6_hdr(skb)->nexthdr; __be16 frag_off; if (len < 0) return true; ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off); if (ptr < 0) return false; if (nexthdr == IPPROTO_ICMPV6) { u8 _type, *tp; tp = skb_header_pointer(skb, ptr+offsetof(struct icmp6hdr, icmp6_type), sizeof(_type), &_type); /* Based on RFC 8200, Section 4.5 Fragment Header, return * false if this is a fragment packet with no icmp header info. */ if (!tp && frag_off != 0) return false; else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) return true; } return false; } static bool icmpv6_mask_allow(struct net *net, int type) { if (type > ICMPV6_MSG_MAX) return true; /* Limit if icmp type is set in ratemask. */ if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask)) return true; return false; } static bool icmpv6_global_allow(struct net *net, int type, bool *apply_ratelimit) { if (icmpv6_mask_allow(net, type)) return true; if (icmp_global_allow(net)) { *apply_ratelimit = true; return true; } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } /* * Check the ICMP output rate limit */ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, struct flowi6 *fl6, bool apply_ratelimit) { struct net *net = sock_net(sk); struct dst_entry *dst; bool res = false; if (!apply_ratelimit) return true; /* * Look up the output route. * XXX: perhaps the expire for routing entries cloned by * this lookup should be more aggressive (not longer than timeout). */ dst = ip6_route_output(net, sk, fl6); if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { res = true; } else { struct rt6_info *rt = dst_rt6_info(dst); int tmo = net->ipv6.sysctl.icmpv6_time; struct inet_peer *peer; /* Give more bandwidth to wider prefixes. */ if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); rcu_read_lock(); peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr); res = inet_peer_xrlim_allow(peer, tmo); rcu_read_unlock(); } if (!res) __ICMP6_INC_STATS(net, ip6_dst_idev(dst), ICMP6_MIB_RATELIMITHOST); else icmp_global_consume(net); dst_release(dst); return res; } static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type, struct flowi6 *fl6) { struct net *net = sock_net(sk); struct dst_entry *dst; bool res = false; dst = ip6_route_output(net, sk, fl6); if (!dst->error) { struct rt6_info *rt = dst_rt6_info(dst); struct in6_addr prefsrc; rt6_get_prefsrc(rt, &prefsrc); res = !ipv6_addr_any(&prefsrc); } dst_release(dst); return res; } /* * an inline helper for the "simple" if statement below * checks if parameter problem report is caused by an * unrecognized IPv6 option that has the Option Type * highest-order two bits set to 10 */ static bool opt_unrec(struct sk_buff *skb, __u32 offset) { u8 _optval, *op; offset += skb_network_offset(skb); op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval); if (!op) return true; return (*op & 0xC0) == 0x80; } void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; skb = skb_peek(&sk->sk_write_queue); if (!skb) return; icmp6h = icmp6_hdr(skb); memcpy(icmp6h, thdr, sizeof(struct icmp6hdr)); icmp6h->icmp6_cksum = 0; if (skb_queue_len(&sk->sk_write_queue) == 1) { skb->csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), skb->csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, skb->csum); } else { __wsum tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); } tmp_csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), tmp_csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, tmp_csum); } ip6_push_pending_frames(sk); } struct icmpv6_msg { struct sk_buff *skb; int offset; uint8_t type; }; static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct icmpv6_msg *msg = (struct icmpv6_msg *) from; struct sk_buff *org_skb = msg->skb; __wsum csum; csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (!(msg->type & ICMPV6_INFOMSG_MASK)) nf_ct_attach(skb, org_skb); return 0; } #if IS_ENABLED(CONFIG_IPV6_MIP6) static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); struct ipv6_destopt_hao *hao; int off; if (opt->dsthao) { off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO); if (likely(off >= 0)) { hao = (struct ipv6_destopt_hao *) (skb_network_header(skb) + off); swap(iph->saddr, hao->addr); } } } #else static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, struct sock *sk, struct flowi6 *fl6) { struct dst_entry *dst, *dst2; struct flowi6 fl2; int err; err = ip6_dst_lookup(net, sk, &dst, fl6); if (err) return ERR_PTR(err); /* * We won't send icmp if the destination is known * anycast unless we need to treat anycast as unicast. */ if (!READ_ONCE(net->ipv6.sysctl.icmpv6_error_anycast_as_unicast) && ipv6_anycast_destination(dst, &fl6->daddr)) { net_dbg_ratelimited("icmp6_send: acast source\n"); dst_release(dst); return ERR_PTR(-EINVAL); } /* No need to clone since we're just using its address. */ dst2 = dst; dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0); if (!IS_ERR(dst)) { if (dst != dst2) return dst; } else { if (PTR_ERR(dst) == -EPERM) dst = NULL; else return dst; } err = xfrm_decode_session_reverse(net, skb, flowi6_to_flowi(&fl2), AF_INET6); if (err) goto relookup_failed; err = ip6_dst_lookup(net, sk, &dst2, &fl2); if (err) goto relookup_failed; dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP); if (!IS_ERR(dst2)) { dst_release(dst); dst = dst2; } else { err = PTR_ERR(dst2); if (err == -EPERM) { dst_release(dst); return dst2; } else goto relookup_failed; } relookup_failed: if (dst) return dst; return ERR_PTR(err); } static struct net_device *icmp6_dev(const struct sk_buff *skb) { struct net_device *dev = skb->dev; /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so * get the real device index. Same is needed for replies to a link * local address on a device enslaved to an L3 master device */ if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), * and ip6_null_entry could be set to skb if no route is found. */ if (rt6 && rt6->rt6i_idev) dev = rt6->rt6i_idev->dev; } return dev; } static int icmp6_iif(const struct sk_buff *skb) { return icmp6_dev(skb)->ifindex; } /* * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; struct net *net; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; bool apply_ratelimit = false; struct dst_entry *dst; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; struct ipcm6_cookie ipc6; int iif = 0; int addr_type = 0; int len; u32 mark; if ((u8 *)hdr < skb->head || (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; if (!skb->dev) return; rcu_read_lock(); net = dev_net_rcu(skb->dev); mark = IP6_REPLY_MARK(net, skb->mark); /* * Make sure we respect the rules * i.e. RFC 1885 2.4(e) * Rule (e.1) is enforced by not using icmp6_send * in any code that processes icmp errors. */ addr_type = ipv6_addr_type(&hdr->daddr); if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) || ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr)) saddr = &hdr->daddr; /* * Dest addr check */ if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) { if (type != ICMPV6_PKT_TOOBIG && !(type == ICMPV6_PARAMPROB && code == ICMPV6_UNK_OPTION && (opt_unrec(skb, info)))) goto out; saddr = NULL; } addr_type = ipv6_addr_type(&hdr->saddr); /* * Source addr check */ if (__ipv6_addr_needs_scope_id(addr_type)) { iif = icmp6_iif(skb); } else { /* * The source device is used for looking up which routing table * to use for sending an ICMP error. */ iif = l3mdev_master_ifindex(skb->dev); } /* * Must not send error if the source does not uniquely * identify a single node (RFC2463 Section 2.4). * We check unspecified / multicast addresses here, * and anycast addresses will be checked later. */ if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out; } /* * Never answer to a ICMP packet. */ if (is_ineligible(skb)) { net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out; } /* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */ local_bh_disable(); /* Check global sysctl_icmp_msgs_per_sec ratelimit */ if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type, &apply_ratelimit)) goto out_bh_enable; mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.daddr = hdr->saddr; if (force_saddr) saddr = force_saddr; if (saddr) { fl6.saddr = *saddr; } else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) { /* select a more meaningful saddr from input if */ struct net_device *in_netdev; in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, &fl6.saddr); dev_put(in_netdev); } } fl6.flowi6_mark = mark; fl6.flowi6_oif = iif; fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; fl6.flowi6_uid = sock_net_uid(net, NULL); fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit)) goto out_unlock; tmp_hdr.icmp6_type = type; tmp_hdr.icmp6_code = code; tmp_hdr.icmp6_cksum = 0; tmp_hdr.icmp6_pointer = htonl(info); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); ipcm6_init_sk(&ipc6, sk); ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) goto out_unlock; ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); msg.skb = skb; msg.offset = skb_network_offset(skb); msg.type = type; len = skb->len - msg.offset; len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr)); if (len < 0) { net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out_dst_release; } idev = __in6_dev_get(skb->dev); if (ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr)); } out_dst_release: dst_release(dst); out_unlock: icmpv6_xmit_unlock(sk); out_bh_enable: local_bh_enable(); out: rcu_read_unlock(); } EXPORT_SYMBOL(icmp6_send); /* Slightly more convenient version of icmp6_send with drop reasons. */ void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos, enum skb_drop_reason reason) { icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb_reason(skb, reason); } /* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH * if sufficient data bytes are available * @nhs is the size of the tunnel header(s) : * Either an IPv4 header for SIT encap * an IPv4 header + GRE header for GRE encap */ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len) { struct in6_addr temp_saddr; struct rt6_info *rt; struct sk_buff *skb2; u32 info = 0; if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8)) return 1; /* RFC 4884 (partial) support for ICMP extensions */ if (data_len < 128 || (data_len & 7) || skb->len < data_len) data_len = 0; skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC); if (!skb2) return 1; skb_dst_drop(skb2); skb_pull(skb2, nhs); skb_reset_network_header(skb2); rt = rt6_lookup(dev_net_rcu(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, skb, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr); if (data_len) { /* RFC 4884 (partial) support : * insert 0 padding at the end, before the extensions */ __skb_push(skb2, nhs); skb_reset_network_header(skb2); memmove(skb2->data, skb2->data + nhs, data_len - nhs); memset(skb2->data + data_len - nhs, 0, nhs); /* RFC 4884 4.5 : Length is measured in 64-bit words, * and stored in reserved[0] */ info = (data_len/8) << 24; } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); kfree_skb(skb2); return 0; } EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach); static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); struct sock *sk; struct inet6_dev *idev; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; struct icmp6hdr *icmph = icmp6_hdr(skb); bool apply_ratelimit = false; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; struct dst_entry *dst; struct ipcm6_cookie ipc6; u32 mark = IP6_REPLY_MARK(net, skb->mark); SKB_DR(reason); bool acast; u8 type; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) && net->ipv6.sysctl.icmpv6_echo_ignore_multicast) return reason; saddr = &ipv6_hdr(skb)->daddr; acast = ipv6_anycast_destination(skb_dst(skb), saddr); if (acast && net->ipv6.sysctl.icmpv6_echo_ignore_anycast) return reason; if (!ipv6_unicast_destination(skb) && !(net->ipv6.sysctl.anycast_src_echo_reply && acast)) saddr = NULL; if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) type = ICMPV6_EXT_ECHO_REPLY; else type = ICMPV6_ECHO_REPLY; memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); tmp_hdr.icmp6_type = type; memset(&fl6, 0, sizeof(fl6)); if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES) fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb)); fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) fl6.saddr = *saddr; fl6.flowi6_oif = icmp6_iif(skb); fl6.fl6_icmp_type = type; fl6.flowi6_mark = mark; fl6.flowi6_uid = sock_net_uid(net, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); local_bh_disable(); sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); if (ip6_dst_lookup(net, sk, &dst, &fl6)) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) goto out; /* Check the ratelimit */ if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY, &apply_ratelimit)) || !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6, apply_ratelimit)) goto out_dst_release; idev = __in6_dev_get(skb->dev); msg.skb = skb; msg.offset = 0; msg.type = type; ipcm6_init_sk(&ipc6, sk); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); ipc6.sockc.mark = mark; if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) if (!icmp_build_probe(skb, (struct icmphdr *)&tmp_hdr)) goto out_dst_release; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); reason = SKB_CONSUMED; } out_dst_release: dst_release(dst); out: icmpv6_xmit_unlock(sk); out_bh_enable: local_bh_enable(); return reason; } enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net_rcu(skb->dev); const struct inet6_protocol *ipprot; enum skb_drop_reason reason; int inner_offset; __be16 frag_off; u8 nexthdr; reason = pskb_may_pull_reason(skb, sizeof(struct ipv6hdr)); if (reason != SKB_NOT_DROPPED_YET) goto out; seg6_icmp_srh(skb, opt); nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { /* now skip over extension headers */ inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (inner_offset < 0) { SKB_DR_SET(reason, IPV6_BAD_EXTHDR); goto out; } } else { inner_offset = sizeof(struct ipv6hdr); } /* Checkin header including 8 bytes of inner protocol header. */ reason = pskb_may_pull_reason(skb, inner_offset + 8); if (reason != SKB_NOT_DROPPED_YET) goto out; /* BUGGG_FUTURE: we should try to parse exthdrs in this packet. Without this we will not able f.e. to make source routed pmtu discovery. Corresponding argument (opt) to notifiers is already added. --ANK (980726) */ ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, opt, type, code, inner_offset, info); raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); return SKB_CONSUMED; out: __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return reason; } /* * Handle icmp messages */ static int icmpv6_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct net *net = dev_net_rcu(skb->dev); struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; struct icmp6hdr *hdr; u8 type; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; } if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr))) goto drop_no_count; nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*hdr)); if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; } skb_set_network_header(skb, nh); } __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INMSGS); saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) { net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n", saddr, daddr); goto csum_error; } if (!pskb_pull(skb, sizeof(*hdr))) goto discard_it; hdr = icmp6_hdr(skb); type = hdr->icmp6_type; ICMP6MSGIN_INC_STATS(dev_net_rcu(dev), idev, type); switch (type) { case ICMPV6_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all) reason = icmpv6_echo_reply(skb); break; case ICMPV6_EXT_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all && READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) reason = icmpv6_echo_reply(skb); break; case ICMPV6_ECHO_REPLY: case ICMPV6_EXT_ECHO_REPLY: ping_rcv(skb); return 0; case ICMPV6_PKT_TOOBIG: /* BUGGG_FUTURE: if packet contains rthdr, we cannot update standard destination cache. Seems, only "advanced" destination cache will allow to solve this problem --ANK (980726) */ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto discard_it; hdr = icmp6_hdr(skb); /* to notify */ fallthrough; case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: reason = icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu); break; case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: reason = ndisc_rcv(skb); break; case ICMPV6_MGM_QUERY: igmp6_event_query(skb); return 0; case ICMPV6_MGM_REPORT: igmp6_event_report(skb); return 0; case ICMPV6_MGM_REDUCTION: case ICMPV6_NI_QUERY: case ICMPV6_NI_REPLY: case ICMPV6_MLD2_REPORT: case ICMPV6_DHAAD_REQUEST: case ICMPV6_DHAAD_REPLY: case ICMPV6_MOBILE_PREFIX_SOL: case ICMPV6_MOBILE_PREFIX_ADV: break; default: /* informational */ if (type & ICMPV6_INFOMSG_MASK) break; net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n", saddr, daddr); /* * error of unknown type. * must pass to upper level */ reason = icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu); } /* until the v6 path can be better sorted assume failure and * preserve the status quo behaviour for the rest of the paths to here */ if (reason) kfree_skb_reason(skb, reason); else consume_skb(skb); return 0; csum_error: reason = SKB_DROP_REASON_ICMP_CSUM; __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_CSUMERRORS); discard_it: __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INERRORS); drop_no_count: kfree_skb_reason(skb, reason); return 0; } void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif) { memset(fl6, 0, sizeof(*fl6)); fl6->saddr = *saddr; fl6->daddr = *daddr; fl6->flowi6_proto = IPPROTO_ICMPV6; fl6->fl6_icmp_type = type; fl6->fl6_icmp_code = 0; fl6->flowi6_oif = oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } int __init icmpv6_init(void) { struct sock *sk; int err, i; for_each_possible_cpu(i) { err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, &init_net); if (err < 0) { pr_err("Failed to initialize the ICMP6 control socket (err %d)\n", err); return err; } per_cpu(ipv6_icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); } err = -EAGAIN; if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) goto fail; err = inet6_register_icmp_sender(icmp6_send); if (err) goto sender_reg_err; return 0; sender_reg_err: inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); fail: pr_err("Failed to register ICMP6 protocol\n"); return err; } void icmpv6_cleanup(void) { inet6_unregister_icmp_sender(icmp6_send); inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); } static const struct icmp6_err { int err; int fatal; } tab_unreach[] = { { /* NOROUTE */ .err = ENETUNREACH, .fatal = 0, }, { /* ADM_PROHIBITED */ .err = EACCES, .fatal = 1, }, { /* Was NOT_NEIGHBOUR, now reserved */ .err = EHOSTUNREACH, .fatal = 0, }, { /* ADDR_UNREACH */ .err = EHOSTUNREACH, .fatal = 0, }, { /* PORT_UNREACH */ .err = ECONNREFUSED, .fatal = 1, }, { /* POLICY_FAIL */ .err = EACCES, .fatal = 1, }, { /* REJECT_ROUTE */ .err = EACCES, .fatal = 1, }, }; int icmpv6_err_convert(u8 type, u8 code, int *err) { int fatal = 0; *err = EPROTO; switch (type) { case ICMPV6_DEST_UNREACH: fatal = 1; if (code < ARRAY_SIZE(tab_unreach)) { *err = tab_unreach[code].err; fatal = tab_unreach[code].fatal; } break; case ICMPV6_PKT_TOOBIG: *err = EMSGSIZE; break; case ICMPV6_PARAMPROB: *err = EPROTO; fatal = 1; break; case ICMPV6_TIME_EXCEED: *err = EHOSTUNREACH; break; } return fatal; } EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL static struct ctl_table ipv6_icmp_table_template[] = { { .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "echo_ignore_all", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_all, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "echo_ignore_multicast", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_multicast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "echo_ignore_anycast", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_anycast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ratemask", .data = &init_net.ipv6.sysctl.icmpv6_ratemask_ptr, .maxlen = ICMPV6_MSG_MAX + 1, .mode = 0644, .proc_handler = proc_do_large_bitmap, }, { .procname = "error_anycast_as_unicast", .data = &init_net.ipv6.sysctl.icmpv6_error_anycast_as_unicast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_icmp_table_template, sizeof(ipv6_icmp_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.icmpv6_time; table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all; table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast; table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast; table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr; table[5].data = &net->ipv6.sysctl.icmpv6_error_anycast_as_unicast; } return table; } size_t ipv6_icmp_sysctl_table_size(void) { return ARRAY_SIZE(ipv6_icmp_table_template); } #endif |
| 537 539 538 406 539 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/symlink.c - kernfs symlink implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/fs.h> #include <linux/gfp.h> #include <linux/namei.h> #include "kernfs-internal.h" /** * kernfs_create_link - create a symlink * @parent: directory to create the symlink in * @name: name of the symlink * @target: target node for the symlink to point to * * Return: the created node on success, ERR_PTR() value on error. * Ownership of the link matches ownership of the target. */ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target) { struct kernfs_node *kn; int error; kuid_t uid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID; if (target->iattr) { uid = target->iattr->ia_uid; gid = target->iattr->ia_gid; } kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK); if (!kn) return ERR_PTR(-ENOMEM); if (kernfs_ns_enabled(parent)) kn->ns = target->ns; kn->symlink.target_kn = target; kernfs_get(target); /* ref owned by symlink */ error = kernfs_add_one(kn); if (!error) return kn; kernfs_put(kn); return ERR_PTR(error); } static int kernfs_get_target_path(struct kernfs_node *parent, struct kernfs_node *target, char *path) { struct kernfs_node *base, *kn; char *s = path; int len = 0; /* go up to the root, stop at the base */ base = parent; while (kernfs_parent(base)) { kn = kernfs_parent(target); while (kernfs_parent(kn) && base != kn) kn = kernfs_parent(kn); if (base == kn) break; if ((s - path) + 3 >= PATH_MAX) return -ENAMETOOLONG; strcpy(s, "../"); s += 3; base = kernfs_parent(base); } /* determine end of target string for reverse fillup */ kn = target; while (kernfs_parent(kn) && kn != base) { len += strlen(kernfs_rcu_name(kn)) + 1; kn = kernfs_parent(kn); } /* check limits */ if (len < 2) return -EINVAL; len--; if ((s - path) + len >= PATH_MAX) return -ENAMETOOLONG; /* reverse fillup of target string from target to base */ kn = target; while (kernfs_parent(kn) && kn != base) { const char *name = kernfs_rcu_name(kn); int slen = strlen(name); len -= slen; memcpy(s + len, name, slen); if (len) s[--len] = '/'; kn = kernfs_parent(kn); } return 0; } static int kernfs_getlink(struct inode *inode, char *path) { struct kernfs_node *kn = inode->i_private; struct kernfs_node *parent; struct kernfs_node *target = kn->symlink.target_kn; struct kernfs_root *root = kernfs_root(kn); int error; down_read(&root->kernfs_rwsem); parent = kernfs_parent(kn); error = kernfs_get_target_path(parent, target, path); up_read(&root->kernfs_rwsem); return error; } static const char *kernfs_iop_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { char *body; int error; if (!dentry) return ERR_PTR(-ECHILD); body = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!body) return ERR_PTR(-ENOMEM); error = kernfs_getlink(inode, body); if (unlikely(error < 0)) { kfree(body); return ERR_PTR(error); } set_delayed_call(done, kfree_link, body); return body; } const struct inode_operations kernfs_symlink_iops = { .listxattr = kernfs_iop_listxattr, .get_link = kernfs_iop_get_link, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .permission = kernfs_iop_permission, }; |
| 3 9 9 9 16 7 4 2 4 82 81 47 8 52 27 4 73 37 104 98 119 106 5 21 2 2 87 2 19 17 2 16 16 94 25 92 42 38 15 52 7 45 5 58 55 54 3 51 58 58 17 17 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 | // SPDX-License-Identifier: GPL-2.0-or-later /* scm.c - Socket level control messages processing. * * Author: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Alignment and value checking mods by Craig Metz */ #include <linux/module.h> #include <linux/signal.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/user.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/io_uring.h> #include <linux/uaccess.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> #include <net/cls_cgroup.h> #include <net/af_unix.h> /* * Only allow a user to send credentials, that they could set with * setu(g)id. */ static __inline__ int scm_check_creds(struct ucred *creds) { const struct cred *cred = current_cred(); kuid_t uid = make_kuid(cred->user_ns, creds->uid); kgid_t gid = make_kgid(cred->user_ns, creds->gid); if (!uid_valid(uid) || !gid_valid(gid)) return -EINVAL; if ((creds->pid == task_tgid_vnr(current) || ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) { return 0; } return -EPERM; } static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) { int *fdp = (int*)CMSG_DATA(cmsg); struct scm_fp_list *fpl = *fplp; struct file **fpp; int i, num; num = (cmsg->cmsg_len - sizeof(struct cmsghdr))/sizeof(int); if (num <= 0) return 0; if (num > SCM_MAX_FD) return -EINVAL; if (!fpl) { fpl = kmalloc(sizeof(struct scm_fp_list), GFP_KERNEL_ACCOUNT); if (!fpl) return -ENOMEM; *fplp = fpl; fpl->count = 0; fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; #if IS_ENABLED(CONFIG_UNIX) fpl->inflight = false; fpl->dead = false; fpl->edges = NULL; INIT_LIST_HEAD(&fpl->vertices); #endif } fpp = &fpl->fp[fpl->count]; if (fpl->count + num > fpl->max) return -EINVAL; /* * Verify the descriptors and increment the usage count. */ for (i=0; i< num; i++) { int fd = fdp[i]; struct file *file; if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; /* don't allow io_uring files */ if (io_is_uring_fops(file)) { fput(file); return -EINVAL; } if (unix_get_socket(file)) fpl->count_unix++; *fpp++ = file; fpl->count++; } if (!fpl->user) fpl->user = get_uid(current_user()); return num; } void __scm_destroy(struct scm_cookie *scm) { struct scm_fp_list *fpl = scm->fp; int i; if (fpl) { scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); free_uid(fpl->user); kfree(fpl); } } EXPORT_SYMBOL(__scm_destroy); int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) { const struct proto_ops *ops = READ_ONCE(sock->ops); struct cmsghdr *cmsg; int err; for_each_cmsghdr(cmsg, msg) { err = -EINVAL; /* Verify that cmsg_len is at least sizeof(struct cmsghdr) */ /* The first check was omitted in <= 2.2.5. The reasoning was that parser checks cmsg_len in any case, so that additional check would be work duplication. But if cmsg_level is not SOL_SOCKET, we do not check for too short ancillary data object at all! Oops. OK, let's add it... */ if (!CMSG_OK(msg, cmsg)) goto error; if (cmsg->cmsg_level != SOL_SOCKET) continue; switch (cmsg->cmsg_type) { case SCM_RIGHTS: if (!ops || ops->family != PF_UNIX) goto error; err=scm_fp_copy(cmsg, &p->fp); if (err<0) goto error; break; case SCM_CREDENTIALS: { struct ucred creds; kuid_t uid; kgid_t gid; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct ucred))) goto error; memcpy(&creds, CMSG_DATA(cmsg), sizeof(struct ucred)); err = scm_check_creds(&creds); if (err) goto error; p->creds.pid = creds.pid; if (!p->pid || pid_vnr(p->pid) != creds.pid) { struct pid *pid; err = -ESRCH; pid = find_get_pid(creds.pid); if (!pid) goto error; put_pid(p->pid); p->pid = pid; } err = -EINVAL; uid = make_kuid(current_user_ns(), creds.uid); gid = make_kgid(current_user_ns(), creds.gid); if (!uid_valid(uid) || !gid_valid(gid)) goto error; p->creds.uid = uid; p->creds.gid = gid; break; } default: goto error; } } if (p->fp && !p->fp->count) { kfree(p->fp); p->fp = NULL; } return 0; error: scm_destroy(p); return err; } EXPORT_SYMBOL(__scm_send); int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data) { int cmlen = CMSG_LEN(len); if (msg->msg_flags & MSG_CMSG_COMPAT) return put_cmsg_compat(msg, level, type, len, data); if (!msg->msg_control || msg->msg_controllen < sizeof(struct cmsghdr)) { msg->msg_flags |= MSG_CTRUNC; return 0; /* XXX: return error? check spec. */ } if (msg->msg_controllen < cmlen) { msg->msg_flags |= MSG_CTRUNC; cmlen = msg->msg_controllen; } if (msg->msg_control_is_user) { struct cmsghdr __user *cm = msg->msg_control_user; check_object_size(data, cmlen - sizeof(*cm), true); if (!user_write_access_begin(cm, cmlen)) goto efault; unsafe_put_user(cmlen, &cm->cmsg_len, efault_end); unsafe_put_user(level, &cm->cmsg_level, efault_end); unsafe_put_user(type, &cm->cmsg_type, efault_end); unsafe_copy_to_user(CMSG_USER_DATA(cm), data, cmlen - sizeof(*cm), efault_end); user_write_access_end(); } else { struct cmsghdr *cm = msg->msg_control; cm->cmsg_level = level; cm->cmsg_type = type; cm->cmsg_len = cmlen; memcpy(CMSG_DATA(cm), data, cmlen - sizeof(*cm)); } cmlen = min(CMSG_SPACE(len), msg->msg_controllen); if (msg->msg_control_is_user) msg->msg_control_user += cmlen; else msg->msg_control += cmlen; msg->msg_controllen -= cmlen; return 0; efault_end: user_write_access_end(); efault: return -EFAULT; } EXPORT_SYMBOL(put_cmsg); int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, void *data) { /* Don't produce truncated CMSGs */ if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len)) return -ETOOSMALL; return put_cmsg(msg, level, type, len, data); } void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping64 tss; int i; for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; } put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_NEW, sizeof(tss), &tss); } EXPORT_SYMBOL(put_cmsg_scm_timestamping64); void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping tss; int i; for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; } put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(tss), &tss); } EXPORT_SYMBOL(put_cmsg_scm_timestamping); static int scm_max_fds(struct msghdr *msg) { if (msg->msg_controllen <= sizeof(struct cmsghdr)) return 0; return (msg->msg_controllen - sizeof(struct cmsghdr)) / sizeof(int); } void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { struct cmsghdr __user *cm = (__force struct cmsghdr __user *)msg->msg_control_user; unsigned int o_flags = (msg->msg_flags & MSG_CMSG_CLOEXEC) ? O_CLOEXEC : 0; int fdmax = min_t(int, scm_max_fds(msg), scm->fp->count); int __user *cmsg_data = CMSG_USER_DATA(cm); int err = 0, i; /* no use for FD passing from kernel space callers */ if (WARN_ON_ONCE(!msg->msg_control_is_user)) return; if (msg->msg_flags & MSG_CMSG_COMPAT) { scm_detach_fds_compat(msg, scm); return; } for (i = 0; i < fdmax; i++) { err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } if (i > 0) { int cmlen = CMSG_LEN(i * sizeof(int)); err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) err = put_user(cmlen, &cm->cmsg_len); if (!err) { cmlen = CMSG_SPACE(i * sizeof(int)); if (msg->msg_controllen < cmlen) cmlen = msg->msg_controllen; msg->msg_control_user += cmlen; msg->msg_controllen -= cmlen; } } if (i < scm->fp->count || (scm->fp->count && fdmax <= 0)) msg->msg_flags |= MSG_CTRUNC; /* * All of the files that fit in the message have had their usage counts * incremented, so we just free the list. */ __scm_destroy(scm); } EXPORT_SYMBOL(scm_detach_fds); struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) { struct scm_fp_list *new_fpl; int i; if (!fpl) return NULL; new_fpl = kmemdup(fpl, offsetof(struct scm_fp_list, fp[fpl->count]), GFP_KERNEL_ACCOUNT); if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; new_fpl->user = get_uid(fpl->user); #if IS_ENABLED(CONFIG_UNIX) new_fpl->inflight = false; new_fpl->edges = NULL; INIT_LIST_HEAD(&new_fpl->vertices); #endif } return new_fpl; } EXPORT_SYMBOL(scm_fp_dup); |
| 237 237 3 237 237 237 288 288 288 280 278 278 278 26 279 2132 279 5750 409 21 121 149 875 1839 5647 25 273 1775 439 446 195 133 196 195 585 593 25 674 692 692 278 278 1482 409 98 17 116 35 10 877 878 280 47 449 649 5966 5971 167 650 3082 650 654 654 654 141 26 167 167 26 26 167 650 5623 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> #include <linux/cacheinfo.h> #include <linux/rcuwait.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct user_struct; struct pt_regs; struct folio_batch; void arch_mm_preinit(void); void mm_core_init(void); void init_mm_internals(void); extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } extern void * high_memory; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern int mmap_rnd_bits_max __ro_after_init; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #ifndef DIRECT_MAP_PHYSMEM_END # ifdef MAX_PHYSMEM_BITS # define DIRECT_MAP_PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) # else # define DIRECT_MAP_PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) # endif #endif #include <asm/page.h> #include <asm/processor.h> #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); BUILD_BUG_ON(sizeof(struct page) > 96); switch (sizeof(struct page)) { case 96: _pp[11] = 0; fallthrough; case 88: _pp[10] = 0; fallthrough; case 80: _pp[9] = 0; fallthrough; case 72: _pp[8] = 0; fallthrough; case 64: _pp[7] = 0; fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; _pp[4] = 0; _pp[3] = 0; _pp[2] = 0; _pp[1] = 0; _pp[0] = 0; } } #else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) #define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) #else #define nth_page(page,n) ((page) + (n)) #define folio_page_idx(folio, p) ((p) - &(folio)->page) #endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* to align the pointer to the (prev) page boundary */ #define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); } void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #ifdef CONFIG_MMU #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #else /* CONFIG_MMU */ #define VM_MAYOVERLAY 0x00000200 /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ #define VM_UFFD_MISSING 0 #endif /* CONFIG_MMU */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_SYNC 0x00800000 /* Synchronous page faults */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY # define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ #else # define VM_SOFTDIRTY 0 #endif #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_6 38 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5) #define VM_HIGH_ARCH_6 BIT(VM_HIGH_ARCH_BIT_6) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 #if CONFIG_ARCH_PKEY_BITS > 3 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 #else # define VM_PKEY_BIT3 0 #endif #if CONFIG_ARCH_PKEY_BITS > 4 # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #ifdef CONFIG_X86_USER_SHADOW_STACK /* * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of * support core mm. * * These VMAs will get a single end guard page. This helps userspace protect * itself from attacks. A single page is enough for current shadow stack archs * (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c * for more details on the guard size. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_5 #endif #if defined(CONFIG_ARM64_GCS) /* * arm64's Guarded Control Stack implements similar functionality and * has similar constraints to shadow stacks. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_6 #endif #ifndef VM_SHADOW_STACK # define VM_SHADOW_STACK VM_NONE #endif #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC64) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI #elif defined(CONFIG_ARM64) # define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ # define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #if defined(CONFIG_ARM64_MTE) # define VM_MTE VM_HIGH_ARCH_4 /* Use Tagged memory for access control */ # define VM_MTE_ALLOWED VM_HIGH_ARCH_5 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR # define VM_UFFD_MINOR_BIT 38 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ /* * This flag is used to connect VFIO to arch specific KVM code. It * indicates that the memory under this VMA is safe for use with any * non-cachable memory type inside KVM. Some VFIO devices, on some * platforms, are thought to be unsafe and can cause machine crashes * if KVM does not lock down the memory type. */ #ifdef CONFIG_64BIT #define VM_ALLOW_ANY_UNCACHED_BIT 39 #define VM_ALLOW_ANY_UNCACHED BIT(VM_ALLOW_ANY_UNCACHED_BIT) #else #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif #ifdef CONFIG_64BIT #define VM_DROPPABLE_BIT 40 #define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) #elif defined(CONFIG_PPC32) #define VM_DROPPABLE VM_ARCH_1 #else #define VM_DROPPABLE VM_NONE #endif #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) /* Common data flag combinations */ #define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ #define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC #endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #define VM_STACK_EARLY VM_GROWSDOWN #else #define VM_STACK VM_GROWSDOWN #define VM_STACK_EARLY 0 #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR # define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \ FAULT_FLAG_KILLABLE | \ FAULT_FLAG_INTERRUPTIBLE) /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * @flags: Fault flags. * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); } #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { const struct { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address - masked */ unsigned long real_address; /* Faulting virtual address - unmasked */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ union { pte_t orig_pte; /* Value of PTE at the time of fault */ pmd_t orig_pmd; /* Value of PMD at the time of fault, * used by PMD fault only. */ }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() sets up a page * table from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); /** * @close: Called when the VMA is being removed from the MM. * Context: User context. May sleep. Caller holds mmap_lock. */ void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); int (*mremap)(struct vm_area_struct *area); /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not * be modified. Returns 0 if mprotect() can proceed. */ int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs. See also generic_access_phys() for a generic * implementation useful for any iomem mapping. */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); #endif /* * Called by vm_normal_page() for special PTEs to find the * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, unsigned long addr); }; #ifdef CONFIG_NUMA_BALANCING static inline void vma_numab_state_init(struct vm_area_struct *vma) { vma->numab_state = NULL; } static inline void vma_numab_state_free(struct vm_area_struct *vma) { kfree(vma->numab_state); } #else static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_PER_VMA_LOCK static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) { #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key lockdep_key; lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0); #endif if (reset_refcnt) refcount_set(&vma->vm_refcnt, 0); vma->vm_lock_seq = UINT_MAX; } static inline bool is_vma_writer_only(int refcnt) { /* * With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma * is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on * a detached vma happens only in vma_mark_detached() and is a rare * case, therefore most of the time there will be no unnecessary wakeup. */ return refcnt & VMA_LOCK_OFFSET && refcnt <= VMA_LOCK_OFFSET + 1; } static inline void vma_refcount_put(struct vm_area_struct *vma) { /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ struct mm_struct *mm = vma->vm_mm; int oldcnt; rwsem_release(&vma->vmlock_dep_map, _RET_IP_); if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) { if (is_vma_writer_only(oldcnt - 1)) rcuwait_wake_up(&mm->vma_writer_wait); } } /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to * using mmap_lock. The function should never yield false unlocked result. * False locked result is possible if mm_lock_seq overflows or if vma gets * reused and attached to a different mm before we lock it. * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got * detached. */ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, struct vm_area_struct *vma) { int oldcnt; /* * Check before locking. A race might cause false locked result. * We can use READ_ONCE() for the mm_lock_seq here, and don't need * ACQUIRE semantics, because this is just a lockless check whose result * we don't rely on for anything - the mm_lock_seq read against which we * need ordering is below. */ if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence)) return NULL; /* * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire() * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET. * Acquire fence is required here to avoid reordering against later * vm_lock_seq check and checks inside lock_vma_under_rcu(). */ if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, VMA_REF_LIMIT))) { /* return EAGAIN if vma got detached from under us */ return oldcnt ? NULL : ERR_PTR(-EAGAIN); } rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); /* * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq * modification invalidates all existing locks. * * We must use ACQUIRE semantics for the mm_lock_seq so that if we are * racing with vma_end_write_all(), we only start reading from the VMA * after it has been unlocked. * This pairs with RELEASE semantics in vma_end_write_all(). */ if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) { vma_refcount_put(vma); return NULL; } return vma; } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) { int oldcnt; mmap_assert_locked(vma->vm_mm); if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, VMA_REF_LIMIT))) return false; rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); return true; } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked(struct vm_area_struct *vma) { return vma_start_read_locked_nested(vma, 0); } static inline void vma_end_read(struct vm_area_struct *vma) { vma_refcount_put(vma); } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ *mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence; return (vma->vm_lock_seq == *mm_lock_seq); } void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq); /* * Begin writing to a VMA. * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. */ static inline void vma_start_write(struct vm_area_struct *vma) { unsigned int mm_lock_seq; if (__is_vma_write_locked(vma, &mm_lock_seq)) return; __vma_start_write(vma, mm_lock_seq); } static inline void vma_assert_write_locked(struct vm_area_struct *vma) { unsigned int mm_lock_seq; VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } static inline void vma_assert_locked(struct vm_area_struct *vma) { unsigned int mm_lock_seq; VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 && !__is_vma_write_locked(vma, &mm_lock_seq), vma); } /* * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these * assertions should be made either under mmap_write_lock or when the object * has been isolated under mmap_write_lock, ensuring no competing writers. */ static inline void vma_assert_attached(struct vm_area_struct *vma) { WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); } static inline void vma_assert_detached(struct vm_area_struct *vma) { WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); } static inline void vma_mark_attached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_detached(vma); refcount_set_release(&vma->vm_refcnt, 1); } void vma_mark_detached(struct vm_area_struct *vma); static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_end_read(vmf->vma); else mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_assert_locked(vmf->vma); else mmap_assert_locked(vmf->vma->vm_mm); } struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); #else /* CONFIG_PER_VMA_LOCK */ static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, struct vm_area_struct *vma) { return NULL; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_assert_attached(struct vm_area_struct *vma) {} static inline void vma_assert_detached(struct vm_area_struct *vma) {} static inline void vma_mark_attached(struct vm_area_struct *vma) {} static inline void vma_mark_detached(struct vm_area_struct *vma) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { return NULL; } static inline void vma_assert_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); } static inline void release_fault_lock(struct vm_fault *vmf) { mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(struct vm_fault *vmf) { mmap_assert_locked(vmf->vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ extern const struct vm_operations_struct vma_dummy_vm_ops; static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_lock_init(vma, false); } /* Use when VMA is not part of the VMA tree and needs no locking */ static inline void vm_flags_init(struct vm_area_struct *vma, vm_flags_t flags) { ACCESS_PRIVATE(vma, __vm_flags) = flags; } /* * Use when VMA is part of the VMA tree and modifications need coordination * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and * it should be locked explicitly beforehand. */ static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { vma_assert_write_locked(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { vma_assert_write_locked(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) |= flags; } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } /* * Use only if VMA is not part of the VMA tree or has no other users and * therefore needs no locking. */ static inline void __vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vm_flags_init(vma, (vma->vm_flags | set) & ~clear); } /* * Use only when the order of set/clear operations is unimportant, otherwise * use vm_flags_{set|clear} explicitly. */ static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vma_start_write(vma); __vm_flags_mod(vma, set, clear); } static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } /* * Indicate if the VMA is a heap for the given task; for * /proc/PID/maps that is the heap of the main task. */ static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) { return vma->vm_start < vma->vm_mm->brk && vma->vm_end > vma->vm_mm->start_brk; } /* * Indicate if the VMA is a stack for the given task; for * /proc/PID/maps that is the stack of the main task. */ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) { /* * We make no effort to guess what a given thread considers to be * its "stack". It's not even well-defined for programs written * languages like Go. */ return vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } static inline bool vma_is_foreign(struct vm_area_struct *vma) { if (!current->mm) return true; if (current->mm != vma->vm_mm) return true; return false; } static inline bool vma_is_accessible(struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } static inline bool is_shared_maywrite(vm_flags_t vm_flags) { return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == (VM_SHARED | VM_MAYWRITE); } static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) { return is_shared_maywrite(vma->vm_flags); } static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { return mas_find(&vmi->mas, max - 1); } static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) { /* * Uses mas_find() to get the first VMA when the iterator starts. * Calling mas_next() could skip the first entry. */ return mas_find(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) { return mas_next_range(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) { return mas_prev(&vmi->mas, 0); } static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, unsigned long start, unsigned long end, gfp_t gfp) { __mas_set_range(&vmi->mas, start, end - 1); mas_store_gfp(&vmi->mas, NULL, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } /* Free any unused preallocations */ static inline void vma_iter_free(struct vma_iterator *vmi) { mas_destroy(&vmi->mas); } static inline int vma_iter_bulk_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { vmi->mas.index = vma->vm_start; vmi->mas.last = vma->vm_end - 1; mas_store(&vmi->mas, vma); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; vma_mark_attached(vma); return 0; } static inline void vma_iter_invalidate(struct vma_iterator *vmi) { mas_pause(&vmi->mas); } static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) { mas_set(&vmi->mas, addr); } #define for_each_vma(__vmi, __vma) \ while (((__vma) = vma_next(&(__vmi))) != NULL) /* The MM code likes to work with exclusive end addresses */ #define for_each_vma_range(__vmi, __vma, __end) \ while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); bool vma_is_anon_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; extern void prep_compound_page(struct page *page, unsigned int order); static inline unsigned int folio_large_order(const struct folio *folio) { return folio->_flags_1 & 0xff; } #ifdef NR_PAGES_IN_LARGE_FOLIO static inline long folio_large_nr_pages(const struct folio *folio) { return folio->_nr_pages; } #else static inline long folio_large_nr_pages(const struct folio *folio) { return 1L << folio_large_order(folio); } #endif /* * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be * prepared to handle wild return values. For example, PG_head may be * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ static inline unsigned int compound_order(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 0; return folio_large_order(folio); } /** * folio_order - The allocation order of a folio. * @folio: The folio. * * A folio is composed of 2^order pages. See get_order() for the definition * of order. * * Return: The order of the folio. */ static inline unsigned int folio_order(const struct folio *folio) { if (!folio_test_large(folio)) return 0; return folio_large_order(folio); } /** * folio_reset_order - Reset the folio order and derived _nr_pages * @folio: The folio. * * Reset the order and derived _nr_pages to 0. Must only be used in the * process of splitting large folios. */ static inline void folio_reset_order(struct folio *folio) { if (WARN_ON_ONCE(!folio_test_large(folio))) return; folio->_flags_1 &= ~0xffUL; #ifdef NR_PAGES_IN_LARGE_FOLIO folio->_nr_pages = 0; #endif } #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } static inline int folio_put_testzero(struct folio *folio) { return put_page_testzero(&folio->page); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline bool get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } static inline struct folio *folio_get_nontail_page(struct page *page) { if (unlikely(!get_page_unless_zero(page))) return NULL; return (struct folio *)page; } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for * debugging purposes or implementation of other core folio_*() primitives. */ static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio_large_order(folio) == 1)) return 0; return atomic_read(&folio->_entire_mapcount) + 1; } static inline int folio_large_mapcount(const struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_large_mapcount) + 1; } /** * folio_mapcount() - Number of mappings of this folio. * @folio: The folio. * * The folio mapcount corresponds to the number of present user page table * entries that reference any part of a folio. Each such present user page * table entry must be paired with exactly on folio reference. * * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts * exactly once. * * For hugetlb folios, each abstracted "hugetlb" user page table entry that * references the entire folio counts exactly once, even when such special * page table entries are comprised of multiple ordinary page table entries. * * Will report 0 for pages which cannot be mapped into userspace, such as * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ static inline int folio_mapcount(const struct folio *folio) { int mapcount; if (likely(!folio_test_large(folio))) { mapcount = atomic_read(&folio->_mapcount) + 1; if (page_mapcount_is_type(mapcount)) mapcount = 0; return mapcount; } return folio_large_mapcount(folio); } /** * folio_mapped - Is this folio mapped into userspace? * @folio: The folio. * * Return: True if any page in this folio is referenced by user page tables. */ static inline bool folio_mapped(const struct folio *folio) { return folio_mapcount(folio) >= 1; } /* * Return true if this page is mapped into pagetables. * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ static inline bool page_mapped(const struct page *page) { return folio_mapped(page_folio(page)); } static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } static inline struct folio *virt_to_folio(const void *x) { struct page *page = virt_to_page(x); return page_folio(page); } void __folio_put(struct folio *folio); void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { return PAGE_SIZE << compound_order(page); } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { return PAGE_SHIFT + compound_order(page); } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return compound_order(page); } /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { return PAGE_SIZE << thp_order(page); } #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte, vma); return pte; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) /** * folio_get - Increment the reference count on a folio. * @folio: The folio. * * Context: May be called in any context, as long as you know that * you have a refcount on the folio. If you do not already have one, * folio_try_get() may be the right interface for you to use. */ static inline void folio_get(struct folio *folio) { VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio); folio_ref_inc(folio); } static inline void get_page(struct page *page) { struct folio *folio = page_folio(page); if (WARN_ON_ONCE(folio_test_slab(folio))) return; folio_get(folio); } static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); if (WARN_ON_ONCE(page_ref_count(page) <= 0)) return false; page_ref_inc(page); return true; } /** * folio_put - Decrement the reference count on a folio. * @folio: The folio. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put() unless you can be sure that it wasn't the * last reference. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put(struct folio *folio) { if (folio_put_testzero(folio)) __folio_put(folio); } /** * folio_put_refs - Reduce the reference count on a folio. * @folio: The folio. * @refs: The amount to subtract from the folio's reference count. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put_refs() unless you can be sure that these weren't * the last references. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put_refs(struct folio *folio, int refs) { if (folio_ref_sub_and_test(folio, refs)) __folio_put(folio); } void folios_put_refs(struct folio_batch *folios, unsigned int *refs); /* * union release_pages_arg - an array of pages or folios * * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. * * The transparent union syntax for this kind of "any of these * argument types" is all kinds of ugly, so look away. */ typedef union { struct page **pages; struct folio **folios; struct encoded_page **encoded_pages; } release_pages_arg __attribute__ ((__transparent_union__)); void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. * @folios: The folios. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need to * reinitialise it. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folios_put(struct folio_batch *folios) { folios_put_refs(folios, NULL); } static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); if (folio_test_slab(folio)) return; folio_put(folio); } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() * provides safe operation for get_user_pages(), folio_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); void unpin_folio(struct folio *folio); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); void unpin_user_folio(struct folio *folio, unsigned long npages); void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } #ifndef CONFIG_MMU static inline bool is_nommu_shared_mapping(vm_flags_t flags) { /* * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of * a file mapping. R/O MAP_PRIVATE mappings might still modify * underlying memory if ptrace is active, so this is only possible if * ptrace does not apply. Note that there is no mprotect() to upgrade * write permissions later. */ return flags & (VM_MAYSHARE | VM_MAYOVERLAY); } #endif #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { return (PF_POISONED_CHECK(page)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif static inline int folio_nid(const struct folio *folio) { return page_to_nid(&folio->page); } #ifdef CONFIG_NUMA_BALANCING /* page access time bits needs to hold at least 4 seconds */ #define PAGE_ACCESS_TIME_MIN_BITS 12 #if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS #define PAGE_ACCESS_TIME_BUCKETS \ (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) #else #define PAGE_ACCESS_TIME_BUCKETS 0 #endif #define PAGE_ACCESS_TIME_MASK \ (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid); } #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int folio_last_cpupid(struct folio *folio) { return folio->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int folio_last_cpupid(struct folio *folio) { return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ static inline int folio_xchg_access_time(struct folio *folio, int time) { int last_time; last_time = folio_xchg_last_cpupid(folio, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { unsigned int pid_bit; pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) { __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } bool folio_use_access_time(struct folio *folio); #else /* !CONFIG_NUMA_BALANCING */ static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return folio_nid(folio); /* XXX */ } static inline int folio_xchg_access_time(struct folio *folio, int time) { return 0; } static inline int folio_last_cpupid(struct folio *folio) { return folio_nid(folio); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { } static inline bool folio_use_access_time(struct folio *folio) { return false; } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag = KASAN_TAG_KERNEL; if (kasan_enabled()) { tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { unsigned long old_flags, flags; if (!kasan_enabled()) return; tag ^= 0xff; old_flags = READ_ONCE(page->flags); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) { if (kasan_enabled()) page_kasan_tag_set(page, KASAN_TAG_KERNEL); } #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } static inline struct zone *folio_zone(const struct folio *folio) { return page_zone(&folio->page); } static inline pg_data_t *folio_pgdat(const struct folio *folio) { return page_pgdat(&folio->page); } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif /** * folio_pfn - Return the Page Frame Number of a folio. * @folio: The folio. * * A folio may contain multiple pages. The pages have consecutive * Page Frame Numbers. * * Return: The Page Frame Number of the first page in the folio. */ static inline unsigned long folio_pfn(const struct folio *folio) { return page_to_pfn(&folio->page); } static inline struct folio *pfn_folio(unsigned long pfn) { return page_folio(pfn_to_page(pfn)); } static inline bool folio_has_pincount(const struct folio *folio) { if (IS_ENABLED(CONFIG_64BIT)) return folio_test_large(folio); return folio_order(folio) > 1; } /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. * * This function checks if a folio has been pinned via a call to * a function in the pin_user_pages() family. * * For small folios, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal folio references". * * False positives are OK, because: a) it's unlikely for a folio to * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * * For most large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * Return: True, if it is likely that the folio has been "dma-pinned". * False, if the folio is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { if (folio_has_pincount(folio)) return atomic_read(&folio->_pincount) > 0; /* * folio_ref_count() is signed. If that refcount overflows, then * folio_ref_count() returns a negative value, and callers will avoid * further incrementing the refcount. * * Here, for that overflow case, use the sign bit to count a little * bit higher via unsigned math, and thus still get an accurate result. */ return ((unsigned int)folio_ref_count(folio)) >= GUP_PIN_COUNTING_BIAS; } /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, struct folio *folio) { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; return folio_maybe_dma_pinned(folio); } /** * is_zero_page - Query if a page is a zero page * @page: The page to query * * This returns true if @page is one of the permanent zero pages. */ static inline bool is_zero_page(const struct page *page) { return is_zero_pfn(page_to_pfn(page)); } /** * is_zero_folio - Query if a folio is a zero page * @folio: The folio to query * * This returns true if @folio is one of the permanent zero pages. */ static inline bool is_zero_folio(const struct folio *folio) { return is_zero_page(&folio->page); } /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */ #ifdef CONFIG_MIGRATION static inline bool folio_is_longterm_pinnable(struct folio *folio) { #ifdef CONFIG_CMA int mt = folio_migratetype(folio); if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif /* The zero page can be "pinned" but gets special handling. */ if (is_zero_folio(folio)) return true; /* Coherent device memory must always allow eviction. */ if (folio_is_device_coherent(folio)) return false; /* * Filesystems can only tolerate transient delays to truncate and * hole-punch operations */ if (folio_is_fsdax(folio)) return false; /* Otherwise, non-movable zone folios can be pinned. */ return !folio_is_zone_movable(folio); } #else static inline bool folio_is_longterm_pinnable(struct folio *folio) { return true; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } /** * folio_nr_pages - The number of pages in the folio. * @folio: The folio. * * Return: A positive power of two. */ static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; return folio_large_nr_pages(folio); } /* Only hugetlbfs can allocate folios larger than MAX_ORDER */ #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE #define MAX_FOLIO_NR_PAGES (1UL << PUD_ORDER) #else #define MAX_FOLIO_NR_PAGES MAX_ORDER_NR_PAGES #endif /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ static inline long compound_nr(struct page *page) { struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags)) return 1; return folio_large_nr_pages(folio); } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ static inline long thp_nr_pages(struct page *page) { return folio_nr_pages((struct folio *)page); } /** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. * * If you have physically contiguous memory which may span more than * one folio (eg a &struct bio_vec), use this function to move from one * folio to the next. Do not use it if the memory is only virtually * contiguous as the folios are almost certainly not adjacent to each * other. This is the folio equivalent to writing ``page++``. * * Context: We assume that the folios are refcounted and/or locked at a * higher level and do not adjust the reference counts. * Return: The next struct folio. */ static inline struct folio *folio_next(struct folio *folio) { return (struct folio *)folio_page(folio, folio_nr_pages(folio)); } /** * folio_shift - The size of the memory described by this folio. * @folio: The folio. * * A folio represents a number of bytes which is a power-of-two in size. * This function tells you which power-of-two the folio is. See also * folio_size() and folio_order(). * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The base-2 logarithm of the size of this folio. */ static inline unsigned int folio_shift(const struct folio *folio) { return PAGE_SHIFT + folio_order(folio); } /** * folio_size - The number of bytes in a folio. * @folio: The folio. * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The number of bytes in this folio. */ static inline size_t folio_size(const struct folio *folio) { return PAGE_SIZE << folio_order(folio); } /** * folio_maybe_mapped_shared - Whether the folio is mapped into the page * tables of more than one MM * @folio: The folio. * * This function checks if the folio maybe currently mapped into more than one * MM ("maybe mapped shared"), or if the folio is certainly mapped into a single * MM ("mapped exclusively"). * * For KSM folios, this function also returns "mapped shared" when a folio is * mapped multiple times into the same MM, because the individual page mappings * are independent. * * For small anonymous folios and anonymous hugetlb folios, the return * value will be exactly correct: non-KSM folios can only be mapped at most once * into an MM, and they cannot be partially mapped. KSM folios are * considered shared even if mapped multiple times into the same MM. * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly * indicate "mapped shared" (false positive) if a folio was mapped by * more than two MMs at one point in time. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. * * Further, this function only considers current page table mappings that * are tracked using the folio mapcount(s). * * This function does not consider: * #. If the folio might get mapped in the (near) future (e.g., swapcache, * pagecache, temporary unmapping for migration). * #. If the folio is mapped differently (VM_PFNMAP). * #. If hugetlb page table sharing applies. Callers might want to check * hugetlb_pmd_shared(). * * Return: Whether the folio is estimated to be mapped into more than one MM. */ static inline bool folio_maybe_mapped_shared(struct folio *folio) { int mapcount = folio_mapcount(folio); /* Only partially-mappable folios require more care. */ if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) return mapcount > 1; /* * vm_insert_page() without CONFIG_TRANSPARENT_HUGEPAGE ... * simply assume "mapped shared", nobody should really care * about this for arbitrary kernel allocations. */ if (!IS_ENABLED(CONFIG_MM_ID)) return true; /* * A single mapping implies "mapped exclusively", even if the * folio flag says something different: it's easier to handle this * case here instead of on the RMAP hot path. */ if (mapcount <= 1) return false; return folio_test_large_maybe_mapped_shared(folio); } #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { return 0; } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif static inline void *folio_address(const struct folio *folio) { return page_address(&folio->page); } /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(const struct page *page) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)page->lru.next & BIT(1); } /* * Return true only if the folio has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool folio_is_pfmemalloc(const struct folio *folio) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)folio->lru.next & BIT(1); } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { page->lru.next = NULL; } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ bool reclaim_pt; /* Need reclaim page tables? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; /* * Whether to drop the pte markers, for example, the uffd-wp information for * file-backed memory. This should only be specified when we will completely * drop the page in the mm, either by truncation or unmapping of the vma. By * default, the flag is not set. */ #define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit_signals(struct task_struct *t); static inline int task_mm_cid(struct task_struct *t) { return t->mm_cid; } #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } static inline int task_mm_cid(struct task_struct *t) { /* * Use the processor id as a fall-back when the mm cid feature is * disabled. This provides functional per-cpu data structure accesses * in user-space, althrough it won't provide the memory usage benefits. */ return raw_smp_processor_id(); } #endif #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details); static inline void zap_vma_pages(struct vm_area_struct *vma) { zap_page_range_single(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL); } void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long start, unsigned long end, unsigned long tree_end, bool mm_wr_locked); struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); struct follow_pfnmap_args { /** * Inputs: * @vma: Pointer to @vm_area_struct struct * @address: the virtual address to walk */ struct vm_area_struct *vma; unsigned long address; /** * Internals: * * The caller shouldn't touch any of these. */ spinlock_t *lock; pte_t *ptep; /** * Outputs: * * @pfn: the PFN of the address * @addr_mask: address mask covering pfn * @pgprot: the pgprot_t of the mapping * @writable: whether the mapping is writable * @special: whether the mapping is a special mapping (real PFN maps) */ unsigned long pfn; unsigned long addr_mask; pgprot_t pgprot; bool writable; bool special; }; int follow_pfnmap_start(struct follow_pfnmap_args *args); void follow_pfnmap_end(struct follow_pfnmap_args *args); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int generic_error_remove_folio(struct address_space *mapping, struct folio *folio); struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long address, struct pt_regs *regs); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { unmap_mapping_range(mapping, holebegin, holelen, 0); } static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); #ifdef CONFIG_BPF_SYSCALL extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); #endif long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); /* * Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT. */ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, unsigned long addr, int gup_flags, struct vm_area_struct **vmap) { struct page *page; struct vm_area_struct *vma; int got; if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT))) return ERR_PTR(-EINVAL); got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); if (got < 0) return ERR_PTR(got); vma = vma_lookup(mm, addr); if (WARN_ON_ONCE(!vma)) { put_page(page); return ERR_PTR(-EINVAL); } *vmap = vma; return page; } long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, struct folio **folios, unsigned int max_folios, pgoff_t *offset); int folio_add_pins(struct folio *folio, unsigned int pins); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; struct page *get_dump_page(unsigned long addr, int *locked); bool folio_mark_dirty(struct folio *folio); bool folio_mark_dirty_lock(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However * for now all the callers are only use one of the flags at the same * time. */ /* * Whether we should manually check if we can map individual PTEs writable, * because something (e.g., COW, uffd-wp) blocks that from happening for all * PTEs automatically in a writable mapping. */ #define MM_CP_TRY_CHANGE_WRITABLE (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ #define MM_CP_UFFD_WP (1UL << 2) /* do wp */ #define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */ #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); extern long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long cp_flags); extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) { return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; } /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { return percpu_counter_read_positive(&mm->rss_stat[member]); } void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { percpu_counter_add(&mm->rss_stat[member], value); mm_trace_rss_stat(mm, member); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { percpu_counter_inc(&mm->rss_stat[member]); mm_trace_rss_stat(mm, member); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { percpu_counter_dec(&mm->rss_stat[member]); mm_trace_rss_stat(mm, member); } /* Optimized variant when folio is already known not to be anon */ static inline int mm_counter_file(struct folio *folio) { if (folio_test_swapbacked(folio)) return MM_SHMEMPAGES; return MM_FILEPAGES; } static inline int mm_counter(struct folio *folio) { if (folio_test_anon(folio)) return MM_ANONPAGES; return mm_counter_file(folio); } static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { return max(mm->hiwater_rss, get_mm_rss(mm)); } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); } static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); if ((mm)->hiwater_rss < _rss) (mm)->hiwater_rss = _rss; } static inline void update_hiwater_vm(struct mm_struct *mm) { if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm; } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { mm->hiwater_rss = get_mm_rss(mm); } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { unsigned long hiwater_rss = get_mm_hiwater_rss(mm); if (*maxrss < hiwater_rss) *maxrss = hiwater_rss; } #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #endif #ifndef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP static inline bool pmd_special(pmd_t pmd) { return false; } static inline pmd_t pmd_mkspecial(pmd_t pmd) { return pmd; } #endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ #ifndef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP static inline bool pud_special(pud_t pud) { return false; } static inline pud_t pud_mkspecial(pud_t pud) { return pud; } #endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; } #endif extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pte_t *ptep; __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); return ptep; } #ifdef __PAGETABLE_P4D_FOLDED static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return 0; } #else int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif #if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU) static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } static inline void mm_inc_nr_puds(struct mm_struct *mm) {} static inline void mm_dec_nr_puds(struct mm_struct *mm) {} #else int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { atomic_long_set(&mm->pgtables_bytes, 0); } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return atomic_long_read(&mm->pgtables_bytes); } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } #else static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {} static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return 0; } static inline void mm_inc_nr_ptes(struct mm_struct *mm) {} static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} #endif int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address); } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU */ static inline struct ptdesc *virt_to_ptdesc(const void *x) { return page_ptdesc(virt_to_page(x)); } static inline void *ptdesc_to_virt(const struct ptdesc *pt) { return page_to_virt(ptdesc_page(pt)); } static inline void *ptdesc_address(const struct ptdesc *pt) { return folio_address(ptdesc_folio(pt)); } static inline bool pagetable_is_reserved(struct ptdesc *pt) { return folio_test_reserved(ptdesc_folio(pt)); } /** * pagetable_alloc - Allocate pagetables * @gfp: GFP flags * @order: desired pagetable order * * pagetable_alloc allocates memory for page tables as well as a page table * descriptor to describe that memory. * * Return: The ptdesc describing the allocated page tables. */ static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order); return page_ptdesc(page); } #define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) /** * pagetable_free - Free pagetables * @pt: The page table descriptor * * pagetable_free frees the memory of all page tables described by a page * table descriptor and the memory for the descriptor itself. */ static inline void pagetable_free(struct ptdesc *pt) { struct page *page = ptdesc_page(pt); __free_pages(page, compound_order(page)); } #if defined(CONFIG_SPLIT_PTE_PTLOCKS) #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); bool ptlock_alloc(struct ptdesc *ptdesc); void ptlock_free(struct ptdesc *ptdesc); static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { return ptdesc->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) { } static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { return &ptdesc->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) { BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); return ptlock_ptr(virt_to_ptdesc(pte)); } static inline bool ptlock_init(struct ptdesc *ptdesc) { /* * prep_new_page() initialize page->private (and therefore page->ptl) * with 0. Make sure nobody took it in use in between. * * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ VM_BUG_ON_PAGE(*(unsigned long *)&ptdesc->ptl, ptdesc_page(ptdesc)); if (!ptlock_alloc(ptdesc)) return false; spin_lock_init(ptlock_ptr(ptdesc)); return true; } #else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline void __pagetable_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); ptlock_free(ptdesc); __folio_clear_pgtable(folio); lruvec_stat_sub_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor_free(struct ptdesc *ptdesc) { pagetable_dtor(ptdesc); pagetable_free(ptdesc); } static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) { if (!ptlock_init(ptdesc)) return false; __pagetable_ctor(ptdesc); return true; } pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) { pte_t *pte; __cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp)); return pte; } static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { return __pte_offset_map(pmd, addr, NULL); } pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { pte_t *pte; __cond_lock(RCU, __cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp))); return pte; } pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp, spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ pte_unmap(pte); \ } while (0) #define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd)) #define pte_alloc_map(mm, pmd, address) \ (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ (pte_alloc(mm, pmd) ? \ NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) #if defined(CONFIG_SPLIT_PMD_PTLOCKS) static inline struct page *pmd_pgtable_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); } static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd) { return page_ptdesc(pmd_pgtable_page(pmd)); } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_ptdesc(pmd)); } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE ptdesc->pmd_huge_pte = NULL; #endif return ptlock_init(ptdesc); } #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); return ptl; } static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) { if (!pmd_ptlock_init(ptdesc)) return false; ptdesc_pmd_pts_init(ptdesc); __pagetable_ctor(ptdesc); return true; } /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be * considered ready to switch to split PUD locks yet; there may be places * which need to be converted from page_table_lock. */ static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) { return &mm->page_table_lock; } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { spinlock_t *ptl = pud_lockptr(mm, pud); spin_lock(ptl); return ptl; } static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { __pagetable_ctor(ptdesc); } static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc) { __pagetable_ctor(ptdesc); } static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc) { __pagetable_ctor(ptdesc); } extern void __init pagecache_init(void); extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ void free_reserved_page(struct page *page); static inline void mark_page_reserved(struct page *page) { SetPageReserved(page); adjust_managed_page_count(page, -1); } static inline void free_reserved_ptdesc(struct ptdesc *pt) { free_reserved_page(ptdesc_page(pt)); } /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within * range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, poison, "unused kernel image (initmem)"); } static inline unsigned long get_num_physpages(void) { int nid; unsigned long phys_pages = 0; for_each_online_node(nid) phys_pages += node_present_pages(nid); return phys_pages; } /* * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in an * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void mem_init(void); extern void __init mmap_init(void); extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); static inline void show_mem(void) { __show_mem(0, NULL, MAX_NR_ZONES - 1); } extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); #define vma_interval_tree_foreach(vma, root, start, last) \ for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root); struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node); #endif #define anon_vma_interval_tree_foreach(avc, root, start, last) \ for (avc = anon_vma_interval_tree_iter_first(root, start, last); \ avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, bool write); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, unsigned long end_data, unsigned long start_data) { if (rlim < RLIM_INFINITY) { if (((new - start) + (end_data - start_data)) > rlim) return -ENOSPC; } return 0; } extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); static inline unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return __get_unmapped_area(file, addr, len, pgoff, flags, 0); } extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) { /* Ignore errors */ (void) __mm_populate(addr, len, 1); } #else static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* This takes the mm semaphore itself */ extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); struct vm_unmapped_area_info { #define VM_UNMAPPED_AREA_TOPDOWN 1 unsigned long flags; unsigned long length; unsigned long low_limit; unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; unsigned long start_gap; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); /* * Look up the first VMA which intersects the interval [start_addr, end_addr) * NULL if none. Assume start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr); /** * vma_lookup() - Find a VMA at a specific address * @mm: The process address space. * @addr: The user address. * * Return: The vm_area_struct at the given address, %NULL otherwise. */ static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { return mtree_load(&mm->mm_mt, addr); } static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) { if (vma->vm_flags & VM_GROWSDOWN) return stack_guard_gap; /* See reasoning around the VM_SHADOW_STACK definition */ if (vma->vm_flags & VM_SHADOW_STACK) return PAGE_SIZE; return 0; } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { unsigned long gap = stack_guard_start_gap(vma); unsigned long vm_start = vma->vm_start; vm_start -= gap; if (vm_start > vma->vm_start) vm_start = 0; return vm_start; } static inline unsigned long vm_end_gap(struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; if (vma->vm_flags & VM_GROWSUP) { vm_end += stack_guard_gap; if (vm_end < vma->vm_end) vm_end = -PAGE_SIZE; } return vm_end; } static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { struct vm_area_struct *vma = vma_lookup(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; return vma; } static inline bool range_in_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return (vma && vma->vm_start <= start && end <= vma->vm_end); } #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); #else static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) { return __pgprot(0); } static inline void vma_set_page_prot(struct vm_area_struct *vma) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } #endif void vma_set_file(struct vm_area_struct *vma, struct file *file); #ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif struct vm_area_struct *find_extend_vma_locked(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page, bool write); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { int err = vm_insert_page(vma, addr, page); if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } #ifndef io_remap_pfn_range static inline int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); } #endif static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) return VM_FAULT_OOM; else if (err == -EHWPOISON) return VM_FAULT_HWPOISON; return VM_FAULT_SIGBUS; } /* * Convert errno to return value for ->page_mkwrite() calls. * * This should eventually be merged with vmf_error() above, but will need a * careful audit of all vmf_error() callers. */ static inline vm_fault_t vmf_fs_error(int err) { if (err == 0) return VM_FAULT_LOCKED; if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) return -ENOMEM; if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; return 0; } /* * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ static inline bool gup_can_follow_protnone(struct vm_area_struct *vma, unsigned int flags) { /* * If callers don't want to honor NUMA hinting faults, no need to * determine if we would actually have to trigger a NUMA hinting fault. */ if (!(flags & FOLL_HONOR_NUMA_FAULT)) return true; /* * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs. * * Requiring a fault here even for inaccessible VMAs would mean that * FOLL_FORCE cannot make any progress, because handle_mm_fault() * refuses to process NUMA hinting faults in inaccessible VMAs. */ return !vma_is_accessible(vma); } typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); extern bool _page_poisoning_enabled_early; DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled); static inline bool page_poisoning_enabled(void) { return _page_poisoning_enabled_early; } /* * For use in fast paths after init_mem_debugging() has run, or when a * false negative result is not harmful when called too early. */ static inline bool page_poisoning_enabled_static(void) { return static_branch_unlikely(&_page_poisoning_enabled); } static inline void kernel_poison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_poison_pages(page, numpages); } static inline void kernel_unpoison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_unpoison_pages(page, numpages); } #else static inline bool page_poisoning_enabled(void) { return false; } static inline bool page_poisoning_enabled_static(void) { return false; } static inline void __kernel_poison_pages(struct page *page, int nunmpages) { } static inline void kernel_poison_pages(struct page *page, int numpages) { } static inline void kernel_unpoison_pages(struct page *page, int numpages) { } #endif DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); static inline bool want_init_on_alloc(gfp_t flags) { if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc)) return true; return flags & __GFP_ZERO; } DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, &init_on_free); } extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled_early; } /* * For use in fast paths after mem_debugging_and_hardening_init() has run, * or when a false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; return static_branch_unlikely(&_debug_pagealloc_enabled); } /* * To support DEBUG_PAGEALLOC architecture must ensure that * __kernel_map_pages() never fails */ extern void __kernel_map_pages(struct page *page, int numpages, int enable); #ifdef CONFIG_DEBUG_PAGEALLOC static inline void debug_pagealloc_map_pages(struct page *page, int numpages) { if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 1); } static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) { if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 0); } extern unsigned int _debug_guardpage_minorder; DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { return _debug_guardpage_minorder; } static inline bool debug_guardpage_enabled(void) { return static_branch_unlikely(&_debug_guardpage_enabled); } static inline bool page_is_guard(struct page *page) { if (!debug_guardpage_enabled()) return false; return PageGuard(page); } bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { if (!debug_guardpage_enabled()) return false; return __set_page_guard(zone, page, order); } void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) { if (!debug_guardpage_enabled()) return; __clear_page_guard(zone, page, order); } #else /* CONFIG_DEBUG_PAGEALLOC */ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); extern int in_gate_area_no_mm(unsigned long addr); extern int in_gate_area(struct mm_struct *mm, unsigned long addr); #else static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } static inline int in_gate_area_no_mm(unsigned long addr) { return 0; } static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } #endif /* __HAVE_ARCH_GATE_AREA */ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); void drop_slab(void); #ifndef CONFIG_MMU #define randomize_va_space 0 #else extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); #ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); #else static inline void print_vma_addr(char *prefix, unsigned long rip) { } #endif void *sparse_buffer_alloc(unsigned long size); unsigned long section_map_size(void); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap, unsigned long ptpfn, unsigned long flags); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); void vmemmap_set_pmd(pmd_t *pmd, void *p, int node, unsigned long addr, unsigned long next); int vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate_hvo(unsigned long start, unsigned long end, int node, unsigned long headsize); int vmemmap_undo_hvo(unsigned long start, unsigned long end, int node, unsigned long headsize); void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node, unsigned long headsize); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ if (altmap) return altmap->reserve + altmap->free; return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { altmap->alloc -= nr_pfns; } #else static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { } #endif #define VMEMMAP_RESERVE_NR 2 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { unsigned long nr_pages; unsigned long nr_vmemmap_pages; if (!pgmap || !is_power_of_2(sizeof(struct page))) return false; nr_pages = pgmap_vmemmap_nr(pgmap); nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT); /* * For vmemmap optimization with DAX we need minimum 2 vmemmap * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst */ return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR); } /* * If we don't have an architecture override, use the generic rule */ #ifndef vmemmap_can_optimize #define vmemmap_can_optimize __vmemmap_can_optimize #endif #else static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { return false; } #endif enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, MF_UNPOISON = 1 << 4, MF_SW_SIMULATED = 1 << 5, MF_NO_RETRY = 1 << 6, MF_MEM_PRE_REMOVE = 1 << 7, }; int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE /* * Sysfs entries for memory failure handling statistics. */ extern const struct attribute_group memory_failure_attr_group; extern void memory_failure_queue(unsigned long pfn, int flags); extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { } static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void num_poisoned_pages_inc(unsigned long pfn) { } static inline void num_poisoned_pages_sub(unsigned long pfn, long i) { } #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); #else static inline void memblk_nr_poison_inc(unsigned long pfn) { } static inline void memblk_nr_poison_sub(unsigned long pfn, long i) { } #endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) { return -ENXIO; } #endif #ifndef arch_is_platform_page static inline bool arch_is_platform_page(u64 paddr) { return false; } #endif /* * Error handlers for various types of pages. */ enum mf_result { MF_IGNORED, /* Error: cannot be handled */ MF_FAILED, /* Error: handling failed */ MF_DELAYED, /* Will be handled later */ MF_RECOVERED, /* Successfully recovered */ }; enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_GET_HWPOISON, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, MF_MSG_DIRTY_MLOCKED_LRU, MF_MSG_CLEAN_MLOCKED_LRU, MF_MSG_DIRTY_UNEVICTABLE_LRU, MF_MSG_CLEAN_UNEVICTABLE_LRU, MF_MSG_DIRTY_LRU, MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_ALREADY_POISONED, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) void folio_zero_user(struct folio *folio, unsigned long addr_hint); int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? * @vma: Pointer to the struct vm_area_struct to consider * * Whether transhuge page-table entries are considered "special" following * the definition in vm_normal_page(). * * Return: true if transhuge page-table entries should be considered special, * false otherwise. */ static inline bool vma_is_special_huge(const struct vm_area_struct *vma) { return vma_is_dax(vma) || (vma->vm_file && (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else static inline void setup_nr_node_ids(void) {} #endif extern int memcmp_pages(struct page *page1, struct page *page2); static inline int pages_identical(struct page *page1, struct page *page2) { return !memcmp_pages(page1, page2); } #ifdef CONFIG_MAPPING_DIRTY_HELPERS unsigned long clean_record_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, pgoff_t bitmap_pgoff, unsigned long *bitmap, pgoff_t *start, pgoff_t *end); unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name); #else static inline int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { return 0; } #endif #ifdef CONFIG_UNACCEPTED_MEMORY bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size); void accept_memory(phys_addr_t start, unsigned long size); #else static inline bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size) { return false; } static inline void accept_memory(phys_addr_t start, unsigned long size) { } #endif static inline bool pfn_is_unaccepted_memory(unsigned long pfn) { return range_contains_unaccepted_memory(pfn << PAGE_SHIFT, PAGE_SIZE); } void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); int reserve_mem_release_by_name(const char *name); #ifdef CONFIG_64BIT int do_mseal(unsigned long start, size_t len_in, unsigned long flags); #else static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags) { /* noop on 32 bit */ return 0; } #endif /* * user_alloc_needs_zeroing checks if a user folio from page allocator needs to * be zeroed or not. */ static inline bool user_alloc_needs_zeroing(void) { /* * for user folios, arch with cache aliasing requires cache flush and * arc changes folio->flags to make icache coherent with dcache, so * always return false to make caller use * clear_user_page()/clear_user_highpage(). */ return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() || !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc); } int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); /* * mseal of userspace process's system mappings. */ #ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS #define VM_SEALED_SYSMAP VM_SEALED #else #define VM_SEALED_SYSMAP VM_NONE #endif #endif /* _LINUX_MM_H */ |
| 216 217 575 409 239 239 172 151 456 458 430 458 578 578 130 129 26 14 14 14 7 23 23 7 7 21 21 458 458 458 447 31 458 456 458 20 20 20 20 20 20 20 458 20 20 20 20 20 25 25 458 458 20 217 217 9 9 9 216 217 216 217 216 215 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 | // SPDX-License-Identifier: GPL-2.0-only /* * proc/fs/generic.c --- generic routines for the proc-fs * * This file contains generic proc-fs routines for handling * directories and files. * * Copyright (C) 1991, 1992 Linus Torvalds. * Copyright (C) 1997 Theodore Ts'o */ #include <linux/cache.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/slab.h> #include <linux/printk.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/idr.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/uaccess.h> #include <linux/seq_file.h> #include "internal.h" static DEFINE_RWLOCK(proc_subdir_lock); struct kmem_cache *proc_dir_entry_cache __ro_after_init; void pde_free(struct proc_dir_entry *pde) { if (S_ISLNK(pde->mode)) kfree(pde->data); if (pde->name != pde->inline_name) kfree(pde->name); kmem_cache_free(proc_dir_entry_cache, pde); } static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len) { if (len < de->namelen) return -1; if (len > de->namelen) return 1; return memcmp(name, de->name, len); } static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir) { return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry, subdir_node); } static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir) { return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry, subdir_node); } static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, const char *name, unsigned int len) { struct rb_node *node = dir->subdir.rb_node; while (node) { struct proc_dir_entry *de = rb_entry(node, struct proc_dir_entry, subdir_node); int result = proc_match(name, de, len); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return de; } return NULL; } static bool pde_subdir_insert(struct proc_dir_entry *dir, struct proc_dir_entry *de) { struct rb_root *root = &dir->subdir; struct rb_node **new = &root->rb_node, *parent = NULL; /* Figure out where to put new node */ while (*new) { struct proc_dir_entry *this = rb_entry(*new, struct proc_dir_entry, subdir_node); int result = proc_match(de->name, this, de->namelen); parent = *new; if (result < 0) new = &(*new)->rb_left; else if (result > 0) new = &(*new)->rb_right; else return false; } /* Add new node and rebalance tree. */ rb_link_node(&de->subdir_node, parent, new); rb_insert_color(&de->subdir_node, root); return true; } static int proc_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct proc_dir_entry *de = PDE(inode); int error; error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, iattr); proc_set_user(de, inode->i_uid, inode->i_gid); de->mode = inode->i_mode; return 0; } static int proc_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_dir_entry *de = PDE(inode); if (de) { nlink_t nlink = READ_ONCE(de->nlink); if (nlink > 0) { set_nlink(inode, nlink); } } generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); return 0; } static const struct inode_operations proc_file_inode_operations = { .setattr = proc_notify_change, }; /* * This function parses a name such as "tty/driver/serial", and * returns the struct proc_dir_entry for "/proc/tty/driver", and * returns "serial" in residual. */ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret, const char **residual) { const char *cp = name, *next; struct proc_dir_entry *de; de = *ret ?: &proc_root; while ((next = strchr(cp, '/')) != NULL) { de = pde_subdir_find(de, cp, next - cp); if (!de) { WARN(1, "name '%s'\n", name); return -ENOENT; } cp = next + 1; } *residual = cp; *ret = de; return 0; } static int xlate_proc_name(const char *name, struct proc_dir_entry **ret, const char **residual) { int rv; read_lock(&proc_subdir_lock); rv = __xlate_proc_name(name, ret, residual); read_unlock(&proc_subdir_lock); return rv; } static DEFINE_IDA(proc_inum_ida); #define PROC_DYNAMIC_FIRST 0xF0000000U /* * Return an inode number between PROC_DYNAMIC_FIRST and * 0xffffffff, or zero on failure. */ int proc_alloc_inum(unsigned int *inum) { int i; i = ida_alloc_max(&proc_inum_ida, UINT_MAX - PROC_DYNAMIC_FIRST, GFP_KERNEL); if (i < 0) return i; *inum = PROC_DYNAMIC_FIRST + (unsigned int)i; return 0; } void proc_free_inum(unsigned int inum) { ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); } static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0) return 0; /* revalidate */ return 1; } static int proc_misc_d_delete(const struct dentry *dentry) { return atomic_read(&PDE(d_inode(dentry))->in_use) < 0; } static const struct dentry_operations proc_misc_dentry_ops = { .d_revalidate = proc_misc_d_revalidate, .d_delete = proc_misc_d_delete, }; /* * Don't create negative dentries here, return -ENOENT by hand * instead. */ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, struct proc_dir_entry *de) { struct inode *inode; read_lock(&proc_subdir_lock); de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len); if (de) { pde_get(de); read_unlock(&proc_subdir_lock); inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); d_set_d_op(dentry, de->proc_dops); return d_splice_alias(inode, dentry); } read_unlock(&proc_subdir_lock); return ERR_PTR(-ENOENT); } struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb); if (fs_info->pidonly == PROC_PIDONLY_ON) return ERR_PTR(-ENOENT); return proc_lookup_de(dir, dentry, PDE(dir)); } /* * This returns non-zero if at EOF, so that the /proc * root directory can use this and check if it should * continue with the <pid> entries.. * * Note that the VFS-layer doesn't care about the return * value of the readdir() call, as long as it's non-negative * for success.. */ int proc_readdir_de(struct file *file, struct dir_context *ctx, struct proc_dir_entry *de) { int i; if (!dir_emit_dots(file, ctx)) return 0; i = ctx->pos - 2; read_lock(&proc_subdir_lock); de = pde_subdir_first(de); for (;;) { if (!de) { read_unlock(&proc_subdir_lock); return 0; } if (!i) break; de = pde_subdir_next(de); i--; } do { struct proc_dir_entry *next; pde_get(de); read_unlock(&proc_subdir_lock); if (!dir_emit(ctx, de->name, de->namelen, de->low_ino, de->mode >> 12)) { pde_put(de); return 0; } ctx->pos++; read_lock(&proc_subdir_lock); next = pde_subdir_next(de); pde_put(de); de = next; } while (de); read_unlock(&proc_subdir_lock); return 1; } int proc_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); if (fs_info->pidonly == PROC_PIDONLY_ON) return 1; return proc_readdir_de(file, ctx, PDE(inode)); } /* * These are the generic /proc directory operations. They * use the in-memory "struct proc_dir_entry" tree to parse * the /proc directory. */ static const struct file_operations proc_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = proc_readdir, }; static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { return 0; } const struct dentry_operations proc_net_dentry_ops = { .d_revalidate = proc_net_d_revalidate, .d_delete = always_delete_dentry, }; /* * proc directories can do almost nothing.. */ static const struct inode_operations proc_dir_inode_operations = { .lookup = proc_lookup, .getattr = proc_getattr, .setattr = proc_notify_change, }; /* returns the registered entry, or frees dp and returns NULL on failure */ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, struct proc_dir_entry *dp) { if (proc_alloc_inum(&dp->low_ino)) goto out_free_entry; write_lock(&proc_subdir_lock); dp->parent = dir; if (pde_subdir_insert(dir, dp) == false) { WARN(1, "proc_dir_entry '%s/%s' already registered\n", dir->name, dp->name); write_unlock(&proc_subdir_lock); goto out_free_inum; } dir->nlink++; write_unlock(&proc_subdir_lock); return dp; out_free_inum: proc_free_inum(dp->low_ino); out_free_entry: pde_free(dp); return NULL; } static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, const char *name, umode_t mode, nlink_t nlink) { struct proc_dir_entry *ent = NULL; const char *fn; struct qstr qstr; if (xlate_proc_name(name, parent, &fn) != 0) goto out; qstr.name = fn; qstr.len = strlen(fn); if (qstr.len == 0 || qstr.len >= 256) { WARN(1, "name len %u\n", qstr.len); return NULL; } if (qstr.len == 1 && fn[0] == '.') { WARN(1, "name '.'\n"); return NULL; } if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') { WARN(1, "name '..'\n"); return NULL; } if (*parent == &proc_root && name_to_int(&qstr) != ~0U) { WARN(1, "create '/proc/%s' by hand\n", qstr.name); return NULL; } if (is_empty_pde(*parent)) { WARN(1, "attempt to add to permanently empty directory"); return NULL; } ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!ent) goto out; if (qstr.len + 1 <= SIZEOF_PDE_INLINE_NAME) { ent->name = ent->inline_name; } else { ent->name = kmalloc(qstr.len + 1, GFP_KERNEL); if (!ent->name) { pde_free(ent); return NULL; } } memcpy(ent->name, fn, qstr.len + 1); ent->namelen = qstr.len; ent->mode = mode; ent->nlink = nlink; ent->subdir = RB_ROOT; refcount_set(&ent->refcnt, 1); spin_lock_init(&ent->pde_unload_lock); INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); ent->proc_dops = &proc_misc_dentry_ops; /* Revalidate everything under /proc/${pid}/net */ if ((*parent)->proc_dops == &proc_net_dentry_ops) pde_force_lookup(ent); out: return ent; } struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent, const char *dest) { struct proc_dir_entry *ent; ent = __proc_create(&parent, name, (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1); if (ent) { ent->size = strlen(dest); ent->data = kmemdup(dest, ent->size + 1, GFP_KERNEL); if (ent->data) { ent->proc_iops = &proc_link_inode_operations; ent = proc_register(parent, ent); } else { pde_free(ent); ent = NULL; } } return ent; } EXPORT_SYMBOL(proc_symlink); struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data, bool force_lookup) { struct proc_dir_entry *ent; if (mode == 0) mode = S_IRUGO | S_IXUGO; ent = __proc_create(&parent, name, S_IFDIR | mode, 2); if (ent) { ent->data = data; ent->proc_dir_ops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; if (force_lookup) { pde_force_lookup(ent); } ent = proc_register(parent, ent); } return ent; } EXPORT_SYMBOL_GPL(_proc_mkdir); struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return _proc_mkdir(name, mode, parent, data, false); } EXPORT_SYMBOL_GPL(proc_mkdir_data); struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return proc_mkdir_data(name, mode, parent, NULL); } EXPORT_SYMBOL(proc_mkdir_mode); struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) { return proc_mkdir_data(name, 0, parent, NULL); } EXPORT_SYMBOL(proc_mkdir); struct proc_dir_entry *proc_create_mount_point(const char *name) { umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO; struct proc_dir_entry *ent, *parent = NULL; ent = __proc_create(&parent, name, mode, 2); if (ent) { ent->data = NULL; ent->proc_dir_ops = NULL; ent->proc_iops = NULL; ent = proc_register(parent, ent); } return ent; } EXPORT_SYMBOL(proc_create_mount_point); struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, struct proc_dir_entry **parent, void *data) { struct proc_dir_entry *p; if ((mode & S_IFMT) == 0) mode |= S_IFREG; if ((mode & S_IALLUGO) == 0) mode |= S_IRUGO; if (WARN_ON_ONCE(!S_ISREG(mode))) return NULL; p = __proc_create(parent, name, mode, 1); if (p) { p->proc_iops = &proc_file_inode_operations; p->data = data; } return p; } static void pde_set_flags(struct proc_dir_entry *pde) { if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT) pde->flags |= PROC_ENTRY_PERMANENT; if (pde->proc_ops->proc_read_iter) pde->flags |= PROC_ENTRY_proc_read_iter; #ifdef CONFIG_COMPAT if (pde->proc_ops->proc_compat_ioctl) pde->flags |= PROC_ENTRY_proc_compat_ioctl; #endif } struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; p->proc_ops = proc_ops; pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_data); struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops) { return proc_create_data(name, mode, parent, proc_ops, NULL); } EXPORT_SYMBOL(proc_create); static int proc_seq_open(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); if (de->state_size) return seq_open_private(file, de->seq_ops, de->state_size); return seq_open(file, de->seq_ops); } static int proc_seq_release(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); if (de->state_size) return seq_release_private(inode, file); return seq_release(inode, file); } static const struct proc_ops proc_seq_ops = { /* not permanent -- can call into arbitrary seq_operations */ .proc_open = proc_seq_open, .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = proc_seq_release, }; struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; p->proc_ops = &proc_seq_ops; p->seq_ops = ops; p->state_size = state_size; pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_seq_private); static int proc_single_open(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); return single_open(file, de->single_show, de->data); } static const struct proc_ops proc_single_ops = { /* not permanent -- can call into arbitrary ->single_show */ .proc_open = proc_single_open, .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = single_release, }; struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; p->proc_ops = &proc_single_ops; p->single_show = show; pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_single_data); void proc_set_size(struct proc_dir_entry *de, loff_t size) { de->size = size; } EXPORT_SYMBOL(proc_set_size); void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) { de->uid = uid; de->gid = gid; } EXPORT_SYMBOL(proc_set_user); void pde_put(struct proc_dir_entry *pde) { if (refcount_dec_and_test(&pde->refcnt)) { proc_free_inum(pde->low_ino); pde_free(pde); } } /* * Remove a /proc entry and free it if it's not currently in use. */ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) { struct proc_dir_entry *de = NULL; const char *fn = name; unsigned int len; write_lock(&proc_subdir_lock); if (__xlate_proc_name(name, &parent, &fn) != 0) { write_unlock(&proc_subdir_lock); return; } len = strlen(fn); de = pde_subdir_find(parent, fn, len); if (de) { if (unlikely(pde_is_permanent(de))) { WARN(1, "removing permanent /proc entry '%s'", de->name); de = NULL; } else { rb_erase(&de->subdir_node, &parent->subdir); if (S_ISDIR(de->mode)) parent->nlink--; } } write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); return; } proc_entry_rundown(de); WARN(pde_subdir_first(de), "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n", __func__, de->parent->name, de->name, pde_subdir_first(de)->name); pde_put(de); } EXPORT_SYMBOL(remove_proc_entry); int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { struct proc_dir_entry *root = NULL, *de, *next; const char *fn = name; unsigned int len; write_lock(&proc_subdir_lock); if (__xlate_proc_name(name, &parent, &fn) != 0) { write_unlock(&proc_subdir_lock); return -ENOENT; } len = strlen(fn); root = pde_subdir_find(parent, fn, len); if (!root) { write_unlock(&proc_subdir_lock); return -ENOENT; } if (unlikely(pde_is_permanent(root))) { write_unlock(&proc_subdir_lock); WARN(1, "removing permanent /proc entry '%s/%s'", root->parent->name, root->name); return -EINVAL; } rb_erase(&root->subdir_node, &parent->subdir); de = root; while (1) { next = pde_subdir_first(de); if (next) { if (unlikely(pde_is_permanent(next))) { write_unlock(&proc_subdir_lock); WARN(1, "removing permanent /proc entry '%s/%s'", next->parent->name, next->name); return -EINVAL; } rb_erase(&next->subdir_node, &de->subdir); de = next; continue; } next = de->parent; if (S_ISDIR(de->mode)) next->nlink--; write_unlock(&proc_subdir_lock); proc_entry_rundown(de); if (de == root) break; pde_put(de); write_lock(&proc_subdir_lock); de = next; } pde_put(root); return 0; } EXPORT_SYMBOL(remove_proc_subtree); void *proc_get_parent_data(const struct inode *inode) { struct proc_dir_entry *de = PDE(inode); return de->parent->data; } EXPORT_SYMBOL_GPL(proc_get_parent_data); void proc_remove(struct proc_dir_entry *de) { if (de) remove_proc_subtree(de->name, de->parent); } EXPORT_SYMBOL(proc_remove); /* * Pull a user buffer into memory and pass it to the file's write handler if * one is supplied. The ->write() method is permitted to modify the * kernel-side buffer. */ ssize_t proc_simple_write(struct file *f, const char __user *ubuf, size_t size, loff_t *_pos) { struct proc_dir_entry *pde = PDE(file_inode(f)); char *buf; int ret; if (!pde->write) return -EACCES; if (size == 0 || size > PAGE_SIZE - 1) return -EINVAL; buf = memdup_user_nul(ubuf, size); if (IS_ERR(buf)) return PTR_ERR(buf); ret = pde->write(f, buf, size); kfree(buf); return ret == 0 ? size : ret; } |
| 109 97 6 91 88 4 90 2 210 223 214 109 210 218 218 219 218 218 1 166 1 55 214 55 212 1 211 210 211 10 11 3 28 28 28 91 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2003, 2004 * * This file is part of the SCTP kernel implementation * * This file contains the code relating the chunk abstraction. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Jon Grimm <jgrimm@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* This file is mostly in anticipation of future work, but initially * populate with fragment tracking for an outbound message. */ /* Initialize datamsg from memory. */ static void sctp_datamsg_init(struct sctp_datamsg *msg) { refcount_set(&msg->refcnt, 1); msg->send_failed = 0; msg->send_error = 0; msg->can_delay = 1; msg->abandoned = 0; msg->expires_at = 0; INIT_LIST_HEAD(&msg->chunks); } /* Allocate and initialize datamsg. */ static struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp) { struct sctp_datamsg *msg; msg = kmalloc(sizeof(struct sctp_datamsg), gfp); if (msg) { sctp_datamsg_init(msg); SCTP_DBG_OBJCNT_INC(datamsg); } return msg; } void sctp_datamsg_free(struct sctp_datamsg *msg) { struct sctp_chunk *chunk; /* This doesn't have to be a _safe vairant because * sctp_chunk_free() only drops the refs. */ list_for_each_entry(chunk, &msg->chunks, frag_list) sctp_chunk_free(chunk); sctp_datamsg_put(msg); } /* Final destructruction of datamsg memory. */ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) { struct sctp_association *asoc = NULL; struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_ulpevent *ev; int error, sent; /* Release all references. */ list_for_each_safe(pos, temp, &msg->chunks) { list_del_init(pos); chunk = list_entry(pos, struct sctp_chunk, frag_list); if (!msg->send_failed) { sctp_chunk_put(chunk); continue; } asoc = chunk->asoc; error = msg->send_error ?: asoc->outqueue.error; sent = chunk->has_tsn ? SCTP_DATA_SENT : SCTP_DATA_UNSENT; if (sctp_ulpevent_type_enabled(asoc->subscribe, SCTP_SEND_FAILED)) { ev = sctp_ulpevent_make_send_failed(asoc, chunk, sent, error, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } if (sctp_ulpevent_type_enabled(asoc->subscribe, SCTP_SEND_FAILED_EVENT)) { ev = sctp_ulpevent_make_send_failed_event(asoc, chunk, sent, error, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } sctp_chunk_put(chunk); } SCTP_DBG_OBJCNT_DEC(datamsg); kfree(msg); } /* Hold a reference. */ static void sctp_datamsg_hold(struct sctp_datamsg *msg) { refcount_inc(&msg->refcnt); } /* Release a reference. */ void sctp_datamsg_put(struct sctp_datamsg *msg) { if (refcount_dec_and_test(&msg->refcnt)) sctp_datamsg_destroy(msg); } /* Assign a chunk to this datamsg. */ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chunk) { sctp_datamsg_hold(msg); chunk->msg = msg; } /* A data chunk can have a maximum payload of (2^16 - 20). Break * down any such message into smaller chunks. Opportunistically, fragment * the chunks down to the current MTU constraints. We may get refragmented * later if the PMTU changes, but it is _much better_ to fragment immediately * with a reasonable guess than always doing our fragmentation on the * soft-interrupt. */ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct iov_iter *from) { size_t len, first_len, max_data, remaining; size_t msg_len = iov_iter_count(from); struct sctp_shared_key *shkey = NULL; struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_datamsg *msg; int err; msg = sctp_datamsg_new(GFP_KERNEL); if (!msg) return ERR_PTR(-ENOMEM); /* Note: Calculate this outside of the loop, so that all fragments * have the same expiration. */ if (asoc->peer.prsctp_capable && sinfo->sinfo_timetolive && (SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags) || !SCTP_PR_POLICY(sinfo->sinfo_flags))) msg->expires_at = jiffies + msecs_to_jiffies(sinfo->sinfo_timetolive); /* This is the biggest possible DATA chunk that can fit into * the packet */ max_data = asoc->frag_point; if (unlikely(!max_data)) { max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk), sctp_datachk_len(&asoc->stream)); pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%zu)", __func__, asoc, max_data); } /* If the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with * DATA. */ if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) { struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (hmac_desc) max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) + hmac_desc->hmac_len); if (sinfo->sinfo_tsn && sinfo->sinfo_ssn != asoc->active_key_id) { shkey = sctp_auth_get_shkey(asoc, sinfo->sinfo_ssn); if (!shkey) { err = -EINVAL; goto errout; } } else { shkey = asoc->shkey; } } /* Set first_len and then account for possible bundles on first frag */ first_len = max_data; /* Check to see if we have a pending SACK and try to let it be bundled * with this message. Do this if we don't have any data queued already. * To check that, look at out_qlen and retransmit list. * NOTE: we will not reduce to account for SACK, if the message would * not have been fragmented. */ if (timer_pending(&asoc->timers[SCTP_EVENT_TIMEOUT_SACK]) && asoc->outqueue.out_qlen == 0 && list_empty(&asoc->outqueue.retransmit) && msg_len > max_data) first_len -= SCTP_PAD4(sizeof(struct sctp_sack_chunk)); /* Encourage Cookie-ECHO bundling. */ if (asoc->state < SCTP_STATE_COOKIE_ECHOED) first_len -= SCTP_ARBITRARY_COOKIE_ECHO_LEN; /* Account for a different sized first fragment */ if (msg_len >= first_len) { msg->can_delay = 0; if (msg_len > first_len) SCTP_INC_STATS(asoc->base.net, SCTP_MIB_FRAGUSRMSGS); } else { /* Which may be the only one... */ first_len = msg_len; } /* Create chunks for all DATA chunks. */ for (remaining = msg_len; remaining; remaining -= len) { u8 frag = SCTP_DATA_MIDDLE_FRAG; if (remaining == msg_len) { /* First frag, which may also be the last */ frag |= SCTP_DATA_FIRST_FRAG; len = first_len; } else { /* Middle frags */ len = max_data; } if (len >= remaining) { /* Last frag, which may also be the first */ len = remaining; frag |= SCTP_DATA_LAST_FRAG; /* The application requests to set the I-bit of the * last DATA chunk of a user message when providing * the user message to the SCTP implementation. */ if ((sinfo->sinfo_flags & SCTP_EOF) || (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) frag |= SCTP_DATA_SACK_IMM; } chunk = asoc->stream.si->make_datafrag(asoc, sinfo, len, frag, GFP_KERNEL); if (!chunk) { err = -ENOMEM; goto errout; } err = sctp_user_addto_chunk(chunk, len, from); if (err < 0) goto errout_chunk_free; chunk->shkey = shkey; /* Put the chunk->skb back into the form expected by send. */ __skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr - chunk->skb->data); sctp_datamsg_assign(msg, chunk); list_add_tail(&chunk->frag_list, &msg->chunks); } return msg; errout_chunk_free: sctp_chunk_free(chunk); errout: list_for_each_safe(pos, temp, &msg->chunks) { list_del_init(pos); chunk = list_entry(pos, struct sctp_chunk, frag_list); sctp_chunk_free(chunk); } sctp_datamsg_put(msg); return ERR_PTR(err); } /* Check whether this message has expired. */ int sctp_chunk_abandoned(struct sctp_chunk *chunk) { if (!chunk->asoc->peer.prsctp_capable) return 0; if (chunk->msg->abandoned) return 1; if (!chunk->has_tsn && !(chunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG)) return 0; if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = SCTP_SO(&chunk->asoc->stream, chunk->sinfo.sinfo_stream); if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++; } else { chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; } chunk->msg->abandoned = 1; return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = SCTP_SO(&chunk->asoc->stream, chunk->sinfo.sinfo_stream); chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; chunk->msg->abandoned = 1; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && time_after(jiffies, chunk->msg->expires_at)) { chunk->msg->abandoned = 1; return 1; } /* PRIO policy is processed by sendmsg, not here */ return 0; } /* This chunk (and consequently entire message) has failed in its sending. */ void sctp_chunk_fail(struct sctp_chunk *chunk, int error) { chunk->msg->send_failed = 1; chunk->msg->send_error = error; } |
| 4464 2688 52 4464 2245 2694 2694 2240 2694 3993 3993 3991 1275 1275 1274 1275 1274 156 155 156 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <asm/processor.h> #include <linux/kasan.h> #include <trace/events/ipi.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); static void wake_irq_workd(void) { struct task_struct *tsk = __this_cpu_read(irq_workd); if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk) wake_up_process(tsk); } #ifdef CONFIG_SMP static void irq_work_wake(struct irq_work *entry) { wake_irq_workd(); } static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) = IRQ_WORK_INIT_HARD(irq_work_wake); #endif static int irq_workd_should_run(unsigned int cpu) { return !llist_empty(this_cpu_ptr(&lazy_list)); } /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } static __always_inline void irq_work_raise(struct irq_work *work) { if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { struct llist_head *list; bool rt_lazy_work = false; bool lazy_work = false; int work_flags; work_flags = atomic_read(&work->node.a_flags); if (work_flags & IRQ_WORK_LAZY) lazy_work = true; else if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work_flags & IRQ_WORK_HARD_IRQ)) rt_lazy_work = true; if (lazy_work || rt_lazy_work) list = this_cpu_ptr(&lazy_list); else list = this_cpu_ptr(&raised_list); if (!llist_add(&work->node.llist, list)) return; /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) irq_work_raise(work); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); /* * On PREEMPT_RT the items which are not marked as * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work * item is used on the remote CPU to wake the thread. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) goto out; work = &per_cpu(irq_work_wakeup, cpu); if (!irq_work_claim(work)) goto out; } __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } out: preempt_enable(); return true; #endif /* CONFIG_SMP */ } bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; /* * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed * in a per-CPU thread in preemptible context. Only the items which are * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context. */ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT)); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); might_sleep(); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; } while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { irq_work_run_list(this_cpu_ptr(&lazy_list)); } static void irq_workd_setup(unsigned int cpu) { sched_set_fifo_low(current); } static struct smp_hotplug_thread irqwork_threads = { .store = &irq_workd, .setup = irq_workd_setup, .thread_should_run = irq_workd_should_run, .thread_fn = run_irq_workd, .thread_comm = "irq_work/%u", }; static __init int irq_work_init_threads(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) BUG_ON(smpboot_register_percpu_thread(&irqwork_threads)); return 0; } early_initcall(irq_work_init_threads); |
| 44 44 11 2 2 20 6 9 2 18 5 7 27 23 23 23 4 21 21 2 19 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * "Ping" sockets * * Based on ipv4/ping.c code. * * Authors: Lorenzo Colitti (IPv6 support) * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6), * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32) */ #include <net/addrconf.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/protocol.h> #include <net/udp.h> #include <net/transp_v6.h> #include <linux/proc_fs.h> #include <linux/bpf-cgroup.h> #include <net/ping.h> /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { return -EAFNOSUPPORT; } static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { } static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) { return -EAFNOSUPPORT; } static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) {} static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict) { return 0; } static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from __ip6_datagram_connect() and * intended to prevent BPF program called below from accessing * bytes that are out of the bound specified by user in addr_len. */ if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); } static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct icmp6hdr user_icmph; int addr_type; struct in6_addr *daddr; int oif = 0; struct flowi6 fl6; int err; struct dst_entry *dst; struct rt6_info *rt; struct pingfakehdr pfh; struct ipcm6_cookie ipc6; err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, sizeof(user_icmph)); if (err) return err; memset(&fl6, 0, sizeof(fl6)); if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); if (msg->msg_namelen < sizeof(*u)) return -EINVAL; if (u->sin6_family != AF_INET6) { return -EAFNOSUPPORT; } daddr = &(u->sin6_addr); if (inet6_test_bit(SNDFLOW, sk)) fl6.flowlabel = u->sin6_flowinfo & IPV6_FLOWINFO_MASK; if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (!oif) oif = sk->sk_bound_dev_if; if (!oif) oif = np->sticky_pktinfo.ipi6_ifindex; if (!oif && ipv6_addr_is_multicast(daddr)) oif = READ_ONCE(np->mcast_oif); else if (!oif) oif = READ_ONCE(np->ucast_oif); addr_type = ipv6_addr_type(daddr); if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || (addr_type & IPV6_ADDR_MAPPED) || (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if && l3mdev_master_ifindex_by_index(sock_net(sk), oif) != sk->sk_bound_dev_if)) return -EINVAL; ipcm6_init_sk(&ipc6, sk); fl6.flowi6_oif = oif; if (msg->msg_controllen) { struct ipv6_txoptions opt = {}; opt.tot_len = sizeof(opt); ipc6.opt = &opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) return err; /* Changes to txoptions and flow info are not implemented, yet. * Drop the options. */ ipc6.opt = NULL; } fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; fl6.flowi6_mark = ipc6.sockc.mark; fl6.flowi6_uid = sk->sk_uid; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); if (IS_ERR(dst)) return PTR_ERR(dst); rt = dst_rt6_info(dst); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); pfh.icmph.type = user_icmph.icmp6_type; pfh.icmph.code = user_icmph.icmp6_code; pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; pfh.msg = msg; pfh.wcheck = 0; pfh.family = AF_INET6; if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); lock_sock(sk); err = ip6_append_data(sk, ping_getfrag, &pfh, len, sizeof(struct icmp6hdr), &ipc6, &fl6, rt, MSG_DONTWAIT); if (err) { ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, (struct icmp6hdr *)&pfh.icmph, len); } release_sock(sk); dst_release(dst); if (err) return err; return len; } struct proto pingv6_prot = { .name = "PINGv6", .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, .pre_connect = ping_v6_pre_connect, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .sendmsg = ping_v6_sendmsg, .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, .put_port = ping_unhash, .obj_size = sizeof(struct raw6_sock), .ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6), }; EXPORT_SYMBOL_GPL(pingv6_prot); static struct inet_protosw pingv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; #ifdef CONFIG_PROC_FS static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) { return ping_seq_start(seq, pos, AF_INET6); } static int ping_v6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { int bucket = ((struct ping_iter_state *) seq->private)->bucket; struct inet_sock *inet = inet_sk((struct sock *)v); __u16 srcp = ntohs(inet->inet_sport); __u16 destp = ntohs(inet->inet_dport); ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); } return 0; } static const struct seq_operations ping_v6_seq_ops = { .start = ping_v6_seq_start, .show = ping_v6_seq_show, .next = ping_seq_next, .stop = ping_seq_stop, }; static int __net_init ping_v6_proc_init_net(struct net *net) { if (!proc_create_net("icmp6", 0444, net->proc_net, &ping_v6_seq_ops, sizeof(struct ping_iter_state))) return -ENOMEM; return 0; } static void __net_exit ping_v6_proc_exit_net(struct net *net) { remove_proc_entry("icmp6", net->proc_net); } static struct pernet_operations ping_v6_net_ops = { .init = ping_v6_proc_init_net, .exit = ping_v6_proc_exit_net, }; #endif int __init pingv6_init(void) { #ifdef CONFIG_PROC_FS int ret = register_pernet_subsys(&ping_v6_net_ops); if (ret) return ret; #endif pingv6_ops.ipv6_recv_error = ipv6_recv_error; pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl; pingv6_ops.ip6_datagram_recv_specific_ctl = ip6_datagram_recv_specific_ctl; pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; return inet6_register_protosw(&pingv6_protosw); } /* This never gets called because it's not possible to unload the ipv6 module, * but just in case. */ void pingv6_exit(void) { pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; #ifdef CONFIG_PROC_FS unregister_pernet_subsys(&ping_v6_net_ops); #endif inet6_unregister_protosw(&pingv6_protosw); } |
| 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC virtual connection handler, common bits. * * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/skbuff.h> #include "ar-internal.h" /* * Time till a connection expires after last use (in seconds). */ unsigned int __read_mostly rxrpc_connection_expiry = 10 * 60; unsigned int __read_mostly rxrpc_closed_conn_expiry = 10; static void rxrpc_clean_up_connection(struct work_struct *work); static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, unsigned long reap_at); void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { struct rxrpc_local *local = conn->local; bool busy; if (WARN_ON_ONCE(!local)) return; spin_lock_irq(&local->lock); busy = !list_empty(&conn->attend_link); if (!busy) { rxrpc_get_connection(conn, why); list_add_tail(&conn->attend_link, &local->conn_attend_q); } spin_unlock_irq(&local->lock); rxrpc_wake_up_io_thread(local); } static void rxrpc_connection_timer(struct timer_list *timer) { struct rxrpc_connection *conn = container_of(timer, struct rxrpc_connection, timer); rxrpc_poke_conn(conn, rxrpc_conn_get_poke_timer); } /* * allocate a new connection */ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, gfp_t gfp) { struct rxrpc_connection *conn; _enter(""); conn = kzalloc(sizeof(struct rxrpc_connection), gfp); if (conn) { INIT_LIST_HEAD(&conn->cache_link); timer_setup(&conn->timer, &rxrpc_connection_timer, 0); INIT_WORK(&conn->processor, rxrpc_process_connection); INIT_WORK(&conn->destructor, rxrpc_clean_up_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); INIT_LIST_HEAD(&conn->attend_link); mutex_init(&conn->security_lock); mutex_init(&conn->tx_data_alloc_lock); skb_queue_head_init(&conn->rx_queue); conn->rxnet = rxnet; conn->security = &rxrpc_no_security; spin_lock_init(&conn->state_lock); conn->debug_id = atomic_inc_return(&rxrpc_debug_id); conn->idle_timestamp = jiffies; } _leave(" = %p{%d}", conn, conn ? conn->debug_id : 0); return conn; } /* * Look up a connection in the cache by protocol parameters. * * If successful, a pointer to the connection is returned, but no ref is taken. * NULL is returned if there is no match. * * When searching for a service call, if we find a peer but no connection, we * return that through *_peer in case we need to create a new service call. * * The caller must be holding the RCU read lock. */ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, struct sk_buff *skb) { struct rxrpc_connection *conn; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); /* Look up client connections by connection ID alone as their * IDs are unique for this machine. */ conn = idr_find(&local->conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); if (!conn || refcount_read(&conn->ref) == 0) { _debug("no conn"); goto not_found; } if (conn->proto.epoch != sp->hdr.epoch || conn->local != local) goto not_found; peer = conn->peer; switch (srx->transport.family) { case AF_INET: if (peer->srx.transport.sin.sin_port != srx->transport.sin.sin_port) goto not_found; break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: if (peer->srx.transport.sin6.sin6_port != srx->transport.sin6.sin6_port) goto not_found; break; #endif default: BUG(); } _leave(" = %p", conn); return conn; not_found: _leave(" = NULL"); return NULL; } /* * Disconnect a call and clear any channel it occupies when that call * terminates. The caller must hold the channel_lock and must release the * call's ref on the connection. */ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, struct rxrpc_call *call) { struct rxrpc_channel *chan = &conn->channels[call->cid & RXRPC_CHANNELMASK]; _enter("%d,%x", conn->debug_id, call->cid); if (chan->call == call) { /* Save the result of the call so that we can repeat it if necessary * through the channel, whilst disposing of the actual call record. */ trace_rxrpc_disconnect_call(call); switch (call->completion) { case RXRPC_CALL_SUCCEEDED: chan->last_seq = call->rx_highest_seq; chan->last_type = RXRPC_PACKET_TYPE_ACK; break; case RXRPC_CALL_LOCALLY_ABORTED: chan->last_abort = call->abort_code; chan->last_type = RXRPC_PACKET_TYPE_ABORT; break; default: chan->last_abort = RX_CALL_DEAD; chan->last_type = RXRPC_PACKET_TYPE_ABORT; break; } chan->last_call = chan->call_id; chan->call_id = chan->call_counter; chan->call = NULL; } _leave(""); } /* * Disconnect a call and clear any channel it occupies when that call * terminates. */ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); rxrpc_see_call(call, rxrpc_call_see_disconnected); call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { spin_lock_irq(&call->peer->lock); hlist_del_init(&call->error_link); spin_unlock_irq(&call->peer->lock); } if (rxrpc_is_client_call(call)) { rxrpc_disconnect_client_call(call->bundle, call); } else { __rxrpc_disconnect_call(conn, call); conn->idle_timestamp = jiffies; if (atomic_dec_and_test(&conn->active)) rxrpc_set_service_reap_timer(conn->rxnet, jiffies + rxrpc_connection_expiry * HZ); } rxrpc_put_call(call, rxrpc_call_put_io_thread); } /* * Queue a connection's work processor, getting a ref to pass to the work * queue. */ void rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { if (atomic_read(&conn->active) >= 0 && rxrpc_queue_work(&conn->processor)) rxrpc_see_connection(conn, why); } /* * Note the re-emergence of a connection. */ void rxrpc_see_connection(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { if (conn) { int r = refcount_read(&conn->ref); trace_rxrpc_conn(conn->debug_id, r, why); } } /* * Get a ref on a connection. */ struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { int r; __refcount_inc(&conn->ref, &r); trace_rxrpc_conn(conn->debug_id, r + 1, why); return conn; } /* * Try to get a ref on a connection. */ struct rxrpc_connection * rxrpc_get_connection_maybe(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { int r; if (conn) { if (__refcount_inc_not_zero(&conn->ref, &r)) trace_rxrpc_conn(conn->debug_id, r + 1, why); else conn = NULL; } return conn; } /* * Set the service connection reap timer. */ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, unsigned long reap_at) { if (rxnet->live) timer_reduce(&rxnet->service_conn_reap_timer, reap_at); } /* * destroy a virtual connection */ static void rxrpc_rcu_free_connection(struct rcu_head *rcu) { struct rxrpc_connection *conn = container_of(rcu, struct rxrpc_connection, rcu); struct rxrpc_net *rxnet = conn->rxnet; _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), rxrpc_conn_free); kfree(conn); if (atomic_dec_and_test(&rxnet->nr_conns)) wake_up_var(&rxnet->nr_conns); } /* * Clean up a dead connection. */ static void rxrpc_clean_up_connection(struct work_struct *work) { struct rxrpc_connection *conn = container_of(work, struct rxrpc_connection, destructor); struct rxrpc_net *rxnet = conn->rxnet; ASSERT(!conn->channels[0].call && !conn->channels[1].call && !conn->channels[2].call && !conn->channels[3].call); ASSERT(list_empty(&conn->cache_link)); timer_delete_sync(&conn->timer); cancel_work_sync(&conn->processor); /* Processing may restart the timer */ timer_delete_sync(&conn->timer); write_lock(&rxnet->conn_lock); list_del_init(&conn->proc_link); write_unlock(&rxnet->conn_lock); if (conn->pmtud_probe) { trace_rxrpc_pmtud_lost(conn, 0); conn->peer->pmtud_probing = false; conn->peer->pmtud_pending = true; } rxrpc_purge_queue(&conn->rx_queue); rxrpc_kill_client_conn(conn); conn->security->clear(conn); key_put(conn->key); rxrpc_put_bundle(conn->bundle, rxrpc_bundle_put_conn); rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); rxrpc_put_local(conn->local, rxrpc_local_put_kill_conn); /* Drain the Rx queue. Note that even though we've unpublished, an * incoming packet could still be being added to our Rx queue, so we * will need to drain it again in the RCU cleanup handler. */ rxrpc_purge_queue(&conn->rx_queue); page_frag_cache_drain(&conn->tx_data_alloc); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } /* * Drop a ref on a connection. */ void rxrpc_put_connection(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { unsigned int debug_id; bool dead; int r; if (!conn) return; debug_id = conn->debug_id; dead = __refcount_dec_and_test(&conn->ref, &r); trace_rxrpc_conn(debug_id, r - 1, why); if (dead) { timer_delete(&conn->timer); cancel_work(&conn->processor); if (in_softirq() || work_busy(&conn->processor) || timer_pending(&conn->timer)) /* Can't use the rxrpc workqueue as we need to cancel/flush * something that may be running/waiting there. */ schedule_work(&conn->destructor); else rxrpc_clean_up_connection(&conn->destructor); } } /* * reap dead service connections */ void rxrpc_service_connection_reaper(struct work_struct *work) { struct rxrpc_connection *conn, *_p; struct rxrpc_net *rxnet = container_of(work, struct rxrpc_net, service_conn_reaper); unsigned long expire_at, earliest, idle_timestamp, now; int active; LIST_HEAD(graveyard); _enter(""); now = jiffies; earliest = now + MAX_JIFFY_OFFSET; write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { ASSERTCMP(atomic_read(&conn->active), >=, 0); if (likely(atomic_read(&conn->active) > 0)) continue; if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; if (rxnet->live && !conn->local->dead) { idle_timestamp = READ_ONCE(conn->idle_timestamp); expire_at = idle_timestamp + rxrpc_connection_expiry * HZ; if (conn->local->service_closed) expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ; _debug("reap CONN %d { a=%d,t=%ld }", conn->debug_id, atomic_read(&conn->active), (long)expire_at - (long)now); if (time_before(now, expire_at)) { if (time_before(expire_at, earliest)) earliest = expire_at; continue; } } /* The activity count sits at 0 whilst the conn is unused on * the list; we reduce that to -1 to make the conn unavailable. */ active = 0; if (!atomic_try_cmpxchg(&conn->active, &active, -1)) continue; rxrpc_see_connection(conn, rxrpc_conn_see_reap_service); if (rxrpc_conn_is_client(conn)) BUG(); else rxrpc_unpublish_service_conn(conn); list_move_tail(&conn->link, &graveyard); } write_unlock(&rxnet->conn_lock); if (earliest != now + MAX_JIFFY_OFFSET) { _debug("reschedule reaper %ld", (long)earliest - (long)now); ASSERT(time_after(earliest, now)); rxrpc_set_service_reap_timer(rxnet, earliest); } while (!list_empty(&graveyard)) { conn = list_entry(graveyard.next, struct rxrpc_connection, link); list_del_init(&conn->link); ASSERTCMP(atomic_read(&conn->active), ==, -1); rxrpc_put_connection(conn, rxrpc_conn_put_service_reaped); } _leave(""); } /* * preemptively destroy all the service connection records rather than * waiting for them to time out */ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) { struct rxrpc_connection *conn, *_p; bool leak = false; _enter(""); atomic_dec(&rxnet->nr_conns); timer_delete_sync(&rxnet->service_conn_reap_timer); rxrpc_queue_work(&rxnet->service_conn_reaper); flush_workqueue(rxrpc_workqueue); write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { pr_err("AF_RXRPC: Leaked conn %p {%d}\n", conn, refcount_read(&conn->ref)); leak = true; } write_unlock(&rxnet->conn_lock); BUG_ON(leak); ASSERT(list_empty(&rxnet->conn_proc_list)); /* We need to wait for the connections to be destroyed by RCU as they * pin things that we still need to get rid of. */ wait_var_event(&rxnet->nr_conns, !atomic_read(&rxnet->nr_conns)); _leave(""); } |
| 74 286 2862 288 237 237 16048 94 11234 2769 2718 15214 120 15207 2786 15018 9323 14076 14065 5326 5326 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Variant of atomic_t specialized for reference counts. * * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * * Saturation semantics * ==================== * * refcount_t differs from atomic_t in that the counter saturates at * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the * counter and causing 'spurious' use-after-free issues. In order to avoid the * cost associated with introducing cmpxchg() loops into all of the saturating * operations, we temporarily allow the counter to take on an unchecked value * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow * or overflow has occurred. Although this is racy when multiple threads * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly * equidistant from 0 and INT_MAX we minimise the scope for error: * * INT_MAX REFCOUNT_SATURATED UINT_MAX * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) * +--------------------------------+----------------+----------------+ * <---------- bad value! ----------> * * (in a signed view of the world, the "bad value" range corresponds to * a negative counter value). * * As an example, consider a refcount_inc() operation that causes the counter * to overflow: * * int old = atomic_fetch_add_relaxed(r); * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) * if (old < 0) * atomic_set(r, REFCOUNT_SATURATED); * * If another thread also performs a refcount_inc() operation between the two * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the * underlying object. * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). * With the current PID limit, if no batched refcounting operations are used and * the attacker can't repeatedly trigger kernel oopses in the middle of refcount * operations, this makes it impossible for a saturated refcount to leave the * saturation range, even if it is possible for multiple uses of the same * refcount to nest in the context of a single task: * * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = * 0x40000000 / 0x400000 = 0x100 = 256 * * If hundreds of references are added/removed with a single refcounting * operation, it may potentially be possible to leave the saturation range; but * given the precise timing details involved with the round-robin scheduling of * each thread manipulating the refcount and the need to hit the race multiple * times in succession, there doesn't appear to be a practical avenue of attack * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object we're increasing the * reference count on will provide the ordering. For locked data structures, * its the lock acquire, for RCU/lockless data structures its the dependent * load. * * Do note that inc_not_zero() provides a control dependency which will order * future stores against the inc, this ensures we'll never modify the object * if we did not in fact acquire a reference. * * The decrements will provide release order, such that all the prior loads and * stores will be issued before, it also provides a control dependency, which * will order us against the subsequent free(). * * The control dependency is against the load of the cmpxchg (ll/sc) that * succeeded. This means the stores aren't fully ordered, but this is fine * because the 1->0 transition indicates no concurrency. * * Note that the allocator is responsible for ordering things between free() * and alloc(). * * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() provide * acquire and release ordering for cases when the memory occupied by the * object might be reused to store another object. This is important for the * cases where secondary validation is required to detect such reuse, e.g. * SLAB_TYPESAFE_BY_RCU. The secondary validation checks have to happen after * the refcount is taken, hence acquire order is necessary. Similarly, when the * object is initialized, all stores to its attributes should be visible before * the refcount is set, otherwise a stale attribute value might be used by * another task which succeeds in taking a refcount to the new object. */ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> #include <linux/refcount_types.h> #include <linux/spinlock_types.h> struct mutex; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, REFCOUNT_ADD_OVF, REFCOUNT_ADD_UAF, REFCOUNT_SUB_UAF, REFCOUNT_DEC_LEAK, }; void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } /** * refcount_set_release - set a refcount's value with release ordering * @r: the refcount * @n: value to which the refcount will be set * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides release memory ordering which will order previous memory operations * against this store. This ensures all updates to this object are visible * once the refcount is set and stale values from the object previously * occupying this memory are overwritten with new ones. * * This function should be called only after new object is fully initialized. * After this call the object should be considered visible to other tasks even * if it was not yet added into an object collection normally used to discover * it. This is because other tasks might have discovered the object previously * occupying the same memory and after memory reuse they can succeed in taking * refcount to the new object and start using it. */ static inline void refcount_set_release(refcount_t *r, int n) { atomic_set_release(&r->refs, n); } /** * refcount_read - get a refcount's value * @r: the refcount * * Return: the refcount's value */ static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); } static inline __must_check __signed_wrap bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); do { if (!old) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return __refcount_add_not_zero(i, r, NULL); } static inline __must_check __signed_wrap bool __refcount_add_not_zero_limited_acquire(int i, refcount_t *r, int *oldp, int limit) { int old = refcount_read(r); do { if (!old) break; if (i > limit - old) { if (oldp) *oldp = old; return false; } } while (!atomic_try_cmpxchg_acquire(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } static inline __must_check bool __refcount_inc_not_zero_limited_acquire(refcount_t *r, int *oldp, int limit) { return __refcount_add_not_zero_limited_acquire(1, r, oldp, limit); } static inline __must_check __signed_wrap bool __refcount_add_not_zero_acquire(int i, refcount_t *r, int *oldp) { return __refcount_add_not_zero_limited_acquire(i, r, oldp, INT_MAX); } /** * refcount_add_not_zero_acquire - add a value to a refcount with acquire ordering unless it is 0 * * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides acquire memory ordering on success, it is assumed the caller has * guaranteed the object memory to be stable (RCU, etc.). It does provide a * control dependency and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc_not_zero_acquire() should instead be used to increment a * reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero_acquire(int i, refcount_t *r) { return __refcount_add_not_zero_acquire(i, r, NULL); } static inline __signed_wrap void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); if (oldp) *oldp = old; if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) { return __refcount_add_not_zero(1, r, oldp); } /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { return __refcount_inc_not_zero(r, NULL); } static inline __must_check bool __refcount_inc_not_zero_acquire(refcount_t *r, int *oldp) { return __refcount_add_not_zero_acquire(1, r, oldp); } /** * refcount_inc_not_zero_acquire - increment a refcount with acquire ordering unless it is 0 * @r: the refcount to increment * * Similar to refcount_inc_not_zero(), but provides acquire memory ordering on * success. * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides acquire memory ordering on success, it is assumed the caller has * guaranteed the object memory to be stable (RCU, etc.). It does provide a * control dependency and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero_acquire(refcount_t *r) { return __refcount_inc_not_zero_acquire(r, NULL); } static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); } /** * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. * * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ static inline void refcount_inc(refcount_t *r) { __refcount_inc(r, NULL); } static inline __must_check __signed_wrap bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); if (oldp) *oldp = old; if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } /** * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_dec(), or one of its variants, should instead be used to * decrement a reference count. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return __refcount_sub_and_test(i, r, NULL); } static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { return __refcount_sub_and_test(1, r, oldp); } /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); if (oldp) *oldp = old; if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } /** * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); } extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) __cond_acquires(lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) __cond_acquires(lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags) __cond_acquires(lock); #endif /* _LINUX_REFCOUNT_H */ |
| 139 139 125 139 139 139 7352 7359 4511 4159 4160 5649 5649 4250 1861 474 1522 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 | // SPDX-License-Identifier: GPL-2.0-or-later #define pr_fmt(fmt) "ref_tracker: " fmt #include <linux/export.h> #include <linux/list_sort.h> #include <linux/ref_tracker.h> #include <linux/slab.h> #include <linux/stacktrace.h> #include <linux/stackdepot.h> #define REF_TRACKER_STACK_ENTRIES 16 #define STACK_BUF_SIZE 1024 struct ref_tracker { struct list_head head; /* anchor into dir->list or dir->quarantine */ bool dead; depot_stack_handle_t alloc_stack_handle; depot_stack_handle_t free_stack_handle; }; struct ref_tracker_dir_stats { int total; int count; struct { depot_stack_handle_t stack_handle; unsigned int count; } stacks[]; }; static struct ref_tracker_dir_stats * ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit) { struct ref_tracker_dir_stats *stats; struct ref_tracker *tracker; stats = kmalloc(struct_size(stats, stacks, limit), GFP_NOWAIT | __GFP_NOWARN); if (!stats) return ERR_PTR(-ENOMEM); stats->total = 0; stats->count = 0; list_for_each_entry(tracker, &dir->list, head) { depot_stack_handle_t stack = tracker->alloc_stack_handle; int i; ++stats->total; for (i = 0; i < stats->count; ++i) if (stats->stacks[i].stack_handle == stack) break; if (i >= limit) continue; if (i >= stats->count) { stats->stacks[i].stack_handle = stack; stats->stacks[i].count = 0; ++stats->count; } ++stats->stacks[i].count; } return stats; } struct ostream { char *buf; int size, used; }; #define pr_ostream(stream, fmt, args...) \ ({ \ struct ostream *_s = (stream); \ \ if (!_s->buf) { \ pr_err(fmt, ##args); \ } else { \ int ret, len = _s->size - _s->used; \ ret = snprintf(_s->buf + _s->used, len, pr_fmt(fmt), ##args); \ _s->used += min(ret, len); \ } \ }) static void __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir, unsigned int display_limit, struct ostream *s) { struct ref_tracker_dir_stats *stats; unsigned int i = 0, skipped; depot_stack_handle_t stack; char *sbuf; lockdep_assert_held(&dir->lock); if (list_empty(&dir->list)) return; stats = ref_tracker_get_stats(dir, display_limit); if (IS_ERR(stats)) { pr_ostream(s, "%s@%pK: couldn't get stats, error %pe\n", dir->name, dir, stats); return; } sbuf = kmalloc(STACK_BUF_SIZE, GFP_NOWAIT | __GFP_NOWARN); for (i = 0, skipped = stats->total; i < stats->count; ++i) { stack = stats->stacks[i].stack_handle; if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4)) sbuf[0] = 0; pr_ostream(s, "%s@%pK has %d/%d users at\n%s\n", dir->name, dir, stats->stacks[i].count, stats->total, sbuf); skipped -= stats->stacks[i].count; } if (skipped) pr_ostream(s, "%s@%pK skipped reports about %d/%d users.\n", dir->name, dir, skipped, stats->total); kfree(sbuf); kfree(stats); } void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir, unsigned int display_limit) { struct ostream os = {}; __ref_tracker_dir_pr_ostream(dir, display_limit, &os); } EXPORT_SYMBOL(ref_tracker_dir_print_locked); void ref_tracker_dir_print(struct ref_tracker_dir *dir, unsigned int display_limit) { unsigned long flags; spin_lock_irqsave(&dir->lock, flags); ref_tracker_dir_print_locked(dir, display_limit); spin_unlock_irqrestore(&dir->lock, flags); } EXPORT_SYMBOL(ref_tracker_dir_print); int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size) { struct ostream os = { .buf = buf, .size = size }; unsigned long flags; spin_lock_irqsave(&dir->lock, flags); __ref_tracker_dir_pr_ostream(dir, 16, &os); spin_unlock_irqrestore(&dir->lock, flags); return os.used; } EXPORT_SYMBOL(ref_tracker_dir_snprint); void ref_tracker_dir_exit(struct ref_tracker_dir *dir) { struct ref_tracker *tracker, *n; unsigned long flags; bool leak = false; dir->dead = true; spin_lock_irqsave(&dir->lock, flags); list_for_each_entry_safe(tracker, n, &dir->quarantine, head) { list_del(&tracker->head); kfree(tracker); dir->quarantine_avail++; } if (!list_empty(&dir->list)) { ref_tracker_dir_print_locked(dir, 16); leak = true; list_for_each_entry_safe(tracker, n, &dir->list, head) { list_del(&tracker->head); kfree(tracker); } } spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(leak); WARN_ON_ONCE(refcount_read(&dir->untracked) != 1); WARN_ON_ONCE(refcount_read(&dir->no_tracker) != 1); } EXPORT_SYMBOL(ref_tracker_dir_exit); int ref_tracker_alloc(struct ref_tracker_dir *dir, struct ref_tracker **trackerp, gfp_t gfp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; struct ref_tracker *tracker; unsigned int nr_entries; gfp_t gfp_mask = gfp | __GFP_NOWARN; unsigned long flags; WARN_ON_ONCE(dir->dead); if (!trackerp) { refcount_inc(&dir->no_tracker); return 0; } if (gfp & __GFP_DIRECT_RECLAIM) gfp_mask |= __GFP_NOFAIL; *trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask); if (unlikely(!tracker)) { pr_err_once("memory allocation failure, unreliable refcount tracker.\n"); refcount_inc(&dir->untracked); return -ENOMEM; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); spin_lock_irqsave(&dir->lock, flags); list_add(&tracker->head, &dir->list); spin_unlock_irqrestore(&dir->lock, flags); return 0; } EXPORT_SYMBOL_GPL(ref_tracker_alloc); int ref_tracker_free(struct ref_tracker_dir *dir, struct ref_tracker **trackerp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; depot_stack_handle_t stack_handle; struct ref_tracker *tracker; unsigned int nr_entries; unsigned long flags; WARN_ON_ONCE(dir->dead); if (!trackerp) { refcount_dec(&dir->no_tracker); return 0; } tracker = *trackerp; if (!tracker) { refcount_dec(&dir->untracked); return -EEXIST; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); stack_handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT | __GFP_NOWARN); spin_lock_irqsave(&dir->lock, flags); if (tracker->dead) { pr_err("reference already released.\n"); if (tracker->alloc_stack_handle) { pr_err("allocated in:\n"); stack_depot_print(tracker->alloc_stack_handle); } if (tracker->free_stack_handle) { pr_err("freed in:\n"); stack_depot_print(tracker->free_stack_handle); } spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(1); return -EINVAL; } tracker->dead = true; tracker->free_stack_handle = stack_handle; list_move_tail(&tracker->head, &dir->quarantine); if (!dir->quarantine_avail) { tracker = list_first_entry(&dir->quarantine, struct ref_tracker, head); list_del(&tracker->head); } else { dir->quarantine_avail--; tracker = NULL; } spin_unlock_irqrestore(&dir->lock, flags); kfree(tracker); return 0; } EXPORT_SYMBOL_GPL(ref_tracker_free); |
| 4 111 47 715 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Integer base 2 logarithm calculation * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_LOG2_H #define _LINUX_LOG2_H #include <linux/types.h> #include <linux/bitops.h> /* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() * - the arch is not required to handle n==0 if implementing the fallback */ #ifndef CONFIG_ARCH_HAS_ILOG2_U32 static __always_inline __attribute__((const)) int __ilog2_u32(u32 n) { return fls(n) - 1; } #endif #ifndef CONFIG_ARCH_HAS_ILOG2_U64 static __always_inline __attribute__((const)) int __ilog2_u64(u64 n) { return fls64(n) - 1; } #endif /** * is_power_of_2() - check if a value is a power of two * @n: the value to check * * Determine whether some value is a power of two, where zero is * *not* considered a power of two. * Return: true if @n is a power of 2, otherwise false. */ static __always_inline __attribute__((const)) bool is_power_of_2(unsigned long n) { return (n != 0 && ((n & (n - 1)) == 0)); } /** * __roundup_pow_of_two() - round up to nearest power of two * @n: value to round up */ static inline __attribute__((const)) unsigned long __roundup_pow_of_two(unsigned long n) { return 1UL << fls_long(n - 1); } /** * __rounddown_pow_of_two() - round down to nearest power of two * @n: value to round down */ static inline __attribute__((const)) unsigned long __rounddown_pow_of_two(unsigned long n) { return 1UL << (fls_long(n) - 1); } /** * const_ilog2 - log base 2 of 32-bit or a 64-bit constant unsigned value * @n: parameter * * Use this where sparse expects a true constant expression, e.g. for array * indices. */ #define const_ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ (n) & (1ULL << 60) ? 60 : \ (n) & (1ULL << 59) ? 59 : \ (n) & (1ULL << 58) ? 58 : \ (n) & (1ULL << 57) ? 57 : \ (n) & (1ULL << 56) ? 56 : \ (n) & (1ULL << 55) ? 55 : \ (n) & (1ULL << 54) ? 54 : \ (n) & (1ULL << 53) ? 53 : \ (n) & (1ULL << 52) ? 52 : \ (n) & (1ULL << 51) ? 51 : \ (n) & (1ULL << 50) ? 50 : \ (n) & (1ULL << 49) ? 49 : \ (n) & (1ULL << 48) ? 48 : \ (n) & (1ULL << 47) ? 47 : \ (n) & (1ULL << 46) ? 46 : \ (n) & (1ULL << 45) ? 45 : \ (n) & (1ULL << 44) ? 44 : \ (n) & (1ULL << 43) ? 43 : \ (n) & (1ULL << 42) ? 42 : \ (n) & (1ULL << 41) ? 41 : \ (n) & (1ULL << 40) ? 40 : \ (n) & (1ULL << 39) ? 39 : \ (n) & (1ULL << 38) ? 38 : \ (n) & (1ULL << 37) ? 37 : \ (n) & (1ULL << 36) ? 36 : \ (n) & (1ULL << 35) ? 35 : \ (n) & (1ULL << 34) ? 34 : \ (n) & (1ULL << 33) ? 33 : \ (n) & (1ULL << 32) ? 32 : \ (n) & (1ULL << 31) ? 31 : \ (n) & (1ULL << 30) ? 30 : \ (n) & (1ULL << 29) ? 29 : \ (n) & (1ULL << 28) ? 28 : \ (n) & (1ULL << 27) ? 27 : \ (n) & (1ULL << 26) ? 26 : \ (n) & (1ULL << 25) ? 25 : \ (n) & (1ULL << 24) ? 24 : \ (n) & (1ULL << 23) ? 23 : \ (n) & (1ULL << 22) ? 22 : \ (n) & (1ULL << 21) ? 21 : \ (n) & (1ULL << 20) ? 20 : \ (n) & (1ULL << 19) ? 19 : \ (n) & (1ULL << 18) ? 18 : \ (n) & (1ULL << 17) ? 17 : \ (n) & (1ULL << 16) ? 16 : \ (n) & (1ULL << 15) ? 15 : \ (n) & (1ULL << 14) ? 14 : \ (n) & (1ULL << 13) ? 13 : \ (n) & (1ULL << 12) ? 12 : \ (n) & (1ULL << 11) ? 11 : \ (n) & (1ULL << 10) ? 10 : \ (n) & (1ULL << 9) ? 9 : \ (n) & (1ULL << 8) ? 8 : \ (n) & (1ULL << 7) ? 7 : \ (n) & (1ULL << 6) ? 6 : \ (n) & (1ULL << 5) ? 5 : \ (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ 1) : \ -1) /** * ilog2 - log base 2 of 32-bit or a 64-bit unsigned value * @n: parameter * * constant-capable log of base 2 calculation * - this can be used to initialise global variables from constant data, hence * the massive ternary operator construction * * selects the appropriately-sized optimised version depending on sizeof(n) */ #define ilog2(n) \ ( \ __builtin_constant_p(n) ? \ ((n) < 2 ? 0 : \ 63 - __builtin_clzll(n)) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ ) /** * roundup_pow_of_two - round the given value up to nearest power of two * @n: parameter * * round the given value up to the nearest power of two * - the result is undefined when n == 0 * - this can be used to initialise global variables from constant data */ #define roundup_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 1) ? 1 : \ (1UL << (ilog2((n) - 1) + 1)) \ ) : \ __roundup_pow_of_two(n) \ ) /** * rounddown_pow_of_two - round the given value down to nearest power of two * @n: parameter * * round the given value down to the nearest power of two * - the result is undefined when n == 0 * - this can be used to initialise global variables from constant data */ #define rounddown_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ (1UL << ilog2(n))) : \ __rounddown_pow_of_two(n) \ ) static inline __attribute_const__ int __order_base_2(unsigned long n) { return n > 1 ? ilog2(n - 1) + 1 : 0; } /** * order_base_2 - calculate the (rounded up) base 2 order of the argument * @n: parameter * * The first few values calculated by this routine: * ob2(0) = 0 * ob2(1) = 0 * ob2(2) = 1 * ob2(3) = 2 * ob2(4) = 2 * ob2(5) = 3 * ... and so on. */ #define order_base_2(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 0 || (n) == 1) ? 0 : \ ilog2((n) - 1) + 1) : \ __order_base_2(n) \ ) static inline __attribute__((const)) int __bits_per(unsigned long n) { if (n < 2) return 1; if (is_power_of_2(n)) return order_base_2(n) + 1; return order_base_2(n); } /** * bits_per - calculate the number of bits required for the argument * @n: parameter * * This is constant-capable and can be used for compile time * initializations, e.g bitfields. * * The first few values calculated by this routine: * bf(0) = 1 * bf(1) = 1 * bf(2) = 2 * bf(3) = 2 * bf(4) = 3 * ... and so on. */ #define bits_per(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 0 || (n) == 1) \ ? 1 : ilog2(n) + 1 \ ) : \ __bits_per(n) \ ) #endif /* _LINUX_LOG2_H */ |
| 10294 16 16 16 16 16 16 16 16 16 16 16 16 4168 4172 4174 16 16 4179 4169 4171 4179 4174 4179 4170 4179 4173 4821 4836 513 4822 4836 121 4824 4836 4836 4836 4825 4828 16 4836 16 16 16 104 4786 2921 2923 4174 4731 4172 3584 3584 4406 4401 4405 4784 4729 4784 4783 4734 4617 4786 4792 182 593 4233 4173 593 3567 4784 4792 4792 182 182 182 183 3584 3582 3584 3521 3525 3513 593 3423 38 180 592 3566 3417 183 3584 3584 3584 3520 1053 3 3509 4184 44 75 4728 4731 3518 4186 4783 4792 3574 4185 3579 3584 4791 4787 4777 4176 4172 4174 4179 4170 513 270 4172 4179 4173 4780 4785 4781 4756 56 1 270 270 271 4175 4172 4169 2 4169 81 4167 4173 5 5 56 56 56 16 4399 4734 15 4755 430 416 14 428 16 431 30 4752 4761 4466 4415 4754 4748 4752 4782 18 4757 16 4762 4751 270 4341 3954 4104 13 34 32 34 34 34 33 34 34 34 34 34 34 34 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019 */ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/set_memory.h> #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <linux/io.h> #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/memcontrol.h> #include <linux/llist.h> #include <linux/uio.h> #include <linux/bitops.h> #include <linux/rbtree_augmented.h> #include <linux/overflow.h> #include <linux/pgtable.h> #include <linux/hugetlb.h> #include <linux/sched/mm.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> #include <linux/page_owner.h> #define CREATE_TRACE_POINTS #include <trace/events/vmalloc.h> #include "internal.h" #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { ioremap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ static const unsigned int ioremap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC static bool __ro_after_init vmap_allow_huge = true; static int __init set_nohugevmalloc(char *str) { vmap_allow_huge = false; return 0; } early_param("nohugevmalloc", set_nohugevmalloc); #else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ static const bool vmap_allow_huge = false; #endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ bool is_vmalloc_addr(const void *x) { unsigned long addr = (unsigned long)kasan_reset_tag(x); return addr >= VMALLOC_START && addr < VMALLOC_END; } EXPORT_SYMBOL(is_vmalloc_addr); struct vfree_deferred { struct llist_head list; struct work_struct wq; }; static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); /*** Page table manipulation functions ***/ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pte_t *pte; u64 pfn; struct page *page; unsigned long size = PAGE_SIZE; pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { if (unlikely(!pte_none(ptep_get(pte)))) { if (pfn_valid(pfn)) { page = pfn_to_page(pfn); dump_page(page, "remapping already mapped page"); } BUG(); } #ifdef CONFIG_HUGETLB_PAGE size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); if (size != PAGE_SIZE) { pte_t entry = pfn_pte(pfn, prot); entry = arch_make_huge_pte(entry, ilog2(size), 0); set_huge_pte_at(&init_mm, addr, pte, entry, size); pfn += PFN_DOWN(size); continue; } #endif set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte += PFN_DOWN(size), addr += size, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PMD_SHIFT) return 0; if (!arch_vmap_pmd_supported(prot)) return 0; if ((end - addr) != PMD_SIZE) return 0; if (!IS_ALIGNED(addr, PMD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PMD_SIZE)) return 0; if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) return 0; return pmd_set_huge(pmd, phys_addr, prot); } static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PMD_MODIFIED; continue; } if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PUD_SHIFT) return 0; if (!arch_vmap_pud_supported(prot)) return 0; if ((end - addr) != PUD_SIZE) return 0; if (!IS_ALIGNED(addr, PUD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PUD_SIZE)) return 0; if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) return 0; return pud_set_huge(pud, phys_addr, prot); } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PUD_MODIFIED; continue; } if (vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pud++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < P4D_SHIFT) return 0; if (!arch_vmap_p4d_supported(prot)) return 0; if ((end - addr) != P4D_SIZE) return 0; if (!IS_ALIGNED(addr, P4D_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, P4D_SIZE)) return 0; if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) return 0; return p4d_set_huge(p4d, phys_addr, prot); } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_P4D_MODIFIED; continue; } if (vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_range_noflush(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { pgd_t *pgd; unsigned long start; unsigned long next; int err; pgtbl_mod_mask mask = 0; might_sleep(); BUG_ON(addr >= end); start = addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, max_page_shift, &mask); if (err) break; } while (pgd++, phys_addr += (next - addr), addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return err; } int vmap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { int err; err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), ioremap_max_page_shift); flush_cache_vmap(addr, end); if (!err) err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, ioremap_max_page_shift); return err; } int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { struct vm_struct *area; area = find_vm_area((void *)addr); if (!area || !(area->flags & VM_IOREMAP)) { WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr); return -EINVAL; } if (addr != (unsigned long)area->addr || (void *)end != area->addr + get_vm_area_size(area)) { WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n", addr, end, (long)area->addr, (long)area->addr + get_vm_area_size(area)); return -ERANGE; } return vmap_page_range(addr, end, phys_addr, prot); } static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pte_t *pte; pte = pte_offset_kernel(pmd, addr); do { pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; } static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int cleared; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); cleared = pmd_clear_huge(pmd); if (cleared || pmd_bad(*pmd)) *mask |= PGTBL_PMD_MODIFIED; if (cleared) continue; if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); cond_resched(); } while (pmd++, addr = next, addr != end); } static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int cleared; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); cleared = pud_clear_huge(pud); if (cleared || pud_bad(*pud)) *mask |= PGTBL_PUD_MODIFIED; if (cleared) continue; if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end); } static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); p4d_clear_huge(p4d); if (p4d_bad(*p4d)) *mask |= PGTBL_P4D_MODIFIED; if (p4d_none_or_clear_bad(p4d)) continue; vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } /* * vunmap_range_noflush is similar to vunmap_range, but does not * flush caches or TLBs. * * The caller is responsible for calling flush_cache_vmap() before calling * this function, and flush_tlb_kernel_range after it has returned * successfully (and before the addresses are expected to cause a page fault * or be re-mapped for something else, if TLB flushes are being delayed or * coalesced). * * This is an internal function only. Do not use outside mm/. */ void __vunmap_range_noflush(unsigned long start, unsigned long end) { unsigned long next; pgd_t *pgd; unsigned long addr = start; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue; vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); } void vunmap_range_noflush(unsigned long start, unsigned long end) { kmsan_vunmap_range_noflush(start, end); __vunmap_range_noflush(start, end); } /** * vunmap_range - unmap kernel virtual addresses * @addr: start of the VM area to unmap * @end: end of the VM area to unmap (non-inclusive) * * Clears any present PTEs in the virtual address range, flushes TLBs and * caches. Any subsequent access to the address before it has been re-mapped * is a kernel bug. */ void vunmap_range(unsigned long addr, unsigned long end) { flush_cache_vunmap(addr, end); vunmap_range_noflush(addr, end); flush_tlb_kernel_range(addr, end); } static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pte_t *pte; /* * nr is a running index into the array which helps higher level * callers keep track of where we're up to. */ pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { struct page *page = pages[*nr]; if (WARN_ON(!pte_none(ptep_get(pte)))) return -EBUSY; if (WARN_ON(!page)) return -ENOMEM; if (WARN_ON(!pfn_valid(page_to_pfn(page)))) return -EINVAL; set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; } static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages) { unsigned long start = addr; pgd_t *pgd; unsigned long next; int err = 0; int nr = 0; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return err; } /* * vmap_pages_range_noflush is similar to vmap_pages_range, but does not * flush caches. * * The caller is responsible for calling flush_cache_vmap() after this * function returns successfully and before the addresses are accessed. * * This is an internal function only. Do not use outside mm/. */ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { unsigned int i, nr = (end - addr) >> PAGE_SHIFT; WARN_ON(page_shift < PAGE_SHIFT); if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || page_shift == PAGE_SHIFT) return vmap_small_pages_range_noflush(addr, end, prot, pages); for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) { int err; err = vmap_range_noflush(addr, addr + (1UL << page_shift), page_to_phys(pages[i]), prot, page_shift); if (err) return err; addr += 1UL << page_shift; } return 0; } int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, page_shift); if (ret) return ret; return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); } /** * vmap_pages_range - map pages to a kernel virtual address * @addr: start of the VM area to map * @end: end of the VM area to map (non-inclusive) * @prot: page protection flags to use * @pages: pages to map (always PAGE_SIZE pages) * @page_shift: maximum shift that the pages may be mapped with, @pages must * be aligned and contiguous up to at least this shift. * * RETURNS: * 0 on success, -errno on failure. */ int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { int err; err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift); flush_cache_vmap(addr, end); return err; } static int check_sparse_vm_area(struct vm_struct *area, unsigned long start, unsigned long end) { might_sleep(); if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS)) return -EINVAL; if (WARN_ON_ONCE(area->flags & VM_NO_GUARD)) return -EINVAL; if (WARN_ON_ONCE(!(area->flags & VM_SPARSE))) return -EINVAL; if ((end - start) >> PAGE_SHIFT > totalram_pages()) return -E2BIG; if (start < (unsigned long)area->addr || (void *)end > area->addr + get_vm_area_size(area)) return -ERANGE; return 0; } /** * vm_area_map_pages - map pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area * @pages: pages to map (always PAGE_SIZE pages) */ int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages) { int err; err = check_sparse_vm_area(area, start, end); if (err) return err; return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT); } /** * vm_area_unmap_pages - unmap pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area */ void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end) { if (check_sparse_vm_area(area, start, end)) return; vunmap_range(start, end); } int is_vmalloc_or_module_addr(const void *x) { /* * ARM, x86-64 and sparc64 put modules in a special place, * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ #if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)kasan_reset_tag(x); if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr); /* * Walk a vmap address to the struct page it maps. Huge vmap mappings will * return the tail page that corresponds to the base page address, which * matches small vmap mappings. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for * architectures that do not vmalloc module space */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); if (pgd_none(*pgd)) return NULL; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return NULL; /* XXX: no allowance for huge pgd */ if (WARN_ON_ONCE(pgd_bad(*pgd))) return NULL; p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; if (p4d_leaf(*p4d)) return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(p4d_bad(*p4d))) return NULL; pud = pud_offset(p4d, addr); if (pud_none(*pud)) return NULL; if (pud_leaf(*pud)) return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return NULL; if (pmd_leaf(*pmd)) return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; ptep = pte_offset_kernel(pmd, addr); pte = ptep_get(ptep); if (pte_present(pte)) page = pte_page(pte); return page; } EXPORT_SYMBOL(vmalloc_to_page); /* * Map a vmalloc()-space virtual address to the physical page frame number. */ unsigned long vmalloc_to_pfn(const void *vmalloc_addr) { return page_to_pfn(vmalloc_to_page(vmalloc_addr)); } EXPORT_SYMBOL(vmalloc_to_pfn); /*** Global kva allocator ***/ #define DEBUG_AUGMENT_PROPAGATE_CHECK 0 #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 static DEFINE_SPINLOCK(free_vmap_area_lock); static bool vmap_initialized __read_mostly; /* * This kmem_cache is used for vmap_area objects. Instead of * allocating from slab we reuse an object from this cache to * make things faster. Especially in "no edge" splitting of * free block. */ static struct kmem_cache *vmap_area_cachep; /* * This linked list is used in pair with free_vmap_area_root. * It gives O(1) access to prev/next to perform fast coalescing. */ static LIST_HEAD(free_vmap_area_list); /* * This augment red-black tree represents the free vmap space. * All vmap_area objects in this tree are sorted by va->va_start * address. It is used for allocation and merging when a vmap * object is released. * * Each vmap_area node contains a maximum available free block * of its sub-tree, right or left. Therefore it is possible to * find a lowest match of free area. */ static struct rb_root free_vmap_area_root = RB_ROOT; /* * Preload a CPU with one object for "no edge" split case. The * aim is to get rid of allocations from the atomic context, thus * to use more permissive allocation masks. */ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); /* * This structure defines a single, solid model where a list and * rb-tree are part of one entity protected by the lock. Nodes are * sorted in ascending order, thus for O(1) access to left/right * neighbors a list is used as well as for sequential traversal. */ struct rb_list { struct rb_root root; struct list_head head; spinlock_t lock; }; /* * A fast size storage contains VAs up to 1M size. A pool consists * of linked between each other ready to go VAs of certain sizes. * An index in the pool-array corresponds to number of pages + 1. */ #define MAX_VA_SIZE_PAGES 256 struct vmap_pool { struct list_head head; unsigned long len; }; /* * An effective vmap-node logic. Users make use of nodes instead * of a global heap. It allows to balance an access and mitigate * contention. */ static struct vmap_node { /* Simple size segregated storage. */ struct vmap_pool pool[MAX_VA_SIZE_PAGES]; spinlock_t pool_lock; bool skip_populate; /* Bookkeeping data of this node. */ struct rb_list busy; struct rb_list lazy; /* * Ready-to-free areas. */ struct list_head purge_list; struct work_struct purge_work; unsigned long nr_purged; } single; /* * Initial setup consists of one single node, i.e. a balancing * is fully disabled. Later on, after vmap is initialized these * parameters are updated based on a system capacity. */ static struct vmap_node *vmap_nodes = &single; static __read_mostly unsigned int nr_vmap_nodes = 1; static __read_mostly unsigned int vmap_zone_size = 1; static inline unsigned int addr_to_node_id(unsigned long addr) { return (addr / vmap_zone_size) % nr_vmap_nodes; } static inline struct vmap_node * addr_to_node(unsigned long addr) { return &vmap_nodes[addr_to_node_id(addr)]; } static inline struct vmap_node * id_to_node(unsigned int id) { return &vmap_nodes[id % nr_vmap_nodes]; } /* * We use the value 0 to represent "no node", that is why * an encoded value will be the node-id incremented by 1. * It is always greater then 0. A valid node_id which can * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id * is not valid 0 is returned. */ static unsigned int encode_vn_id(unsigned int node_id) { /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return (node_id + 1) << BITS_PER_BYTE; /* Warn and no node encoded. */ WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id); return 0; } /* * Returns an encoded node-id, the valid range is within * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is * returned if extracted data is wrong. */ static unsigned int decode_vn_id(unsigned int val) { unsigned int node_id = (val >> BITS_PER_BYTE) - 1; /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return node_id; /* If it was _not_ zero, warn. */ WARN_ONCE(node_id != UINT_MAX, "Decode wrong node id (%d)\n", node_id); return nr_vmap_nodes; } static bool is_vn_id_valid(unsigned int node_id) { if (node_id < nr_vmap_nodes) return true; return false; } static __always_inline unsigned long va_size(struct vmap_area *va) { return (va->va_end - va->va_start); } static __always_inline unsigned long get_subtree_max_size(struct rb_node *node) { struct vmap_area *va; va = rb_entry_safe(node, struct vmap_area, rb_node); return va ? va->subtree_max_size : 0; } RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) static void reclaim_and_purge_vmap_areas(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); static void drain_vmap_area_work(struct work_struct *work); static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work); static atomic_long_t nr_vmalloc_pages; unsigned long vmalloc_nr_pages(void) { return atomic_long_read(&nr_vmalloc_pages); } static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) { struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr >= va->va_end) n = n->rb_right; else return va; } return NULL; } /* Look up the first VA which satisfies addr < va_end, NULL if none. */ static struct vmap_area * __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) { struct vmap_area *va = NULL; struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *tmp; tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_end > addr) { va = tmp; if (tmp->va_start <= addr) break; n = n->rb_left; } else n = n->rb_right; } return va; } /* * Returns a node where a first VA, that satisfies addr < va_end, resides. * If success, a node is locked. A user is responsible to unlock it when a * VA is no longer needed to be accessed. * * Returns NULL if nothing found. */ static struct vmap_node * find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) { unsigned long va_start_lowest; struct vmap_node *vn; int i; repeat: for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); if (*va) if (!va_start_lowest || (*va)->va_start < va_start_lowest) va_start_lowest = (*va)->va_start; spin_unlock(&vn->busy.lock); } /* * Check if found VA exists, it might have gone away. In this case we * repeat the search because a VA has been removed concurrently and we * need to proceed to the next one, which is a rare case. */ if (va_start_lowest) { vn = addr_to_node(va_start_lowest); spin_lock(&vn->busy.lock); *va = __find_vmap_area(va_start_lowest, &vn->busy.root); if (*va) return vn; spin_unlock(&vn->busy.lock); goto repeat; } return NULL; } /* * This function returns back addresses of parent node * and its left or right link for further processing. * * Otherwise NULL is returned. In that case all further * steps regarding inserting of conflicting overlap range * have to be declined and actually considered as a bug. */ static __always_inline struct rb_node ** find_va_links(struct vmap_area *va, struct rb_root *root, struct rb_node *from, struct rb_node **parent) { struct vmap_area *tmp_va; struct rb_node **link; if (root) { link = &root->rb_node; if (unlikely(!*link)) { *parent = NULL; return link; } } else { link = &from; } /* * Go to the bottom of the tree. When we hit the last point * we end up with parent rb_node and correct direction, i name * it link, where the new va->rb_node will be attached to. */ do { tmp_va = rb_entry(*link, struct vmap_area, rb_node); /* * During the traversal we also do some sanity check. * Trigger the BUG() if there are sides(left/right) * or full overlaps. */ if (va->va_end <= tmp_va->va_start) link = &(*link)->rb_left; else if (va->va_start >= tmp_va->va_end) link = &(*link)->rb_right; else { WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end); return NULL; } } while (*link); *parent = &tmp_va->rb_node; return link; } static __always_inline struct list_head * get_va_next_sibling(struct rb_node *parent, struct rb_node **link) { struct list_head *list; if (unlikely(!parent)) /* * The red-black tree where we try to find VA neighbors * before merging or inserting is empty, i.e. it means * there is no free vmap space. Normally it does not * happen but we handle this case anyway. */ return NULL; list = &rb_entry(parent, struct vmap_area, rb_node)->list; return (&parent->rb_right == link ? list->next : list); } static __always_inline void __link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head, bool augment) { /* * VA is still not in the list, but we can * identify its future previous list_head node. */ if (likely(parent)) { head = &rb_entry(parent, struct vmap_area, rb_node)->list; if (&parent->rb_right != link) head = head->prev; } /* Insert to the rb-tree */ rb_link_node(&va->rb_node, parent, link); if (augment) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). * It is because we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, * to let __augment_tree_propagate_from() puts everything to * the correct order later on. */ rb_insert_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); va->subtree_max_size = 0; } else { rb_insert_color(&va->rb_node, root); } /* Address-sort this list */ list_add(&va->list, head); } static __always_inline void link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, false); } static __always_inline void link_va_augment(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, true); } static __always_inline void __unlink_va(struct vmap_area *va, struct rb_root *root, bool augment) { if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) return; if (augment) rb_erase_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); else rb_erase(&va->rb_node, root); list_del_init(&va->list); RB_CLEAR_NODE(&va->rb_node); } static __always_inline void unlink_va(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, false); } static __always_inline void unlink_va_augment(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, true); } #if DEBUG_AUGMENT_PROPAGATE_CHECK /* * Gets called when remove the node and rotate. */ static __always_inline unsigned long compute_subtree_max_size(struct vmap_area *va) { return max3(va_size(va), get_subtree_max_size(va->rb_node.rb_left), get_subtree_max_size(va->rb_node.rb_right)); } static void augment_tree_propagate_check(void) { struct vmap_area *va; unsigned long computed_size; list_for_each_entry(va, &free_vmap_area_list, list) { computed_size = compute_subtree_max_size(va); if (computed_size != va->subtree_max_size) pr_emerg("tree is corrupted: %lu, %lu\n", va_size(va), va->subtree_max_size); } } #endif /* * This function populates subtree_max_size from bottom to upper * levels starting from VA point. The propagation must be done * when VA size is modified by changing its va_start/va_end. Or * in case of newly inserting of VA to the tree. * * It means that __augment_tree_propagate_from() must be called: * - After VA has been inserted to the tree(free path); * - After VA has been shrunk(allocation path); * - After VA has been increased(merging path). * * Please note that, it does not mean that upper parent nodes * and their subtree_max_size are recalculated all the time up * to the root node. * * 4--8 * /\ * / \ * / \ * 2--2 8--8 * * For example if we modify the node 4, shrinking it to 2, then * no any modification is required. If we shrink the node 2 to 1 * its subtree_max_size is updated only, and set to 1. If we shrink * the node 8 to 6, then its subtree_max_size is set to 6 and parent * node becomes 4--6. */ static __always_inline void augment_tree_propagate_from(struct vmap_area *va) { /* * Populate the tree from bottom towards the root until * the calculated maximum available size of checked node * is equal to its current one. */ free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL); #if DEBUG_AUGMENT_PROPAGATE_CHECK augment_tree_propagate_check(); #endif } static void insert_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; link = find_va_links(va, root, NULL, &parent); if (link) link_va(va, root, parent, link, head); } static void insert_vmap_area_augment(struct vmap_area *va, struct rb_node *from, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; if (from) link = find_va_links(va, NULL, from, &parent); else link = find_va_links(va, root, NULL, &parent); if (link) { link_va_augment(va, root, parent, link, head); augment_tree_propagate_from(va); } } /* * Merge de-allocated chunk of VA memory with previous * and next free blocks. If coalesce is not done a new * free area is inserted. If VA has been merged, it is * freed. * * Please note, it can return NULL in case of overlap * ranges, followed by WARN() report. Despite it is a * buggy behaviour, a system can be alive and keep * ongoing. */ static __always_inline struct vmap_area * __merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head, bool augment) { struct vmap_area *sibling; struct list_head *next; struct rb_node **link; struct rb_node *parent; bool merged = false; /* * Find a place in the tree where VA potentially will be * inserted, unless it is merged with its sibling/siblings. */ link = find_va_links(va, root, NULL, &parent); if (!link) return NULL; /* * Get next node of VA to check if merging can be done. */ next = get_va_next_sibling(parent, link); if (unlikely(next == NULL)) goto insert; /* * start end * | | * |<------VA------>|<-----Next----->| * | | * start end */ if (next != head) { sibling = list_entry(next, struct vmap_area, list); if (sibling->va_start == va->va_end) { sibling->va_start = va->va_start; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } /* * start end * | | * |<-----Prev----->|<------VA------>| * | | * start end */ if (next->prev != head) { sibling = list_entry(next->prev, struct vmap_area, list); if (sibling->va_end == va->va_start) { /* * If both neighbors are coalesced, it is important * to unlink the "next" node first, followed by merging * with "previous" one. Otherwise the tree might not be * fully populated if a sibling's augmented value is * "normalized" because of rotation operations. */ if (merged) __unlink_va(va, root, augment); sibling->va_end = va->va_end; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } insert: if (!merged) __link_va(va, root, parent, link, head, augment); return va; } static __always_inline struct vmap_area * merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { return __merge_or_add_vmap_area(va, root, head, false); } static __always_inline struct vmap_area * merge_or_add_vmap_area_augment(struct vmap_area *va, struct rb_root *root, struct list_head *head) { va = __merge_or_add_vmap_area(va, root, head, true); if (va) augment_tree_propagate_from(va); return va; } static __always_inline bool is_within_this_va(struct vmap_area *va, unsigned long size, unsigned long align, unsigned long vstart) { unsigned long nva_start_addr; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Can be overflowed due to big size or alignment. */ if (nva_start_addr + size < nva_start_addr || nva_start_addr < vstart) return false; return (nva_start_addr + size <= va->va_end); } /* * Find the first free block(lowest start address) in the tree, * that will accomplish the request corresponding to passing * parameters. Please note, with an alignment bigger than PAGE_SIZE, * a search length is adjusted to account for worst case alignment * overhead. */ static __always_inline struct vmap_area * find_vmap_lowest_match(struct rb_root *root, unsigned long size, unsigned long align, unsigned long vstart, bool adjust_search_size) { struct vmap_area *va; struct rb_node *node; unsigned long length; /* Start from the root. */ node = root->rb_node; /* Adjust the search size for alignment overhead. */ length = adjust_search_size ? size + align - 1 : size; while (node) { va = rb_entry(node, struct vmap_area, rb_node); if (get_subtree_max_size(node->rb_left) >= length && vstart < va->va_start) { node = node->rb_left; } else { if (is_within_this_va(va, size, align, vstart)) return va; /* * Does not make sense to go deeper towards the right * sub-tree if it does not have a free block that is * equal or bigger to the requested search length. */ if (get_subtree_max_size(node->rb_right) >= length) { node = node->rb_right; continue; } /* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen * due to "vstart" restriction or an alignment overhead * that is bigger then PAGE_SIZE. */ while ((node = rb_parent(node))) { va = rb_entry(node, struct vmap_area, rb_node); if (is_within_this_va(va, size, align, vstart)) return va; if (get_subtree_max_size(node->rb_right) >= length && vstart <= va->va_start) { /* * Shift the vstart forward. Please note, we update it with * parent's start address adding "1" because we do not want * to enter same sub-tree after it has already been checked * and no suitable free block found there. */ vstart = va->va_start + 1; node = node->rb_right; break; } } } } return NULL; } #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK #include <linux/random.h> static struct vmap_area * find_vmap_lowest_linear_match(struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart) { struct vmap_area *va; list_for_each_entry(va, head, list) { if (!is_within_this_va(va, size, align, vstart)) continue; return va; } return NULL; } static void find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align) { struct vmap_area *va_1, *va_2; unsigned long vstart; unsigned int rnd; get_random_bytes(&rnd, sizeof(rnd)); vstart = VMALLOC_START + rnd; va_1 = find_vmap_lowest_match(root, size, align, vstart, false); va_2 = find_vmap_lowest_linear_match(head, size, align, vstart); if (va_1 != va_2) pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", va_1, va_2, vstart); } #endif enum fit_type { NOTHING_FIT = 0, FL_FIT_TYPE = 1, /* full fit */ LE_FIT_TYPE = 2, /* left edge fit */ RE_FIT_TYPE = 3, /* right edge fit */ NE_FIT_TYPE = 4 /* no edge fit */ }; static __always_inline enum fit_type classify_va_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { enum fit_type type; /* Check if it is within VA. */ if (nva_start_addr < va->va_start || nva_start_addr + size > va->va_end) return NOTHING_FIT; /* Now classify. */ if (va->va_start == nva_start_addr) { if (va->va_end == nva_start_addr + size) type = FL_FIT_TYPE; else type = LE_FIT_TYPE; } else if (va->va_end == nva_start_addr + size) { type = RE_FIT_TYPE; } else { type = NE_FIT_TYPE; } return type; } static __always_inline int va_clip(struct rb_root *root, struct list_head *head, struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { struct vmap_area *lva = NULL; enum fit_type type = classify_va_fit_type(va, nva_start_addr, size); if (type == FL_FIT_TYPE) { /* * No need to split VA, it fully fits. * * | | * V NVA V * |---------------| */ unlink_va_augment(va, root); kmem_cache_free(vmap_area_cachep, va); } else if (type == LE_FIT_TYPE) { /* * Split left edge of fit VA. * * | | * V NVA V R * |-------|-------| */ va->va_start += size; } else if (type == RE_FIT_TYPE) { /* * Split right edge of fit VA. * * | | * L V NVA V * |-------|-------| */ va->va_end = nva_start_addr; } else if (type == NE_FIT_TYPE) { /* * Split no edge of fit VA. * * | | * L V NVA V R * |---|-------|---| */ lva = __this_cpu_xchg(ne_fit_preload_node, NULL); if (unlikely(!lva)) { /* * For percpu allocator we do not do any pre-allocation * and leave it as it is. The reason is it most likely * never ends up with NE_FIT_TYPE splitting. In case of * percpu allocations offsets and sizes are aligned to * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE * are its main fitting cases. * * There are a few exceptions though, as an example it is * a first allocation (early boot up) when we have "one" * big free space that has to be split. * * Also we can hit this path in case of regular "vmap" * allocations, if "this" current CPU was not preloaded. * See the comment in alloc_vmap_area() why. If so, then * GFP_NOWAIT is used instead to get an extra object for * split purpose. That is rare and most time does not * occur. * * What happens if an allocation gets failed. Basically, * an "overflow" path is triggered to purge lazily freed * areas to free some memory, then, the "retry" path is * triggered to repeat one more time. See more details * in alloc_vmap_area() function. */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) return -1; } /* * Build the remainder. */ lva->va_start = va->va_start; lva->va_end = nva_start_addr; /* * Shrink this VA to remaining size. */ va->va_start = nva_start_addr + size; } else { return -1; } if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, root, head); } return 0; } static unsigned long va_alloc(struct vmap_area *va, struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { unsigned long nva_start_addr; int ret; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Check the "vend" restriction. */ if (nva_start_addr + size > vend) return vend; /* Update the free vmap_area. */ ret = va_clip(root, head, va, nva_start_addr, size); if (WARN_ON_ONCE(ret)) return vend; return nva_start_addr; } /* * Returns a start address of the newly allocated area, if success. * Otherwise a vend is returned that indicates failure. */ static __always_inline unsigned long __alloc_vmap_area(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { bool adjust_search_size = true; unsigned long nva_start_addr; struct vmap_area *va; /* * Do not adjust when: * a) align <= PAGE_SIZE, because it does not make any sense. * All blocks(their start addresses) are at least PAGE_SIZE * aligned anyway; * b) a short range where a requested size corresponds to exactly * specified [vstart:vend] interval and an alignment > PAGE_SIZE. * With adjusted search length an allocation would not succeed. */ if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size)) adjust_search_size = false; va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va)) return vend; nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend); if (nva_start_addr == vend) return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK find_vmap_lowest_match_check(root, head, size, align); #endif return nva_start_addr; } /* * Free a region of KVA allocated by alloc_vmap_area */ static void free_vmap_area(struct vmap_area *va) { struct vmap_node *vn = addr_to_node(va->va_start); /* * Remove from the busy tree/list. */ spin_lock(&vn->busy.lock); unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); /* * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static inline void preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) { struct vmap_area *va = NULL, *tmp; /* * Preload this CPU with one extra vmap_area object. It is used * when fit type of free area is NE_FIT_TYPE. It guarantees that * a CPU that does an allocation is preloaded. * * We do it in non-atomic context, thus it allows us to use more * permissive allocation masks to be more stable under low memory * condition and high memory pressure. */ if (!this_cpu_read(ne_fit_preload_node)) va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); spin_lock(lock); tmp = NULL; if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va)) kmem_cache_free(vmap_area_cachep, va); } static struct vmap_pool * size_to_va_pool(struct vmap_node *vn, unsigned long size) { unsigned int idx = (size - 1) / PAGE_SIZE; if (idx < MAX_VA_SIZE_PAGES) return &vn->pool[idx]; return NULL; } static bool node_pool_add_va(struct vmap_node *n, struct vmap_area *va) { struct vmap_pool *vp; vp = size_to_va_pool(n, va_size(va)); if (!vp) return false; spin_lock(&n->pool_lock); list_add(&va->list, &vp->head); WRITE_ONCE(vp->len, vp->len + 1); spin_unlock(&n->pool_lock); return true; } static struct vmap_area * node_pool_del_va(struct vmap_node *vn, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { struct vmap_area *va = NULL; struct vmap_pool *vp; int err = 0; vp = size_to_va_pool(vn, size); if (!vp || list_empty(&vp->head)) return NULL; spin_lock(&vn->pool_lock); if (!list_empty(&vp->head)) { va = list_first_entry(&vp->head, struct vmap_area, list); if (IS_ALIGNED(va->va_start, align)) { /* * Do some sanity check and emit a warning * if one of below checks detects an error. */ err |= (va_size(va) != size); err |= (va->va_start < vstart); err |= (va->va_end > vend); if (!WARN_ON_ONCE(err)) { list_del_init(&va->list); WRITE_ONCE(vp->len, vp->len - 1); } else { va = NULL; } } else { list_move_tail(&va->list, &vp->head); va = NULL; } } spin_unlock(&vn->pool_lock); return va; } static struct vmap_area * node_alloc(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, unsigned long *addr, unsigned int *vn_id) { struct vmap_area *va; *vn_id = 0; *addr = vend; /* * Fallback to a global heap if not vmalloc or there * is only one node. */ if (vstart != VMALLOC_START || vend != VMALLOC_END || nr_vmap_nodes == 1) return NULL; *vn_id = raw_smp_processor_id() % nr_vmap_nodes; va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend); *vn_id = encode_vn_id(*vn_id); if (va) *addr = va->va_start; return va; } static inline void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va_size(va); vm->caller = caller; va->vm = vm; } /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. If vm is passed in, the two will also be bound. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask, unsigned long va_flags, struct vm_struct *vm) { struct vmap_node *vn; struct vmap_area *va; unsigned long freed; unsigned long addr; unsigned int vn_id; int purged = 0; int ret; if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align))) return ERR_PTR(-EINVAL); if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); might_sleep(); /* * If a VA is obtained from a global heap(if it fails here) * it is anyway marked with this "vn_id" so it is returned * to this pool's node later. Such way gives a possibility * to populate pools based on users demand. * * On success a ready to go VA is returned. */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { gfp_mask = gfp_mask & GFP_RECLAIM_MASK; va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); /* * Only scan the relevant parts containing pointers to other objects * to avoid false negatives. */ kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); } retry: if (addr == vend) { preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, size, align, vstart, vend); spin_unlock(&free_vmap_area_lock); } trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend); /* * If an allocation fails, the "vend" address is * returned. Therefore trigger the overflow path. */ if (unlikely(addr == vend)) goto overflow; va->va_start = addr; va->va_end = addr + size; va->vm = NULL; va->flags = (va_flags | vn_id); if (vm) { vm->addr = (void *)va->va_start; vm->size = va_size(va); va->vm = vm; } vn = addr_to_node(va->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); spin_unlock(&vn->busy.lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); ret = kasan_populate_vmalloc(addr, size); if (ret) { free_vmap_area(va); return ERR_PTR(ret); } return va; overflow: if (!purged) { reclaim_and_purge_vmap_areas(); purged = 1; goto retry; } freed = 0; blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); if (freed > 0) { purged = 0; goto retry; } if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n", size, vstart, vend); kmem_cache_free(vmap_area_cachep, va); return ERR_PTR(-EBUSY); } int register_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(register_vmap_purge_notifier); int unregister_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); /* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); /* * Serialize vmap purging. There is no actual critical section protected * by this lock, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); static cpumask_t purge_nodes; static void reclaim_list_global(struct list_head *head) { struct vmap_area *va, *n; if (list_empty(head)) return; spin_lock(&free_vmap_area_lock); list_for_each_entry_safe(va, n, head, list) merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static void decay_va_pool_node(struct vmap_node *vn, bool full_decay) { LIST_HEAD(decay_list); struct rb_root decay_root = RB_ROOT; struct vmap_area *va, *nva; unsigned long n_decay; int i; for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { LIST_HEAD(tmp_list); if (list_empty(&vn->pool[i].head)) continue; /* Detach the pool, so no-one can access it. */ spin_lock(&vn->pool_lock); list_replace_init(&vn->pool[i].head, &tmp_list); spin_unlock(&vn->pool_lock); if (full_decay) WRITE_ONCE(vn->pool[i].len, 0); /* Decay a pool by ~25% out of left objects. */ n_decay = vn->pool[i].len >> 2; list_for_each_entry_safe(va, nva, &tmp_list, list) { list_del_init(&va->list); merge_or_add_vmap_area(va, &decay_root, &decay_list); if (!full_decay) { WRITE_ONCE(vn->pool[i].len, vn->pool[i].len - 1); if (!--n_decay) break; } } /* * Attach the pool back if it has been partly decayed. * Please note, it is supposed that nobody(other contexts) * can populate the pool therefore a simple list replace * operation takes place here. */ if (!full_decay && !list_empty(&tmp_list)) { spin_lock(&vn->pool_lock); list_replace_init(&tmp_list, &vn->pool[i].head); spin_unlock(&vn->pool_lock); } } reclaim_list_global(&decay_list); } static void kasan_release_vmalloc_node(struct vmap_node *vn) { struct vmap_area *va; unsigned long start, end; start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start; end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end; list_for_each_entry(va, &vn->purge_list, list) { if (is_vmalloc_or_module_addr((void *) va->va_start)) kasan_release_vmalloc(va->va_start, va->va_end, va->va_start, va->va_end, KASAN_VMALLOC_PAGE_RANGE); } kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH); } static void purge_vmap_node(struct work_struct *work) { struct vmap_node *vn = container_of(work, struct vmap_node, purge_work); unsigned long nr_purged_pages = 0; struct vmap_area *va, *n_va; LIST_HEAD(local_list); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) kasan_release_vmalloc_node(vn); vn->nr_purged = 0; list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { unsigned long nr = va_size(va) >> PAGE_SHIFT; unsigned int vn_id = decode_vn_id(va->flags); list_del_init(&va->list); nr_purged_pages += nr; vn->nr_purged++; if (is_vn_id_valid(vn_id) && !vn->skip_populate) if (node_pool_add_va(vn, va)) continue; /* Go back to global. */ list_add(&va->list, &local_list); } atomic_long_sub(nr_purged_pages, &vmap_lazy_nr); reclaim_list_global(&local_list); } /* * Purges all lazily-freed vmap areas. */ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, bool full_pool_decay) { unsigned long nr_purged_areas = 0; unsigned int nr_purge_helpers; unsigned int nr_purge_nodes; struct vmap_node *vn; int i; lockdep_assert_held(&vmap_purge_lock); /* * Use cpumask to mark which node has to be processed. */ purge_nodes = CPU_MASK_NONE; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; INIT_LIST_HEAD(&vn->purge_list); vn->skip_populate = full_pool_decay; decay_va_pool_node(vn, full_pool_decay); if (RB_EMPTY_ROOT(&vn->lazy.root)) continue; spin_lock(&vn->lazy.lock); WRITE_ONCE(vn->lazy.root.rb_node, NULL); list_replace_init(&vn->lazy.head, &vn->purge_list); spin_unlock(&vn->lazy.lock); start = min(start, list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start); end = max(end, list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end); cpumask_set_cpu(i, &purge_nodes); } nr_purge_nodes = cpumask_weight(&purge_nodes); if (nr_purge_nodes > 0) { flush_tlb_kernel_range(start, end); /* One extra worker is per a lazy_max_pages() full set minus one. */ nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages(); nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1; for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (nr_purge_helpers > 0) { INIT_WORK(&vn->purge_work, purge_vmap_node); if (cpumask_test_cpu(i, cpu_online_mask)) schedule_work_on(i, &vn->purge_work); else schedule_work(&vn->purge_work); nr_purge_helpers--; } else { vn->purge_work.func = NULL; purge_vmap_node(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (vn->purge_work.func) { flush_work(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } } trace_purge_vmap_area_lazy(start, end, nr_purged_areas); return nr_purged_areas > 0; } /* * Reclaim vmap areas by purging fragmented blocks and purge_vmap_area_list. */ static void reclaim_and_purge_vmap_areas(void) { mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); __purge_vmap_area_lazy(ULONG_MAX, 0, true); mutex_unlock(&vmap_purge_lock); } static void drain_vmap_area_work(struct work_struct *work) { mutex_lock(&vmap_purge_lock); __purge_vmap_area_lazy(ULONG_MAX, 0, false); mutex_unlock(&vmap_purge_lock); } /* * Free a vmap area, caller ensuring that the area has been unmapped, * unlinked and flush_cache_vunmap had been called for the correct * range previously. */ static void free_vmap_area_noflush(struct vmap_area *va) { unsigned long nr_lazy_max = lazy_max_pages(); unsigned long va_start = va->va_start; unsigned int vn_id = decode_vn_id(va->flags); struct vmap_node *vn; unsigned long nr_lazy; if (WARN_ON_ONCE(!list_empty(&va->list))) return; nr_lazy = atomic_long_add_return(va_size(va) >> PAGE_SHIFT, &vmap_lazy_nr); /* * If it was request by a certain node we would like to * return it to that node, i.e. its pool for later reuse. */ vn = is_vn_id_valid(vn_id) ? id_to_node(vn_id):addr_to_node(va->va_start); spin_lock(&vn->lazy.lock); insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head); spin_unlock(&vn->lazy.lock); trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max); /* After this point, we may free va at any time */ if (unlikely(nr_lazy > nr_lazy_max)) schedule_work(&drain_vmap_work); } /* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); free_vmap_area_noflush(va); } struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; if (unlikely(!vmap_initialized)) return NULL; /* * An addr_to_node_id(addr) converts an address to a node index * where a VA is located. If VA spans several zones and passed * addr is not the same as va->va_start, what is not common, we * may need to scan extra nodes. See an example: * * <----va----> * -|-----|-----|-----|-----|- * 1 2 0 1 * * VA resides in node 1 whereas it spans 1, 2 an 0. If passed * addr is within 2 or 0 nodes we should do extra work. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + 1) % nr_vmap_nodes) != j); return NULL; } static struct vmap_area *find_unlink_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; /* * Check the comment in the find_vmap_area() about the loop. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); if (va) unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + 1) % nr_vmap_nodes) != j); return NULL; } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS \ VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) /* * Purge threshold to prevent overeager purging of fragmented blocks for * regular operations: Purge if vb->free is less than 1/4 of the capacity. */ #define VMAP_PURGE_THRESHOLD (VMAP_BBMAP_BITS / 4) #define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ #define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ #define VMAP_FLAGS_MASK 0x3 struct vmap_block_queue { spinlock_t lock; struct list_head free; /* * An xarray requires an extra memory dynamically to * be allocated. If it is an issue, we can use rb-tree * instead. */ struct xarray vmap_blocks; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; DECLARE_BITMAP(used_map, VMAP_BBMAP_BITS); unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; unsigned int cpu; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * In order to fast access to any "vmap_block" associated with a * specific address, we use a hash. * * A per-cpu vmap_block_queue is used in both ways, to serialize * an access to free block chains among CPUs(alloc path) and it * also acts as a vmap_block hash(alloc/free paths). It means we * overload it, since we already have the per-cpu array which is * used as a hash table. When used as a hash a 'cpu' passed to * per_cpu() is not actually a CPU but rather a hash index. * * A hash function is addr_to_vb_xa() which hashes any address * to a specific index(in a hash) it belongs to. This then uses a * per_cpu() macro to access an array with generated index. * * An example: * * CPU_1 CPU_2 CPU_0 * | | | * V V V * 0 10 20 30 40 50 60 * |------|------|------|------|------|------|...<vmap address space> * CPU0 CPU1 CPU2 CPU0 CPU1 CPU2 * * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus * it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock; * * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus * it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock; * * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus * it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock. * * This technique almost always avoids lock contention on insert/remove, * however xarray spinlocks protect against any contention that remains. */ static struct xarray * addr_to_vb_xa(unsigned long addr) { int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids; /* * Please note, nr_cpu_ids points on a highest set * possible bit, i.e. we never invoke cpumask_next() * if an index points on it which is nr_cpu_ids - 1. */ if (!cpu_possible(index)) index = cpumask_next(index, cpu_possible_mask); return &per_cpu(vmap_block_queue, index).vmap_blocks; } /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) { unsigned long addr; addr = va_start + (pages_off << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); return (void *)addr; } /** * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this * block. Of course pages number can't exceed VMAP_BBMAP_BITS * @order: how many 2^order pages should be occupied in newly allocated block * @gfp_mask: flags for the page level allocator * * Return: virtual address in a newly allocated block or ERR_PTR(-errno) */ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; struct xarray *xa; unsigned long vb_idx; int node, err; void *vaddr; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask, VMAP_RAM|VMAP_BLOCK, NULL); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); } vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; /* At least something should be left free */ BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); bitmap_zero(vb->used_map, VMAP_BBMAP_BITS); vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); vb->cpu = raw_smp_processor_id(); xa = addr_to_vb_xa(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); err = xa_insert(xa, vb_idx, vb, gfp_mask); if (err) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } /* * list_add_tail_rcu could happened in another core * rather than vb->cpu due to task migration, which * is safe as list_add_tail_rcu will ensure the list's * integrity together with list_for_each_rcu from read * side. */ vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); return vaddr; } static void free_vmap_block(struct vmap_block *vb) { struct vmap_node *vn; struct vmap_block *tmp; struct xarray *xa; xa = addr_to_vb_xa(vb->va->va_start); tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); vn = addr_to_node(vb->va->va_start); spin_lock(&vn->busy.lock); unlink_va(vb->va, &vn->busy.root); spin_unlock(&vn->busy.lock); free_vmap_area_noflush(vb->va); kfree_rcu(vb, rcu_head); } static bool purge_fragmented_block(struct vmap_block *vb, struct list_head *purge_list, bool force_purge) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu); if (vb->free + vb->dirty != VMAP_BBMAP_BITS || vb->dirty == VMAP_BBMAP_BITS) return false; /* Don't overeagerly purge usable blocks unless requested */ if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD)) return false; /* prevent further allocs after releasing lock */ WRITE_ONCE(vb->free, 0); /* prevent purging it again */ WRITE_ONCE(vb->dirty, VMAP_BBMAP_BITS); vb->dirty_min = 0; vb->dirty_max = VMAP_BBMAP_BITS; spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); list_add_tail(&vb->purge, purge_list); return true; } static void free_purged_blocks(struct list_head *purge_list) { struct vmap_block *vb, *n_vb; list_for_each_entry_safe(vb, n_vb, purge_list, purge) { list_del(&vb->purge); free_vmap_block(vb); } } static void purge_fragmented_blocks(int cpu) { LIST_HEAD(purge); struct vmap_block *vb; struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long free = READ_ONCE(vb->free); unsigned long dirty = READ_ONCE(vb->dirty); if (free + dirty != VMAP_BBMAP_BITS || dirty == VMAP_BBMAP_BITS) continue; spin_lock(&vb->lock); purge_fragmented_block(vb, &purge, true); spin_unlock(&vb->lock); } rcu_read_unlock(); free_purged_blocks(&purge); } static void purge_fragmented_blocks_allcpus(void) { int cpu; for_each_possible_cpu(cpu) purge_fragmented_blocks(cpu); } static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; void *vaddr = NULL; unsigned int order; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); if (WARN_ON(size == 0)) { /* * Allocating 0 bytes isn't what caller wants since * get_order(0) returns funny result. Just warn and terminate * early. */ return ERR_PTR(-EINVAL); } order = get_order(size); rcu_read_lock(); vbq = raw_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; if (READ_ONCE(vb->free) < (1UL << order)) continue; spin_lock(&vb->lock); if (vb->free < (1UL << order)) { spin_unlock(&vb->lock); continue; } pages_off = VMAP_BBMAP_BITS - vb->free; vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); WRITE_ONCE(vb->free, vb->free - (1UL << order)); bitmap_set(vb->used_map, pages_off, (1UL << order)); if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); break; } rcu_read_unlock(); /* Allocate new block if nothing was found */ if (!vaddr) vaddr = new_vmap_block(order, gfp_mask); return vaddr; } static void vb_free(unsigned long addr, unsigned long size) { unsigned long offset; unsigned int order; struct vmap_block *vb; struct xarray *xa; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); flush_cache_vunmap(addr, addr + size); order = get_order(size); offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; xa = addr_to_vb_xa(addr); vb = xa_load(xa, addr_to_vb_idx(addr)); spin_lock(&vb->lock); bitmap_clear(vb->used_map, offset, (1UL << order)); spin_unlock(&vb->lock); vunmap_range_noflush(addr, addr + size); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(addr, addr + size); spin_lock(&vb->lock); /* Expand the not yet TLB flushed dirty range */ vb->dirty_min = min(vb->dirty_min, offset); vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); WRITE_ONCE(vb->dirty, vb->dirty + (1UL << order)); if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free); spin_unlock(&vb->lock); free_vmap_block(vb); } else spin_unlock(&vb->lock); } static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { LIST_HEAD(purge_list); int cpu; if (unlikely(!vmap_initialized)) return; mutex_lock(&vmap_purge_lock); for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; unsigned long idx; rcu_read_lock(); xa_for_each(&vbq->vmap_blocks, idx, vb) { spin_lock(&vb->lock); /* * Try to purge a fragmented block first. If it's * not purgeable, check whether there is dirty * space to be flushed. */ if (!purge_fragmented_block(vb, &purge_list, false) && vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; s = va_start + (vb->dirty_min << PAGE_SHIFT); e = va_start + (vb->dirty_max << PAGE_SHIFT); start = min(s, start); end = max(e, end); /* Prevent that this is flushed again */ vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; flush = 1; } spin_unlock(&vb->lock); } rcu_read_unlock(); } free_purged_blocks(&purge_list); if (!__purge_vmap_area_lazy(start, end, false) && flush) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } /** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer. */ void vm_unmap_aliases(void) { unsigned long start = ULONG_MAX, end = 0; int flush = 0; _vm_unmap_aliases(start, end, flush); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial) */ void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr = (unsigned long)kasan_reset_tag(mem); struct vmap_area *va; might_sleep(); BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); BUG_ON(!PAGE_ALIGNED(addr)); kasan_poison_vmalloc(mem, size); if (likely(count <= VMAP_MAX_ALLOC)) { debug_check_no_locks_freed(mem, size); vb_free(addr, size); return; } va = find_unlink_vmap_area(addr); if (WARN_ON_ONCE(!va)) return; debug_check_no_locks_freed((void *)va->va_start, va_size(va)); free_unmap_vmap_area(va); } EXPORT_SYMBOL(vm_unmap_ram); /** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life * objects with vm_map_ram(), it could consume lots of address space through * fragmentation (especially on a 32bit machine). You could see failures in * the end. Please use this function for short-lived objects. * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr; void *mem; if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL, VMAP_RAM, NULL); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; } if (vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, PAGE_SHIFT) < 0) { vm_unmap_ram(mem, count); return NULL; } /* * Mark the pages as accessible, now that they are mapped. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL); return mem; } EXPORT_SYMBOL(vm_map_ram); static struct vm_struct *vmlist __initdata; static inline unsigned int vm_area_page_order(struct vm_struct *vm) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC return vm->page_order; #else return 0; #endif } unsigned int get_vm_area_page_order(struct vm_struct *vm) { return vm_area_page_order(vm); } static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC vm->page_order = order; #else BUG_ON(order != 0); #endif } /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add * * This function is used to add fixed kernel vm area to vmlist before * vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags * should contain proper values and the other fields should be zero. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_add_early(struct vm_struct *vm) { struct vm_struct *tmp, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) { BUG_ON(tmp->addr < vm->addr + vm->size); break; } else BUG_ON(tmp->addr + tmp->size > vm->addr); } vm->next = *p; *p = vm; } /** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register * @align: requested alignment * * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain * proper values on entry and other fields should be zero. On return, * vm->addr contains the allocated address. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { unsigned long addr = ALIGN(VMALLOC_START, align); struct vm_struct *cur, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) { if ((unsigned long)cur->addr - addr >= vm->size) break; addr = ALIGN((unsigned long)cur->addr + cur->size, align); } BUG_ON(addr > VMALLOC_END - vm->size); vm->addr = (void *)addr; vm->next = *p; *p = vm; kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } static void clear_vm_uninitialized_flag(struct vm_struct *vm) { /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. * Pair with smp_rmb() in show_numa_info(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; } struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; unsigned long requested_size = size; BUG_ON(in_interrupt()); size = ALIGN(size, 1ul << shift); if (unlikely(!size)) return NULL; if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; area->flags = flags; area->caller = caller; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { kfree(area); return NULL; } /* * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a * best-effort approach, as they can be mapped outside of vmalloc code. * For VM_ALLOC mappings, the pages are marked as accessible after * getting mapped in __vmalloc_node_range(). * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ if (!(flags & VM_ALLOC)) area->addr = kasan_unpoison_vmalloc(area->addr, requested_size, KASAN_VMALLOC_PROT_NORMAL); return area; } struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * find_vm_area - find a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and return it. * It is up to the caller to do all required locking to keep the returned * pointer valid. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (!va) return NULL; return va->vm; } /** * remove_vm_area - find and remove a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *remove_vm_area(const void *addr) { struct vmap_area *va; struct vm_struct *vm; might_sleep(); if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", addr)) return NULL; va = find_unlink_vmap_area((unsigned long)addr); if (!va || !va->vm) return NULL; vm = va->vm; debug_check_no_locks_freed(vm->addr, get_vm_area_size(vm)); debug_check_no_obj_freed(vm->addr, get_vm_area_size(vm)); kasan_free_module_shadow(vm); kasan_poison_vmalloc(vm->addr, get_vm_area_size(vm)); free_unmap_vmap_area(va); return vm; } static inline void set_area_direct_map(const struct vm_struct *area, int (*set_direct_map)(struct page *page)) { int i; /* HUGE_VMALLOC passes small pages to set_direct_map */ for (i = 0; i < area->nr_pages; i++) if (page_address(area->pages[i])) set_direct_map(area->pages[i]); } /* * Flush the vm mapping and reset the direct map. */ static void vm_reset_perms(struct vm_struct *area) { unsigned long start = ULONG_MAX, end = 0; unsigned int page_order = vm_area_page_order(area); int flush_dmap = 0; int i; /* * Find the start and end range of the direct mappings to make sure that * the vm_unmap_aliases() flush includes the direct map. */ for (i = 0; i < area->nr_pages; i += 1U << page_order) { unsigned long addr = (unsigned long)page_address(area->pages[i]); if (addr) { unsigned long page_size; page_size = PAGE_SIZE << page_order; start = min(addr, start); end = max(addr + page_size, end); flush_dmap = 1; } } /* * Set direct map to something invalid so that it won't be cached if * there are any accesses after the TLB flush, then flush the TLB and * reset the direct map permissions to the default. */ set_area_direct_map(area, set_direct_map_invalid_noflush); _vm_unmap_aliases(start, end, flush_dmap); set_area_direct_map(area, set_direct_map_default_noflush); } static void delayed_vfree_work(struct work_struct *w) { struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); struct llist_node *t, *llnode; llist_for_each_safe(llnode, t, llist_del_all(&p->list)) vfree(llnode); } /** * vfree_atomic - release memory allocated by vmalloc() * @addr: memory base address * * This one is just like vfree() but can be called in any atomic context * except NMIs. */ void vfree_atomic(const void *addr) { struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); BUG_ON(in_nmi()); kmemleak_free(addr); /* * Use raw_cpu_ptr() because this can be called from preemptible * context. Preemption is absolutely fine here, because the llist_add() * implementation is lockless, so it works even if we are adding to * another cpu's list. schedule_work() should be fine with this too. */ if (addr && llist_add((struct llist_node *)addr, &p->list)) schedule_work(&p->wq); } /** * vfree - Release memory allocated by vmalloc() * @addr: Memory base address * * Free the virtually continuous memory area starting at @addr, as obtained * from one of the vmalloc() family of APIs. This will usually also free the * physical memory underlying the virtual allocation, but that memory is * reference counted, so it will not be freed until the last user goes away. * * If @addr is NULL, no operation is performed. * * Context: * May sleep if called *not* from interrupt context. * Must not be called in NMI context (strictly speaking, it could be * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-dependent would be a really bad idea). */ void vfree(const void *addr) { struct vm_struct *vm; int i; if (unlikely(in_interrupt())) { vfree_atomic(addr); return; } BUG_ON(in_nmi()); kmemleak_free(addr); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", addr); return; } if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS)) vm_reset_perms(vm); for (i = 0; i < vm->nr_pages; i++) { struct page *page = vm->pages[i]; BUG_ON(!page); if (!(vm->flags & VM_MAP_PUT_PAGES)) mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations */ __free_page(page); cond_resched(); } if (!(vm->flags & VM_MAP_PUT_PAGES)) atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * * Must not be called in interrupt context. */ void vunmap(const void *addr) { struct vm_struct *vm; BUG_ON(in_interrupt()); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n", addr); return; } kfree(vm); } EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual space. * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself * (which must be kmalloc or vmalloc memory) and one reference per pages in it * are transferred from the caller to vmap(), and will be freed / dropped when * vfree() is called on the return value. * * Return: the address of the area or %NULL on failure */ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; unsigned long addr; unsigned long size; /* In bytes */ might_sleep(); if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS)) return NULL; /* * Your top guard is someone else's bottom guard. Not having a top * guard compromises someone else's mappings too. */ if (WARN_ON_ONCE(flags & VM_NO_GUARD)) flags &= ~VM_NO_GUARD; if (count > totalram_pages()) return NULL; size = (unsigned long)count << PAGE_SHIFT; area = get_vm_area_caller(size, flags, __builtin_return_address(0)); if (!area) return NULL; addr = (unsigned long)area->addr; if (vmap_pages_range(addr, addr + size, pgprot_nx(prot), pages, PAGE_SHIFT) < 0) { vunmap(area->addr); return NULL; } if (flags & VM_MAP_PUT_PAGES) { area->pages = pages; area->nr_pages = count; } return area->addr; } EXPORT_SYMBOL(vmap); #ifdef CONFIG_VMAP_PFN struct vmap_pfn_data { unsigned long *pfns; pgprot_t prot; unsigned int idx; }; static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private) { struct vmap_pfn_data *data = private; unsigned long pfn = data->pfns[data->idx]; pte_t ptent; if (WARN_ON_ONCE(pfn_valid(pfn))) return -EINVAL; ptent = pte_mkspecial(pfn_pte(pfn, data->prot)); set_pte_at(&init_mm, addr, pte, ptent); data->idx++; return 0; } /** * vmap_pfn - map an array of PFNs into virtually contiguous space * @pfns: array of PFNs * @count: number of pages to map * @prot: page protection for the mapping * * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns * the start address of the mapping. */ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) { struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; struct vm_struct *area; area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP, __builtin_return_address(0)); if (!area) return NULL; if (apply_to_page_range(&init_mm, (unsigned long)area->addr, count * PAGE_SIZE, vmap_pfn_apply, &data)) { free_vm_area(area); return NULL; } flush_cache_vmap((unsigned long)area->addr, (unsigned long)area->addr + count * PAGE_SIZE); return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ static inline unsigned int vm_area_alloc_pages(gfp_t gfp, int nid, unsigned int order, unsigned int nr_pages, struct page **pages) { unsigned int nr_allocated = 0; struct page *page; int i; /* * For order-0 pages we make use of bulk allocator, if * the page array is partly or not at all populated due * to fails, fallback to a single page allocator that is * more permissive. */ if (!order) { while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; /* * A maximum allowed request is hard-coded and is 100 * pages per call. That is done in order to prevent a * long preemption off scenario in the bulk-allocator * so the range is [1:100]. */ nr_pages_request = min(100U, nr_pages - nr_allocated); /* memory allocation should consider mempolicy, we can't * wrongly use nearest node when nid == NUMA_NO_NODE, * otherwise memory may be allocated in only one node, * but mempolicy wants to alloc memory by interleaving. */ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) nr = alloc_pages_bulk_mempolicy_noprof(gfp, nr_pages_request, pages + nr_allocated); else nr = alloc_pages_bulk_node_noprof(gfp, nid, nr_pages_request, pages + nr_allocated); nr_allocated += nr; cond_resched(); /* * If zero or pages were obtained partly, * fallback to a single page allocator. */ if (nr != nr_pages_request) break; } } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) page = alloc_pages_noprof(gfp, order); else page = alloc_pages_node_noprof(nid, gfp, order); if (unlikely(!page)) break; /* * High-order allocations must be able to be treated as * independent small pages by callers (as they can with * small-page vmallocs). Some drivers do their own refcounting * on vmalloc_to_page() pages, some use page->mapping, * page->lru, etc. */ if (order) split_page(page, order); /* * Careful, we allocate and map page-order pages, but * tracking is done per PAGE_SIZE page so as to keep the * vm_struct APIs independent of the physical/mapped size. */ for (i = 0; i < (1U << order); i++) pages[nr_allocated + i] = page + i; cond_resched(); nr_allocated += 1U << order; } return nr_allocated; } static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, unsigned int page_shift, int node) { const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; bool nofail = gfp_mask & __GFP_NOFAIL; unsigned long addr = (unsigned long)area->addr; unsigned long size = get_vm_area_size(area); unsigned long array_size; unsigned int nr_small_pages = size >> PAGE_SHIFT; unsigned int page_order; unsigned int flags; int ret; array_size = (unsigned long)nr_small_pages * sizeof(struct page *); if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) gfp_mask |= __GFP_HIGHMEM; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node, area->caller); } else { area->pages = kmalloc_node_noprof(array_size, nested_gfp, node); } if (!area->pages) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocated page array size %lu", nr_small_pages * PAGE_SIZE, array_size); free_vm_area(area); return NULL; } set_vm_area_page_order(area, page_shift - PAGE_SHIFT); page_order = vm_area_page_order(area); /* * High-order nofail allocations are really expensive and * potentially dangerous (pre-mature OOM, disruptive reclaim * and compaction etc. * * Please note, the __vmalloc_node_range_noprof() falls-back * to order-0 pages if high-order attempt is unsuccessful. */ area->nr_pages = vm_area_alloc_pages((page_order ? gfp_mask & ~__GFP_NOFAIL : gfp_mask) | __GFP_NOWARN, node, page_order, nr_small_pages, area->pages); atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (gfp_mask & __GFP_ACCOUNT) { int i; for (i = 0; i < area->nr_pages; i++) mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1); } /* * If not enough pages were obtained to accomplish an * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { /* * vm_area_alloc_pages() can fail due to insufficient memory but * also:- * * - a pending fatal signal * - insufficient huge page-order pages * * Since we always retry allocations at order-0 in the huge page * case a warning for either is spurious. */ if (!fatal_signal_pending(current) && page_order == 0) warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocate pages", area->nr_pages * PAGE_SIZE); goto fail; } /* * page tables allocations ignore external gfp mask, enforce it * by the scope API */ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) flags = memalloc_nofs_save(); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) flags = memalloc_noio_save(); do { ret = vmap_pages_range(addr, addr + size, prot, area->pages, page_shift); if (nofail && (ret < 0)) schedule_timeout_uninterruptible(1); } while (nofail && (ret < 0)); if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) memalloc_nofs_restore(flags); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) memalloc_noio_restore(flags); if (ret < 0) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to map pages", area->nr_pages * PAGE_SIZE); goto fail; } return area->addr; fail: vfree(area->addr); return NULL; } /** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @start: vm area range start * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Please note that the full set of gfp * flags are not supported. GFP_KERNEL, GFP_NOFS and GFP_NOIO are all * supported. * Zone modifiers are not supported. From the reclaim modifiers * __GFP_DIRECT_RECLAIM is required (aka GFP_NOWAIT is not supported) * and only __GFP_NOFAIL is supported (i.e. __GFP_NORETRY and * __GFP_RETRY_MAYFAIL are not supported). * * __GFP_NOWARN can be used to suppress failures messages. * * Map them into contiguous kernel virtual space, using a pagetable * protection of @prot. * * Return: the address of the area or %NULL on failure */ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) { struct vm_struct *area; void *ret; kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE; unsigned long original_align = align; unsigned int shift = PAGE_SHIFT; if (WARN_ON_ONCE(!size)) return NULL; if ((size >> PAGE_SHIFT) > totalram_pages()) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, exceeds total pages", size); return NULL; } if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { /* * Try huge pages. Only try for PAGE_KERNEL allocations, * others like modules don't yet expect huge pages in * their allocations due to apply_to_page_range not * supporting them. */ if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE) shift = PMD_SHIFT; else shift = arch_vmap_pte_supported_shift(size); align = max(original_align, 1UL << shift); } again: area = __get_vm_area_node(size, align, shift, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) { bool nofail = gfp_mask & __GFP_NOFAIL; warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, vm_struct allocation failed%s", size, (nofail) ? ". Retrying." : ""); if (nofail) { schedule_timeout_uninterruptible(1); goto again; } goto fail; } /* * Prepare arguments for __vmalloc_area_node() and * kasan_unpoison_vmalloc(). */ if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) { if (kasan_hw_tags_enabled()) { /* * Modify protection bits to allow tagging. * This must be done before mapping. */ prot = arch_vmap_pgprot_tagged(prot); /* * Skip page_alloc poisoning and zeroing for physical * pages backing VM_ALLOC mapping. Memory is instead * poisoned and zeroed by kasan_unpoison_vmalloc(). */ gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO; } /* Take note that the mapping is PAGE_KERNEL. */ kasan_flags |= KASAN_VMALLOC_PROT_NORMAL; } /* Allocate physical pages and map them into vmalloc space. */ ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node); if (!ret) goto fail; /* * Mark the pages as accessible, now that they are mapped. * The condition for setting KASAN_VMALLOC_INIT should complement the * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check * to make sure that memory is initialized under the same conditions. * Tag-based KASAN modes only assign tags to normal non-executable * allocations, see __kasan_unpoison_vmalloc(). */ kasan_flags |= KASAN_VMALLOC_VM_ALLOC; if (!want_init_on_free() && want_init_on_alloc(gfp_mask) && (gfp_mask & __GFP_SKIP_ZERO)) kasan_flags |= KASAN_VMALLOC_INIT; /* KASAN_VMALLOC_PROT_NORMAL already set if required. */ area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags); /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. * Now, it is fully initialized, so remove this flag here. */ clear_vm_uninitialized_flag(area); if (!(vm_flags & VM_DEFER_KMEMLEAK)) kmemleak_vmalloc(area, PAGE_ALIGN(size), gfp_mask); return area->addr; fail: if (shift > PAGE_SHIFT) { shift = PAGE_SHIFT; align = original_align; goto again; } return NULL; } /** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported * * Any use of gfp flags outside of GFP_KERNEL should be consulted * with mm people. * * Return: pointer to the allocated memory or %NULL on error */ void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, 0, node, caller); } /* * This is only for performance analysis of vmalloc and stress purpose. * It is required by vmalloc test module, therefore do not use it other * than that. */ #ifdef CONFIG_TEST_VMALLOC_MODULE EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); #endif void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc_noprof); /** * vmalloc - allocate virtually contiguous memory * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_noprof); /** * vmalloc_huge - allocate virtually contiguous memory, allow huge pages * @size: allocation size * @gfp_mask: flags for the page level allocator * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * If @size is greater than or equal to PMD_SIZE, allow using * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(vmalloc_huge_noprof); /** * vzalloc - allocate virtually contiguous memory with zero fill * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_noprof); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size * * The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_user_noprof); /** * vmalloc_node - allocate memory on a specific node * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node_noprof); /** * vzalloc_node - allocate memory on a specific node with zero fill * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_node_noprof); /** * vrealloc - reallocate virtually contiguous memory; contents remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate * @flags: the flags for the page level allocator * * If @p is %NULL, vrealloc() behaves exactly like vmalloc(). If @size is 0 and * @p is not a %NULL pointer, the object pointed to is freed. * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. * * This function must not be called concurrently with itself or vfree() for the * same memory allocation. * * Return: pointer to the allocated memory; %NULL if @size is zero or in case of * failure */ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) { size_t old_size = 0; void *n; if (!size) { vfree(p); return NULL; } if (p) { struct vm_struct *vm; vm = find_vm_area(p); if (unlikely(!vm)) { WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL; } old_size = get_vm_area_size(vm); } /* * TODO: Shrink the vm_area, i.e. unmap and free unused pages. What * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { /* Zero out spare memory. */ if (want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); kasan_poison_vmalloc(p + size, old_size - size); kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL); return (void *)p; } /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ n = __vmalloc_noprof(size, flags); if (!n) return NULL; if (p) { memcpy(n, p, old_size); vfree(p); } return n; } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) #else /* * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone. */ #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #endif /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_noprof); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size * * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_user_noprof); /* * Atomically zero bytes in the iterator. * * Returns the number of zeroed bytes. */ static size_t zero_iter(struct iov_iter *iter, size_t count) { size_t remains = count; while (remains > 0) { size_t num, copied; num = min_t(size_t, remains, PAGE_SIZE); copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter); remains -= copied; if (copied < num) break; } return count - remains; } /* * small helper routine, copy contents to iter from addr. * If the page is not present, fill zero. * * Returns the number of copied bytes. */ static size_t aligned_vread_iter(struct iov_iter *iter, const char *addr, size_t count) { size_t remains = count; struct page *page; while (remains > 0) { unsigned long offset, length; size_t copied = 0; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > remains) length = remains; page = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need lock. But * adding lock here means that we need to add overhead of * vmalloc()/vfree() calls for this _debug_ interface, rarely * used. Instead of that, we'll use an local mapping via * copy_page_to_iter_nofault() and accept a small overhead in * this access function. */ if (page) copied = copy_page_to_iter_nofault(page, offset, length, iter); else copied = zero_iter(iter, length); addr += copied; remains -= copied; if (copied != length) break; } return count - remains; } /* * Read from a vm_map_ram region of memory. * * Returns the number of copied bytes. */ static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, size_t count, unsigned long flags) { char *start; struct vmap_block *vb; struct xarray *xa; unsigned long offset; unsigned int rs, re; size_t remains, n; /* * If it's area created by vm_map_ram() interface directly, but * not further subdividing and delegating management to vmap_block, * handle it here. */ if (!(flags & VMAP_BLOCK)) return aligned_vread_iter(iter, addr, count); remains = count; /* * Area is split into regions and tracked with vmap_block, read out * each region and zero fill the hole between regions. */ xa = addr_to_vb_xa((unsigned long) addr); vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr)); if (!vb) goto finished_zero; spin_lock(&vb->lock); if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) { spin_unlock(&vb->lock); goto finished_zero; } for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) { size_t copied; if (remains == 0) goto finished; start = vmap_block_vaddr(vb->va->va_start, rs); if (addr < start) { size_t to_zero = min_t(size_t, start - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } /*it could start reading from the middle of used region*/ offset = offset_in_page(addr); n = ((re - rs + 1) << PAGE_SHIFT) - offset; if (n > remains) n = remains; copied = aligned_vread_iter(iter, start + offset, n); addr += copied; remains -= copied; if (copied != n) goto finished; } spin_unlock(&vb->lock); finished_zero: /* zero-fill the left dirty or free regions */ return count - remains + zero_iter(iter, remains); finished: /* We couldn't copy/zero everything */ spin_unlock(&vb->lock); return count - remains; } /** * vread_iter() - read vmalloc area in a safe way to an iterator. * @iter: the iterator to which data should be written. * @addr: vm address. * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from that area to a given buffer. If the given memory range * of [addr...addr+count) includes some valid address, data is copied to * proper area of @buf. If there are memory holes, they'll be zero-filled. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any information, as /proc/kcore. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *vm; char *vaddr; size_t n, size, flags, remains; unsigned long next; addr = kasan_reset_tag(addr); /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; remains = count; vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va); if (!vn) goto finished_zero; /* no intersects with alive vmap_area */ if ((unsigned long)addr + remains <= va->va_start) goto finished_zero; do { size_t copied; if (remains == 0) goto finished; vm = va->vm; flags = va->flags & VMAP_FLAGS_MASK; /* * VMAP_BLOCK indicates a sub-type of vm_map_ram area, need * be set together with VMAP_RAM. */ WARN_ON(flags == VMAP_BLOCK); if (!vm && !flags) goto next_va; if (vm && (vm->flags & VM_UNINITIALIZED)) goto next_va; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); vaddr = (char *) va->va_start; size = vm ? get_vm_area_size(vm) : va_size(va); if (addr >= vaddr + size) goto next_va; if (addr < vaddr) { size_t to_zero = min_t(size_t, vaddr - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } n = vaddr + size - addr; if (n > remains) n = remains; if (flags & VMAP_RAM) copied = vmap_ram_vread_iter(iter, addr, n, flags); else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE)))) copied = aligned_vread_iter(iter, addr, n); else /* IOREMAP | SPARSE area is treated as memory hole */ copied = zero_iter(iter, n); addr += copied; remains -= copied; if (copied != n) goto finished; next_va: next = va->va_end; spin_unlock(&vn->busy.lock); } while ((vn = find_vmap_area_exceed_addr_lock(next, &va))); finished_zero: if (vn) spin_unlock(&vn->busy.lock); /* zero-fill memory holes */ return count - remains + zero_iter(iter, remains); finished: /* Nothing remains, or We couldn't copy/zero everything. */ if (vn) spin_unlock(&vn->busy.lock); return count - remains; } /** * remap_vmalloc_range_partial - map vmalloc pages to userspace * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory * @pgoff: offset from @kaddr to start at * @size: size of map area * * Returns: 0 for success, -Exxx on failure * * This function checks that @kaddr is a valid vmalloc'ed area, * and that it is big enough to cover the range starting at * @uaddr in @vma. Will return failure if that criteria isn't * met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size) { struct vm_struct *area; unsigned long off; unsigned long end_index; if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) return -EINVAL; size = PAGE_ALIGN(size); if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) return -EINVAL; area = find_vm_area(kaddr); if (!area) return -EINVAL; if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT))) return -EINVAL; if (check_add_overflow(size, off, &end_index) || end_index > get_vm_area_size(area)) return -EINVAL; kaddr += off; do { struct page *page = vmalloc_to_page(kaddr); int ret; ret = vm_insert_page(vma, uaddr, page); if (ret) return ret; uaddr += PAGE_SIZE; kaddr += PAGE_SIZE; size -= PAGE_SIZE; } while (size > 0); vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); return 0; } /** * remap_vmalloc_range - map vmalloc pages to userspace * @vma: vma to cover (map full range of vma) * @addr: vmalloc memory * @pgoff: number of pages into addr before first page to map * * Returns: 0 for success, -Exxx on failure * * This function checks that addr is a valid vmalloc'ed area, and * that it is big enough to cover the vma. Will return failure if * that criteria isn't met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, addr, pgoff, vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range); void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; ret = remove_vm_area(area->addr); BUG_ON(ret != area); kfree(area); } EXPORT_SYMBOL_GPL(free_vm_area); #ifdef CONFIG_SMP static struct vmap_area *node_to_va(struct rb_node *n) { return rb_entry_safe(n, struct vmap_area, rb_node); } /** * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to * @addr: target address * * Returns: vmap_area if it is found. If there is no such area * the first highest(reverse order) vmap_area is returned * i.e. va->va_start < addr && va->va_end < addr or NULL * if there are no any areas before @addr. */ static struct vmap_area * pvm_find_va_enclose_addr(unsigned long addr) { struct vmap_area *va, *tmp; struct rb_node *n; n = free_vmap_area_root.rb_node; va = NULL; while (n) { tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_start <= addr) { va = tmp; if (tmp->va_end >= addr) break; n = n->rb_right; } else { n = n->rb_left; } } return va; } /** * pvm_determine_end_from_reverse - find the highest aligned address * of free block below VMALLOC_END * @va: * in - the VA we start the search(reverse order); * out - the VA with the highest aligned end address. * @align: alignment for required highest address * * Returns: determined end address within vmap_area */ static unsigned long pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align) { unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); unsigned long addr; if (likely(*va)) { list_for_each_entry_from_reverse((*va), &free_vmap_area_list, list) { addr = min((*va)->va_end & ~(align - 1), vmalloc_end); if ((*va)->va_start < addr) return addr; } } return 0; } /** * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator * @offsets: array containing offset of each area * @sizes: array containing size of each area * @nr_vms: the number of areas to allocate * @align: alignment, all entries in @offsets and @sizes must be aligned to this * * Returns: kmalloc'd vm_struct pointer array pointing to allocated * vm_structs on success, %NULL on failure * * Percpu allocator wants to use congruent vm areas so that it can * maintain the offsets among percpu areas. This function allocates * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to * be scattered pretty far, distance between two areas easily going up * to gigabytes. To avoid interacting with regular vmallocs, these * areas are allocated from top. * * Despite its complicated look, this allocator is rather simple. It * does everything top-down and scans free blocks from the end looking * for matching base. While scanning, if any of the areas do not fit the * base address is pulled down to fit the area. Scanning is repeated till * all the areas fit and then all necessary data structures are inserted * and the result is returned. */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); struct vmap_area **vas, *va; struct vm_struct **vms; int area, area2, last_area, term_area; unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !is_power_of_2(align)); for (last_area = 0, area = 0; area < nr_vms; area++) { start = offsets[area]; end = start + sizes[area]; /* is everything aligned properly? */ BUG_ON(!IS_ALIGNED(offsets[area], align)); BUG_ON(!IS_ALIGNED(sizes[area], align)); /* detect the area with the highest address */ if (start > offsets[last_area]) last_area = area; for (area2 = area + 1; area2 < nr_vms; area2++) { unsigned long start2 = offsets[area2]; unsigned long end2 = start2 + sizes[area2]; BUG_ON(start2 < end && start < end2); } } last_end = offsets[last_area] + sizes[last_area]; if (vmalloc_end - vmalloc_start < last_end) { WARN_ON(true); return NULL; } vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL); vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL); if (!vas || !vms) goto err_free2; for (area = 0; area < nr_vms; area++) { vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL); vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); if (!vas[area] || !vms[area]) goto err_free; } retry: spin_lock(&free_vmap_area_lock); /* start scanning - we scan from the top, begin with the last area */ area = term_area = last_area; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(vmalloc_end); base = pvm_determine_end_from_reverse(&va, align) - end; while (true) { /* * base might have underflowed, add last_end before * comparing. */ if (base + last_end < vmalloc_start + last_end) goto overflow; /* * Fitting base has not been found. */ if (va == NULL) goto overflow; /* * If required width exceeds current VA block, move * base downwards and then recheck. */ if (base + end > va->va_end) { base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * If this VA does not fit, move base downwards and recheck. */ if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * This area fits, move on to the previous one. If * the previous one is the terminal one, we're done. */ area = (area + nr_vms - 1) % nr_vms; if (area == term_area) break; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(base + end); } /* we've found a fitting base, insert all va's */ for (area = 0; area < nr_vms; area++) { int ret; start = base + offsets[area]; size = sizes[area]; va = pvm_find_va_enclose_addr(start); if (WARN_ON_ONCE(va == NULL)) /* It is a BUG(), but trigger recovery instead. */ goto recovery; ret = va_clip(&free_vmap_area_root, &free_vmap_area_list, va, start, size); if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery; /* Allocated area. */ va = vas[area]; va->va_start = start; va->va_end = start + size; } spin_unlock(&free_vmap_area_lock); /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) goto err_free_shadow; } /* insert all vm's */ for (area = 0; area < nr_vms; area++) { struct vmap_node *vn = addr_to_node(vas[area]->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); spin_unlock(&vn->busy.lock); } /* * Mark allocated areas as accessible. Do it now as a best-effort * approach, as they can be mapped outside of vmalloc code. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ for (area = 0; area < nr_vms; area++) vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr, vms[area]->size, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; recovery: /* * Remove previously allocated areas. There is no * need in removing these areas from the busy tree, * because they are inserted only on the final step * and when pcpu_get_vm_areas() is success. */ while (area--) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end, KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; } overflow: spin_unlock(&free_vmap_area_lock); if (!purged) { reclaim_and_purge_vmap_areas(); purged = true; /* Before "retry", check if we recover. */ for (area = 0; area < nr_vms; area++) { if (vas[area]) continue; vas[area] = kmem_cache_zalloc( vmap_area_cachep, GFP_KERNEL); if (!vas[area]) goto err_free; } goto retry; } err_free: for (area = 0; area < nr_vms; area++) { if (vas[area]) kmem_cache_free(vmap_area_cachep, vas[area]); kfree(vms[area]); } err_free2: kfree(vas); kfree(vms); return NULL; err_free_shadow: spin_lock(&free_vmap_area_lock); /* * We release all the vmalloc shadows, even the ones for regions that * hadn't been successfully added. This relies on kasan_release_vmalloc * being able to tolerate this case. */ for (area = 0; area < nr_vms; area++) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end, KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; kfree(vms[area]); } spin_unlock(&free_vmap_area_lock); kfree(vas); kfree(vms); return NULL; } /** * pcpu_free_vm_areas - free vmalloc areas for percpu allocator * @vms: vm_struct pointer array returned by pcpu_get_vm_areas() * @nr_vms: the number of allocated areas * * Free vm_structs and the array allocated by pcpu_get_vm_areas(). */ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) { int i; for (i = 0; i < nr_vms; i++) free_vm_area(vms[i]); kfree(vms); } #endif /* CONFIG_SMP */ #ifdef CONFIG_PRINTK bool vmalloc_dump_obj(void *object) { const void *caller; struct vm_struct *vm; struct vmap_area *va; struct vmap_node *vn; unsigned long addr; unsigned int nr_pages; addr = PAGE_ALIGN((unsigned long) object); vn = addr_to_node(addr); if (!spin_trylock(&vn->busy.lock)) return false; va = __find_vmap_area(addr, &vn->busy.root); if (!va || !va->vm) { spin_unlock(&vn->busy.lock); return false; } vm = va->vm; addr = (unsigned long) vm->addr; caller = vm->caller; nr_pages = vm->nr_pages; spin_unlock(&vn->busy.lock); pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", nr_pages, addr, caller); return true; } #endif #ifdef CONFIG_PROC_FS static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { unsigned int nr, *counters = m->private; unsigned int step = 1U << vm_area_page_order(v); if (!counters) return; if (v->flags & VM_UNINITIALIZED) return; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr += step) counters[page_to_nid(v->pages[nr])] += step; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); } } static void show_purge_info(struct seq_file *m) { struct vmap_node *vn; struct vmap_area *va; int i; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->lazy.lock); list_for_each_entry(va, &vn->lazy.head, list) { seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", (void *)va->va_start, (void *)va->va_end, va_size(va)); } spin_unlock(&vn->lazy.lock); } } static int vmalloc_info_show(struct seq_file *m, void *p) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *v; int i; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); list_for_each_entry(va, &vn->busy.head, list) { if (!va->vm) { if (va->flags & VMAP_RAM) seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, va_size(va)); continue; } v = va->vm; seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); if (v->caller) seq_printf(m, " %pS", v->caller); if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) seq_printf(m, " phys=%pa", &v->phys_addr); if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); if (v->flags & VM_SPARSE) seq_puts(m, " sparse"); if (v->flags & VM_ALLOC) seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) seq_puts(m, " user"); if (v->flags & VM_DMA_COHERENT) seq_puts(m, " dma-coherent"); if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); show_numa_info(m, v); seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); } /* * As a final step, dump "unpurged" areas. */ show_purge_info(m); return 0; } static int __init proc_vmalloc_init(void) { void *priv_data = NULL; if (IS_ENABLED(CONFIG_NUMA)) priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); proc_create_single_data("vmallocinfo", 0400, NULL, vmalloc_info_show, priv_data); return 0; } module_init(proc_vmalloc_init); #endif static void __init vmap_init_free_space(void) { unsigned long vmap_start = 1; const unsigned long vmap_end = ULONG_MAX; struct vmap_area *free; struct vm_struct *busy; /* * B F B B B F * -|-----|.....|-----|-----|-----|.....|- * | The KVA space | * |<--------------------------------->| */ for (busy = vmlist; busy; busy = busy->next) { if ((unsigned long) busy->addr - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = (unsigned long) busy->addr; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } vmap_start = (unsigned long) busy->addr + busy->size; } if (vmap_end - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = vmap_end; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } } static void vmap_init_nodes(void) { struct vmap_node *vn; int i, n; #if BITS_PER_LONG == 64 /* * A high threshold of max nodes is fixed and bound to 128, * thus a scale factor is 1 for systems where number of cores * are less or equal to specified threshold. * * As for NUMA-aware notes. For bigger systems, for example * NUMA with multi-sockets, where we can end-up with thousands * of cores in total, a "sub-numa-clustering" should be added. * * In this case a NUMA domain is considered as a single entity * with dedicated sub-nodes in it which describe one group or * set of cores. Therefore a per-domain purging is supposed to * be added as well as a per-domain balancing. */ n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); if (n > 1) { vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN); if (vn) { /* Node partition is 16 pages. */ vmap_zone_size = (1 << 4) * PAGE_SIZE; nr_vmap_nodes = n; vmap_nodes = vn; } else { pr_err("Failed to allocate an array. Disable a node layer\n"); } } #endif for (n = 0; n < nr_vmap_nodes; n++) { vn = &vmap_nodes[n]; vn->busy.root = RB_ROOT; INIT_LIST_HEAD(&vn->busy.head); spin_lock_init(&vn->busy.lock); vn->lazy.root = RB_ROOT; INIT_LIST_HEAD(&vn->lazy.head); spin_lock_init(&vn->lazy.lock); for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { INIT_LIST_HEAD(&vn->pool[i].head); WRITE_ONCE(vn->pool[i].len, 0); } spin_lock_init(&vn->pool_lock); } } static unsigned long vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count; struct vmap_node *vn; int i, j; for (count = 0, i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; for (j = 0; j < MAX_VA_SIZE_PAGES; j++) count += READ_ONCE(vn->pool[j].len); } return count ? count : SHRINK_EMPTY; } static unsigned long vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { int i; for (i = 0; i < nr_vmap_nodes; i++) decay_va_pool_node(&vmap_nodes[i], true); return SHRINK_STOP; } void __init vmalloc_init(void) { struct shrinker *vmap_node_shrinker; struct vmap_area *va; struct vmap_node *vn; struct vm_struct *tmp; int i; /* * Create the cache for vmap_area objects. */ vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); for_each_possible_cpu(i) { struct vmap_block_queue *vbq; struct vfree_deferred *p; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); p = &per_cpu(vfree_deferred, i); init_llist_head(&p->list); INIT_WORK(&p->wq, delayed_vfree_work); xa_init(&vbq->vmap_blocks); } /* * Setup nodes before importing vmlist. */ vmap_init_nodes(); /* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (WARN_ON_ONCE(!va)) continue; va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; va->vm = tmp; vn = addr_to_node(va->va_start); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); } /* * Now we can initialize a free vmap space. */ vmap_init_free_space(); vmap_initialized = true; vmap_node_shrinker = shrinker_alloc(0, "vmap-node"); if (!vmap_node_shrinker) { pr_err("Failed to allocate vmap-node shrinker!\n"); return; } vmap_node_shrinker->count_objects = vmap_node_shrink_count; vmap_node_shrinker->scan_objects = vmap_node_shrink_scan; shrinker_register(vmap_node_shrinker); } |
| 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007 * * Author: Eric Biederman <ebiederm@xmision.com> */ #include <linux/module.h> #include <linux/ipc.h> #include <linux/nsproxy.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/ipc_namespace.h> #include <linux/msg.h> #include <linux/slab.h> #include <linux/cred.h> #include "util.h" static int proc_ipc_dointvec_minmax_orphans(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ipc_namespace *ns = container_of(table->data, struct ipc_namespace, shm_rmid_forced); int err; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (err < 0) return err; if (ns->shm_rmid_forced) shm_destroy_orphaned(ns); return err; } static int proc_ipc_auto_msgmni(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; int dummy = 0; memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = &dummy; if (write) pr_info_once("writing to auto_msgmni has no effect"); return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); } static int proc_ipc_sem_dointvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ipc_namespace *ns = container_of(table->data, struct ipc_namespace, sem_ctls); int ret, semmni; semmni = ns->sem_ctls[3]; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret) ret = sem_check_semmni(ns); /* * Reset the semmni value if an error happens. */ if (ret) ns->sem_ctls[3] = semmni; return ret; } int ipc_mni = IPCMNI; int ipc_mni_shift = IPCMNI_SHIFT; int ipc_min_cycle = RADIX_TREE_MAP_SIZE; static const struct ctl_table ipc_sysctls[] = { { .procname = "shmmax", .data = &init_ipc_ns.shm_ctlmax, .maxlen = sizeof(init_ipc_ns.shm_ctlmax), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "shmall", .data = &init_ipc_ns.shm_ctlall, .maxlen = sizeof(init_ipc_ns.shm_ctlall), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "shmmni", .data = &init_ipc_ns.shm_ctlmni, .maxlen = sizeof(init_ipc_ns.shm_ctlmni), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &ipc_mni, }, { .procname = "shm_rmid_forced", .data = &init_ipc_ns.shm_rmid_forced, .maxlen = sizeof(init_ipc_ns.shm_rmid_forced), .mode = 0644, .proc_handler = proc_ipc_dointvec_minmax_orphans, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "msgmax", .data = &init_ipc_ns.msg_ctlmax, .maxlen = sizeof(init_ipc_ns.msg_ctlmax), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, { .procname = "msgmni", .data = &init_ipc_ns.msg_ctlmni, .maxlen = sizeof(init_ipc_ns.msg_ctlmni), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &ipc_mni, }, { .procname = "auto_msgmni", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_ipc_auto_msgmni, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "msgmnb", .data = &init_ipc_ns.msg_ctlmnb, .maxlen = sizeof(init_ipc_ns.msg_ctlmnb), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, { .procname = "sem", .data = &init_ipc_ns.sem_ctls, .maxlen = 4*sizeof(int), .mode = 0644, .proc_handler = proc_ipc_sem_dointvec, }, #ifdef CONFIG_CHECKPOINT_RESTORE { .procname = "sem_next_id", .data = &init_ipc_ns.ids[IPC_SEM_IDS].next_id, .maxlen = sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id), .mode = 0444, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, { .procname = "msg_next_id", .data = &init_ipc_ns.ids[IPC_MSG_IDS].next_id, .maxlen = sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id), .mode = 0444, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, { .procname = "shm_next_id", .data = &init_ipc_ns.ids[IPC_SHM_IDS].next_id, .maxlen = sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id), .mode = 0444, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, #endif }; static struct ctl_table_set *set_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->ipc_ns->ipc_set; } static int set_is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->ipc_ns->ipc_set == set; } static void ipc_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct ipc_namespace *ns = container_of(head->set, struct ipc_namespace, ipc_set); kuid_t ns_root_uid = make_kuid(ns->user_ns, 0); kgid_t ns_root_gid = make_kgid(ns->user_ns, 0); *uid = uid_valid(ns_root_uid) ? ns_root_uid : GLOBAL_ROOT_UID; *gid = gid_valid(ns_root_gid) ? ns_root_gid : GLOBAL_ROOT_GID; } static int ipc_permissions(struct ctl_table_header *head, const struct ctl_table *table) { int mode = table->mode; #ifdef CONFIG_CHECKPOINT_RESTORE struct ipc_namespace *ns = container_of(head->set, struct ipc_namespace, ipc_set); if (((table->data == &ns->ids[IPC_SEM_IDS].next_id) || (table->data == &ns->ids[IPC_MSG_IDS].next_id) || (table->data == &ns->ids[IPC_SHM_IDS].next_id)) && checkpoint_restore_ns_capable(ns->user_ns)) mode = 0666; else #endif { kuid_t ns_root_uid; kgid_t ns_root_gid; ipc_set_ownership(head, &ns_root_uid, &ns_root_gid); if (uid_eq(current_euid(), ns_root_uid)) mode >>= 6; else if (in_egroup_p(ns_root_gid)) mode >>= 3; } mode &= 7; return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = ipc_permissions, .set_ownership = ipc_set_ownership, }; bool setup_ipc_sysctls(struct ipc_namespace *ns) { struct ctl_table *tbl; setup_sysctl_set(&ns->ipc_set, &set_root, set_is_seen); tbl = kmemdup(ipc_sysctls, sizeof(ipc_sysctls), GFP_KERNEL); if (tbl) { int i; for (i = 0; i < ARRAY_SIZE(ipc_sysctls); i++) { if (tbl[i].data == &init_ipc_ns.shm_ctlmax) tbl[i].data = &ns->shm_ctlmax; else if (tbl[i].data == &init_ipc_ns.shm_ctlall) tbl[i].data = &ns->shm_ctlall; else if (tbl[i].data == &init_ipc_ns.shm_ctlmni) tbl[i].data = &ns->shm_ctlmni; else if (tbl[i].data == &init_ipc_ns.shm_rmid_forced) tbl[i].data = &ns->shm_rmid_forced; else if (tbl[i].data == &init_ipc_ns.msg_ctlmax) tbl[i].data = &ns->msg_ctlmax; else if (tbl[i].data == &init_ipc_ns.msg_ctlmni) tbl[i].data = &ns->msg_ctlmni; else if (tbl[i].data == &init_ipc_ns.msg_ctlmnb) tbl[i].data = &ns->msg_ctlmnb; else if (tbl[i].data == &init_ipc_ns.sem_ctls) tbl[i].data = &ns->sem_ctls; #ifdef CONFIG_CHECKPOINT_RESTORE else if (tbl[i].data == &init_ipc_ns.ids[IPC_SEM_IDS].next_id) tbl[i].data = &ns->ids[IPC_SEM_IDS].next_id; else if (tbl[i].data == &init_ipc_ns.ids[IPC_MSG_IDS].next_id) tbl[i].data = &ns->ids[IPC_MSG_IDS].next_id; else if (tbl[i].data == &init_ipc_ns.ids[IPC_SHM_IDS].next_id) tbl[i].data = &ns->ids[IPC_SHM_IDS].next_id; #endif else tbl[i].data = NULL; } ns->ipc_sysctls = __register_sysctl_table(&ns->ipc_set, "kernel", tbl, ARRAY_SIZE(ipc_sysctls)); } if (!ns->ipc_sysctls) { kfree(tbl); retire_sysctl_set(&ns->ipc_set); return false; } return true; } void retire_ipc_sysctls(struct ipc_namespace *ns) { const struct ctl_table *tbl; tbl = ns->ipc_sysctls->ctl_table_arg; unregister_sysctl_table(ns->ipc_sysctls); retire_sysctl_set(&ns->ipc_set); kfree(tbl); } static int __init ipc_sysctl_init(void) { if (!setup_ipc_sysctls(&init_ipc_ns)) { pr_warn("ipc sysctl registration failed\n"); return -ENOMEM; } return 0; } device_initcall(ipc_sysctl_init); static int __init ipc_mni_extend(char *str) { ipc_mni = IPCMNI_EXTEND; ipc_mni_shift = IPCMNI_EXTEND_SHIFT; ipc_min_cycle = IPCMNI_EXTEND_MIN_CYCLE; pr_info("IPCMNI extended to %d.\n", ipc_mni); return 0; } early_param("ipcmni_extend", ipc_mni_extend); |
| 223 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/posix_acl.h (C) 2002 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #ifndef __LINUX_POSIX_ACL_H #define __LINUX_POSIX_ACL_H #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct user_namespace; struct posix_acl_entry { short e_tag; unsigned short e_perm; union { kuid_t e_uid; kgid_t e_gid; }; }; struct posix_acl { /* New members MUST be added within the struct_group() macro below. */ struct_group_tagged(posix_acl_hdr, hdr, refcount_t a_refcount; unsigned int a_count; struct rcu_head a_rcu; ); struct posix_acl_entry a_entries[] __counted_by(a_count); }; static_assert(offsetof(struct posix_acl, a_entries) == sizeof(struct posix_acl_hdr), "struct member likely outside of struct_group_tagged()"); #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) /* * Duplicate an ACL handle. */ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) refcount_inc(&acl->a_refcount); return acl; } /* * Free an ACL handle. */ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(unsigned int count, gfp_t flags); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); int set_posix_acl(struct mnt_idmap *, struct dentry *, int, struct posix_acl *); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); struct posix_acl *posix_acl_clone(const struct posix_acl *acl, gfp_t flags); #ifdef CONFIG_FS_POSIX_ACL int posix_acl_chmod(struct mnt_idmap *, struct dentry *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); int posix_acl_update_mode(struct mnt_idmap *, struct inode *, umode_t *, struct posix_acl **); int simple_set_acl(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); int posix_acl_valid(struct user_namespace *, const struct posix_acl *); int posix_acl_permission(struct mnt_idmap *, struct inode *, const struct posix_acl *, int); static inline void cache_no_acl(struct inode *inode) { inode->i_acl = NULL; inode->i_default_acl = NULL; } int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size); #else static inline int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { return 0; } #define simple_set_acl NULL static inline int simple_acl_create(struct inode *dir, struct inode *inode) { return 0; } static inline void cache_no_acl(struct inode *inode) { } static inline int posix_acl_create(struct inode *inode, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { *default_acl = *acl = NULL; return 0; } static inline void forget_all_cached_acls(struct inode *inode) { } static inline int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *acl) { return -EOPNOTSUPP; } static inline struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ERR_PTR(-EOPNOTSUPP); } static inline int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return -EOPNOTSUPP; } static inline int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size) { return 0; } #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_inode_acl(struct inode *inode, int type); #endif /* __LINUX_POSIX_ACL_H */ |
| 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/ip.h> #include <linux/sctp.h> #include <net/ip.h> #include <net/ip6_checksum.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <net/sctp/checksum.h> #include <net/ip_vs.h> static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); static int sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_service *svc; struct sctp_chunkhdr _schunkh, *sch; struct sctphdr *sh, _sctph; __be16 _ports[2], *ports = NULL; if (likely(!ip_vs_iph_icmp(iph))) { sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); if (sh) { sch = skb_header_pointer(skb, iph->len + sizeof(_sctph), sizeof(_schunkh), &_schunkh); if (sch) { if (sch->type == SCTP_CID_ABORT || !(sysctl_sloppy_sctp(ipvs) || sch->type == SCTP_CID_INIT)) return 1; ports = &sh->source; } } } else { ports = skb_header_pointer( skb, iph->len, sizeof(_ports), &_ports); } if (!ports) { *verdict = NF_DROP; return 0; } if (likely(!ip_vs_iph_inverse(iph))) svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { int ignored; if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( */ *verdict = NF_DROP; return 0; } /* * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) *verdict = ip_vs_leave(svc, skb, pd, iph); else *verdict = NF_DROP; return 0; } } /* NF_ACCEPT */ return 1; } static void sctp_nat_csum(struct sk_buff *skb, struct sctphdr *sctph, unsigned int sctphoff) { sctph->checksum = sctp_compute_cksum(skb, sctphoff); skb->ip_summed = CHECKSUM_UNNECESSARY; } static int sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct sctphdr *sctph; unsigned int sctphoff = iph->len; bool payload_csum = false; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, sctphoff + sizeof(*sctph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!sctp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ ret = ip_vs_app_pkt_out(cp, skb, iph); if (ret == 0) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 2) payload_csum = true; } sctph = (void *) skb_network_header(skb) + sctphoff; /* Only update csum if we really have to */ if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; } return 1; } static int sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct sctphdr *sctph; unsigned int sctphoff = iph->len; bool payload_csum = false; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, sctphoff + sizeof(*sctph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!sctp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ ret = ip_vs_app_pkt_in(cp, skb, iph); if (ret == 0) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 2) payload_csum = true; } sctph = (void *) skb_network_header(skb) + sctphoff; /* Only update csum if we really have to */ if (sctph->dest != cp->dport || payload_csum || (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; } return 1; } static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int sctphoff; struct sctphdr *sh; __le32 cmp, val; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) sctphoff = sizeof(struct ipv6hdr); else #endif sctphoff = ip_hdrlen(skb); sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; val = sctp_compute_cksum(skb, sctphoff); if (val != cmp) { /* CRC failure, dump it. */ IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } return 1; } enum ipvs_sctp_event_t { IP_VS_SCTP_DATA = 0, /* DATA, SACK, HEARTBEATs */ IP_VS_SCTP_INIT, IP_VS_SCTP_INIT_ACK, IP_VS_SCTP_COOKIE_ECHO, IP_VS_SCTP_COOKIE_ACK, IP_VS_SCTP_SHUTDOWN, IP_VS_SCTP_SHUTDOWN_ACK, IP_VS_SCTP_SHUTDOWN_COMPLETE, IP_VS_SCTP_ERROR, IP_VS_SCTP_ABORT, IP_VS_SCTP_EVENT_LAST }; /* RFC 2960, 3.2 Chunk Field Descriptions */ static __u8 sctp_events[] = { [SCTP_CID_DATA] = IP_VS_SCTP_DATA, [SCTP_CID_INIT] = IP_VS_SCTP_INIT, [SCTP_CID_INIT_ACK] = IP_VS_SCTP_INIT_ACK, [SCTP_CID_SACK] = IP_VS_SCTP_DATA, [SCTP_CID_HEARTBEAT] = IP_VS_SCTP_DATA, [SCTP_CID_HEARTBEAT_ACK] = IP_VS_SCTP_DATA, [SCTP_CID_ABORT] = IP_VS_SCTP_ABORT, [SCTP_CID_SHUTDOWN] = IP_VS_SCTP_SHUTDOWN, [SCTP_CID_SHUTDOWN_ACK] = IP_VS_SCTP_SHUTDOWN_ACK, [SCTP_CID_ERROR] = IP_VS_SCTP_ERROR, [SCTP_CID_COOKIE_ECHO] = IP_VS_SCTP_COOKIE_ECHO, [SCTP_CID_COOKIE_ACK] = IP_VS_SCTP_COOKIE_ACK, [SCTP_CID_ECN_ECNE] = IP_VS_SCTP_DATA, [SCTP_CID_ECN_CWR] = IP_VS_SCTP_DATA, [SCTP_CID_SHUTDOWN_COMPLETE] = IP_VS_SCTP_SHUTDOWN_COMPLETE, }; /* SCTP States: * See RFC 2960, 4. SCTP Association State Diagram * * New states (not in diagram): * - INIT1 state: use shorter timeout for dropped INIT packets * - REJECTED state: use shorter timeout if INIT is rejected with ABORT * - INIT, COOKIE_SENT, COOKIE_REPLIED, COOKIE states: for better debugging * * The states are as seen in real server. In the diagram, INIT1, INIT, * COOKIE_SENT and COOKIE_REPLIED processing happens in CLOSED state. * * States as per packets from client (C) and server (S): * * Setup of client connection: * IP_VS_SCTP_S_INIT1: First C:INIT sent, wait for S:INIT-ACK * IP_VS_SCTP_S_INIT: Next C:INIT sent, wait for S:INIT-ACK * IP_VS_SCTP_S_COOKIE_SENT: S:INIT-ACK sent, wait for C:COOKIE-ECHO * IP_VS_SCTP_S_COOKIE_REPLIED: C:COOKIE-ECHO sent, wait for S:COOKIE-ACK * * Setup of server connection: * IP_VS_SCTP_S_COOKIE_WAIT: S:INIT sent, wait for C:INIT-ACK * IP_VS_SCTP_S_COOKIE: C:INIT-ACK sent, wait for S:COOKIE-ECHO * IP_VS_SCTP_S_COOKIE_ECHOED: S:COOKIE-ECHO sent, wait for C:COOKIE-ACK */ #define sNO IP_VS_SCTP_S_NONE #define sI1 IP_VS_SCTP_S_INIT1 #define sIN IP_VS_SCTP_S_INIT #define sCS IP_VS_SCTP_S_COOKIE_SENT #define sCR IP_VS_SCTP_S_COOKIE_REPLIED #define sCW IP_VS_SCTP_S_COOKIE_WAIT #define sCO IP_VS_SCTP_S_COOKIE #define sCE IP_VS_SCTP_S_COOKIE_ECHOED #define sES IP_VS_SCTP_S_ESTABLISHED #define sSS IP_VS_SCTP_S_SHUTDOWN_SENT #define sSR IP_VS_SCTP_S_SHUTDOWN_RECEIVED #define sSA IP_VS_SCTP_S_SHUTDOWN_ACK_SENT #define sRJ IP_VS_SCTP_S_REJECTED #define sCL IP_VS_SCTP_S_CLOSED static const __u8 sctp_states [IP_VS_DIR_LAST][IP_VS_SCTP_EVENT_LAST][IP_VS_SCTP_S_LAST] = { { /* INPUT */ /* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/ /* d */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* i */{sI1, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sIN, sIN}, /* i_a */{sCW, sCW, sCW, sCS, sCR, sCO, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* c_e */{sCR, sIN, sIN, sCR, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* c_a */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sES, sES, sSS, sSR, sSA, sRJ, sCL}, /* s */{sSR, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sSR, sSS, sSR, sSA, sRJ, sCL}, /* s_a */{sCL, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sES, sCL, sSR, sCL, sRJ, sCL}, /* s_c */{sCL, sCL, sCL, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sCL, sRJ, sCL}, /* err */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCL, sES, sSS, sSR, sSA, sRJ, sCL}, /* ab */{sCL, sCL, sCL, sCL, sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, }, { /* OUTPUT */ /* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/ /* d */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* i */{sCW, sCW, sCW, sCW, sCW, sCW, sCW, sCW, sES, sCW, sCW, sCW, sCW, sCW}, /* i_a */{sCS, sCS, sCS, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* c_e */{sCE, sCE, sCE, sCE, sCE, sCE, sCE, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* c_a */{sES, sES, sES, sES, sES, sES, sES, sES, sES, sSS, sSR, sSA, sRJ, sCL}, /* s */{sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSR, sSA, sRJ, sCL}, /* s_a */{sSA, sSA, sSA, sSA, sSA, sCW, sCO, sCE, sES, sSA, sSA, sSA, sRJ, sCL}, /* s_c */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* err */{sCL, sCL, sCL, sCL, sCL, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* ab */{sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, }, { /* INPUT-ONLY */ /* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/ /* d */{sES, sI1, sIN, sCS, sCR, sES, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* i */{sI1, sIN, sIN, sIN, sIN, sIN, sCO, sCE, sES, sSS, sSR, sSA, sIN, sIN}, /* i_a */{sCE, sCE, sCE, sCE, sCE, sCE, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* c_e */{sES, sES, sES, sES, sES, sES, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* c_a */{sES, sI1, sIN, sES, sES, sCW, sES, sES, sES, sSS, sSR, sSA, sRJ, sCL}, /* s */{sSR, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sSR, sSS, sSR, sSA, sRJ, sCL}, /* s_a */{sCL, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sCL, sCL, sSR, sCL, sRJ, sCL}, /* s_c */{sCL, sCL, sCL, sCL, sCL, sCW, sCO, sCE, sES, sSS, sCL, sCL, sRJ, sCL}, /* err */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL}, /* ab */{sCL, sCL, sCL, sCL, sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, }, }; #define IP_VS_SCTP_MAX_RTO ((60 + 1) * HZ) /* Timeout table[state] */ static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = { [IP_VS_SCTP_S_NONE] = 2 * HZ, [IP_VS_SCTP_S_INIT1] = (0 + 3 + 1) * HZ, [IP_VS_SCTP_S_INIT] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_COOKIE_SENT] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_COOKIE_REPLIED] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_COOKIE_WAIT] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_COOKIE] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_COOKIE_ECHOED] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_ESTABLISHED] = 15 * 60 * HZ, [IP_VS_SCTP_S_SHUTDOWN_SENT] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_SHUTDOWN_RECEIVED] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_SHUTDOWN_ACK_SENT] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_REJECTED] = (0 + 3 + 1) * HZ, [IP_VS_SCTP_S_CLOSED] = IP_VS_SCTP_MAX_RTO, [IP_VS_SCTP_S_LAST] = 2 * HZ, }; static const char *sctp_state_name_table[IP_VS_SCTP_S_LAST + 1] = { [IP_VS_SCTP_S_NONE] = "NONE", [IP_VS_SCTP_S_INIT1] = "INIT1", [IP_VS_SCTP_S_INIT] = "INIT", [IP_VS_SCTP_S_COOKIE_SENT] = "C-SENT", [IP_VS_SCTP_S_COOKIE_REPLIED] = "C-REPLIED", [IP_VS_SCTP_S_COOKIE_WAIT] = "C-WAIT", [IP_VS_SCTP_S_COOKIE] = "COOKIE", [IP_VS_SCTP_S_COOKIE_ECHOED] = "C-ECHOED", [IP_VS_SCTP_S_ESTABLISHED] = "ESTABLISHED", [IP_VS_SCTP_S_SHUTDOWN_SENT] = "S-SENT", [IP_VS_SCTP_S_SHUTDOWN_RECEIVED] = "S-RECEIVED", [IP_VS_SCTP_S_SHUTDOWN_ACK_SENT] = "S-ACK-SENT", [IP_VS_SCTP_S_REJECTED] = "REJECTED", [IP_VS_SCTP_S_CLOSED] = "CLOSED", [IP_VS_SCTP_S_LAST] = "BUG!", }; static const char *sctp_state_name(int state) { if (state >= IP_VS_SCTP_S_LAST) return "ERR!"; if (sctp_state_name_table[state]) return sctp_state_name_table[state]; return "?"; } static inline void set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, const struct sk_buff *skb) { struct sctp_chunkhdr _sctpch, *sch; unsigned char chunk_type; int event, next_state; int ihl, cofs; #ifdef CONFIG_IP_VS_IPV6 ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); #else ihl = ip_hdrlen(skb); #endif cofs = ihl + sizeof(struct sctphdr); sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch); if (sch == NULL) return; chunk_type = sch->type; /* * Section 3: Multiple chunks can be bundled into one SCTP packet * up to the MTU size, except for the INIT, INIT ACK, and * SHUTDOWN COMPLETE chunks. These chunks MUST NOT be bundled with * any other chunk in a packet. * * Section 3.3.7: DATA chunks MUST NOT be bundled with ABORT. Control * chunks (except for INIT, INIT ACK, and SHUTDOWN COMPLETE) MAY be * bundled with an ABORT, but they MUST be placed before the ABORT * in the SCTP packet or they will be ignored by the receiver. */ if ((sch->type == SCTP_CID_COOKIE_ECHO) || (sch->type == SCTP_CID_COOKIE_ACK)) { int clen = ntohs(sch->length); if (clen >= sizeof(_sctpch)) { sch = skb_header_pointer(skb, cofs + ALIGN(clen, 4), sizeof(_sctpch), &_sctpch); if (sch && sch->type == SCTP_CID_ABORT) chunk_type = sch->type; } } event = (chunk_type < sizeof(sctp_events)) ? sctp_events[chunk_type] : IP_VS_SCTP_DATA; /* Update direction to INPUT_ONLY if necessary * or delete NO_OUTPUT flag if output packet detected */ if (cp->flags & IP_VS_CONN_F_NOOUTPUT) { if (direction == IP_VS_DIR_OUTPUT) cp->flags &= ~IP_VS_CONN_F_NOOUTPUT; else direction = IP_VS_DIR_INPUT_ONLY; } next_state = sctp_states[direction][event][cp->state]; if (next_state != cp->state) { struct ip_vs_dest *dest = cp->dest; IP_VS_DBG_BUF(8, "%s %s %s:%d->" "%s:%d state: %s->%s conn->refcnt:%d\n", pd->pp->name, ((direction == IP_VS_DIR_OUTPUT) ? "output " : "input "), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), sctp_state_name(cp->state), sctp_state_name(next_state), refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state != IP_VS_SCTP_S_ESTABLISHED)) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state == IP_VS_SCTP_S_ESTABLISHED)) { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } if (next_state == IP_VS_SCTP_S_ESTABLISHED) ip_vs_control_assure_ct(cp); } if (likely(pd)) cp->timeout = pd->timeout_table[cp->state = next_state]; else /* What to do ? */ cp->timeout = sctp_timeouts[cp->state = next_state]; } static void sctp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { spin_lock_bh(&cp->lock); set_sctp_state(pd, cp, direction, skb); spin_unlock_bh(&cp->lock); } static inline __u16 sctp_app_hashkey(__be16 port) { return (((__force u16)port >> SCTP_APP_TAB_BITS) ^ (__force u16)port) & SCTP_APP_TAB_MASK; } static int sctp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP); hash = sctp_app_hashkey(port); list_for_each_entry(i, &ipvs->sctp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } list_add_rcu(&inc->p_list, &ipvs->sctp_apps[hash]); atomic_inc(&pd->appcnt); out: return ret; } static void sctp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); } static int sctp_app_conn_bind(struct ip_vs_conn *cp) { struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; /* Default binding: bind app only for NAT */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) return 0; /* Lookup application incarnations and bind the right one */ hash = sctp_app_hashkey(cp->vport); list_for_each_entry_rcu(inc, &ipvs->sctp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->" "%s:%u to app %s on port %u\n", __func__, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), inc->name, ntohs(inc->port)); cp->app = inc; if (inc->init_conn) result = inc->init_conn(inc, cp); break; } } return result; } /* --------------------------------------------- * timeouts is netns related now. * --------------------------------------------- */ static int __ip_vs_sctp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, sizeof(sctp_timeouts)); if (!pd->timeout_table) return -ENOMEM; return 0; } static void __ip_vs_sctp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } struct ip_vs_protocol ip_vs_protocol_sctp = { .name = "SCTP", .protocol = IPPROTO_SCTP, .num_states = IP_VS_SCTP_S_LAST, .dont_defrag = 0, .init = NULL, .exit = NULL, .init_netns = __ip_vs_sctp_init, .exit_netns = __ip_vs_sctp_exit, .register_app = sctp_register_app, .unregister_app = sctp_unregister_app, .conn_schedule = sctp_conn_schedule, .conn_in_get = ip_vs_conn_in_get_proto, .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = sctp_snat_handler, .dnat_handler = sctp_dnat_handler, .state_name = sctp_state_name, .state_transition = sctp_state_transition, .app_conn_bind = sctp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, }; |
| 7 7 7 7 7 7 3 5 7 7 7 7 7 3 7 7 7 7 7 7 7 7 7 7 7 6 6 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/phy_link_topology.h> #include <linux/ptp_clock_kernel.h> #include <net/netdev_lock.h> #include "netlink.h" #include "common.h" #include "bitset.h" #include "ts.h" struct tsinfo_req_info { struct ethnl_req_info base; struct hwtstamp_provider_desc hwprov_desc; }; struct tsinfo_reply_data { struct ethnl_reply_data base; struct kernel_ethtool_ts_info ts_info; struct ethtool_ts_stats stats; }; #define TSINFO_REQINFO(__req_base) \ container_of(__req_base, struct tsinfo_req_info, base) #define TSINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct tsinfo_reply_data, base) #define ETHTOOL_TS_STAT_CNT \ (__ETHTOOL_A_TS_STAT_CNT - (ETHTOOL_A_TS_STAT_UNSPEC + 1)) const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1] = { [ETHTOOL_A_TSINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), [ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER] = NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), }; int ts_parse_hwtst_provider(const struct nlattr *nest, struct hwtstamp_provider_desc *hwprov_desc, struct netlink_ext_ack *extack, bool *mod) { struct nlattr *tb[ARRAY_SIZE(ethnl_ts_hwtst_prov_policy)]; int ret; ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_ts_hwtst_prov_policy) - 1, nest, ethnl_ts_hwtst_prov_policy, extack); if (ret < 0) return ret; if (NL_REQ_ATTR_CHECK(extack, nest, tb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX) || NL_REQ_ATTR_CHECK(extack, nest, tb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER)) return -EINVAL; ethnl_update_u32(&hwprov_desc->index, tb[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX], mod); ethnl_update_u32(&hwprov_desc->qualifier, tb[ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER], mod); return 0; } static int tsinfo_parse_request(struct ethnl_req_info *req_base, struct nlattr **tb, struct netlink_ext_ack *extack) { struct tsinfo_req_info *req = TSINFO_REQINFO(req_base); bool mod = false; req->hwprov_desc.index = -1; if (!tb[ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER]) return 0; return ts_parse_hwtst_provider(tb[ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER], &req->hwprov_desc, extack, &mod); } static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); struct tsinfo_req_info *req = TSINFO_REQINFO(req_base); struct net_device *dev = reply_base->dev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; if (req->hwprov_desc.index != -1) { ret = ethtool_get_ts_info_by_phc(dev, &data->ts_info, &req->hwprov_desc); ethnl_ops_complete(dev); return ret; } if (req_base->flags & ETHTOOL_FLAG_STATS) { ethtool_stats_init((u64 *)&data->stats, sizeof(data->stats) / sizeof(u64)); if (dev->ethtool_ops->get_ts_stats) dev->ethtool_ops->get_ts_stats(dev, &data->stats); } ret = __ethtool_get_ts_info(dev, &data->ts_info); ethnl_ops_complete(dev); return ret; } static int tsinfo_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct kernel_ethtool_ts_info *ts_info = &data->ts_info; int len = 0; int ret; BUILD_BUG_ON(__SOF_TIMESTAMPING_CNT > 32); BUILD_BUG_ON(__HWTSTAMP_TX_CNT > 32); BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT > 32); if (ts_info->so_timestamping) { ret = ethnl_bitset32_size(&ts_info->so_timestamping, NULL, __SOF_TIMESTAMPING_CNT, sof_timestamping_names, compact); if (ret < 0) return ret; len += ret; /* _TSINFO_TIMESTAMPING */ } if (ts_info->tx_types) { ret = ethnl_bitset32_size(&ts_info->tx_types, NULL, __HWTSTAMP_TX_CNT, ts_tx_type_names, compact); if (ret < 0) return ret; len += ret; /* _TSINFO_TX_TYPES */ } if (ts_info->rx_filters) { ret = ethnl_bitset32_size(&ts_info->rx_filters, NULL, __HWTSTAMP_FILTER_CNT, ts_rx_filter_names, compact); if (ret < 0) return ret; len += ret; /* _TSINFO_RX_FILTERS */ } if (ts_info->phc_index >= 0) { len += nla_total_size(sizeof(u32)); /* _TSINFO_PHC_INDEX */ /* _TSINFO_HWTSTAMP_PROVIDER */ len += nla_total_size(0) + 2 * nla_total_size(sizeof(u32)); } if (req_base->flags & ETHTOOL_FLAG_STATS) len += nla_total_size(0) + /* _TSINFO_STATS */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_TS_STAT_CNT; return len; } static int tsinfo_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) { if (val == ETHTOOL_STAT_NOT_SET) return 0; if (nla_put_uint(skb, attrtype, val)) return -EMSGSIZE; return 0; } static int tsinfo_put_stats(struct sk_buff *skb, const struct ethtool_ts_stats *stats) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_TSINFO_STATS); if (!nest) return -EMSGSIZE; if (tsinfo_put_stat(skb, stats->tx_stats.pkts, ETHTOOL_A_TS_STAT_TX_PKTS) || tsinfo_put_stat(skb, stats->tx_stats.onestep_pkts_unconfirmed, ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED) || tsinfo_put_stat(skb, stats->tx_stats.lost, ETHTOOL_A_TS_STAT_TX_LOST) || tsinfo_put_stat(skb, stats->tx_stats.err, ETHTOOL_A_TS_STAT_TX_ERR)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int tsinfo_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct kernel_ethtool_ts_info *ts_info = &data->ts_info; int ret; if (ts_info->so_timestamping) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSINFO_TIMESTAMPING, &ts_info->so_timestamping, NULL, __SOF_TIMESTAMPING_CNT, sof_timestamping_names, compact); if (ret < 0) return ret; } if (ts_info->tx_types) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSINFO_TX_TYPES, &ts_info->tx_types, NULL, __HWTSTAMP_TX_CNT, ts_tx_type_names, compact); if (ret < 0) return ret; } if (ts_info->rx_filters) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSINFO_RX_FILTERS, &ts_info->rx_filters, NULL, __HWTSTAMP_FILTER_CNT, ts_rx_filter_names, compact); if (ret < 0) return ret; } if (ts_info->phc_index >= 0) { struct nlattr *nest; ret = nla_put_u32(skb, ETHTOOL_A_TSINFO_PHC_INDEX, ts_info->phc_index); if (ret) return -EMSGSIZE; nest = nla_nest_start(skb, ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, ts_info->phc_index) || nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, ts_info->phc_qualifier)) { nla_nest_cancel(skb, nest); return -EMSGSIZE; } nla_nest_end(skb, nest); } if (req_base->flags & ETHTOOL_FLAG_STATS && tsinfo_put_stats(skb, &data->stats)) return -EMSGSIZE; return 0; } struct ethnl_tsinfo_dump_ctx { struct tsinfo_req_info *req_info; struct tsinfo_reply_data *reply_data; unsigned long pos_ifindex; bool netdev_dump_done; unsigned long pos_phyindex; enum hwtstamp_provider_qualifier pos_phcqualifier; }; static void *ethnl_tsinfo_prepare_dump(struct sk_buff *skb, struct net_device *dev, struct tsinfo_reply_data *reply_data, struct netlink_callback *cb) { struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; void *ehdr = NULL; ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_TSINFO_GET_REPLY); if (!ehdr) return ERR_PTR(-EMSGSIZE); reply_data = ctx->reply_data; memset(reply_data, 0, sizeof(*reply_data)); reply_data->base.dev = dev; reply_data->ts_info.cmd = ETHTOOL_GET_TS_INFO; reply_data->ts_info.phc_index = -1; return ehdr; } static int ethnl_tsinfo_end_dump(struct sk_buff *skb, struct net_device *dev, struct tsinfo_req_info *req_info, struct tsinfo_reply_data *reply_data, void *ehdr) { int ret; reply_data->ts_info.so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_TSINFO_HEADER); if (ret < 0) return ret; ret = tsinfo_fill_reply(skb, &req_info->base, &reply_data->base); if (ret < 0) return ret; reply_data->base.dev = NULL; genlmsg_end(skb, ehdr); return ret; } static int ethnl_tsinfo_dump_one_phydev(struct sk_buff *skb, struct net_device *dev, struct phy_device *phydev, struct netlink_callback *cb) { struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; struct tsinfo_reply_data *reply_data; struct tsinfo_req_info *req_info; void *ehdr = NULL; int ret = 0; if (!phy_has_tsinfo(phydev)) return -EOPNOTSUPP; reply_data = ctx->reply_data; req_info = ctx->req_info; ehdr = ethnl_tsinfo_prepare_dump(skb, dev, reply_data, cb); if (IS_ERR(ehdr)) return PTR_ERR(ehdr); ret = phy_ts_info(phydev, &reply_data->ts_info); if (ret < 0) goto err; ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, ehdr); if (ret < 0) goto err; return ret; err: genlmsg_cancel(skb, ehdr); return ret; } static int ethnl_tsinfo_dump_one_netdev(struct sk_buff *skb, struct net_device *dev, struct netlink_callback *cb) { struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; const struct ethtool_ops *ops = dev->ethtool_ops; struct tsinfo_reply_data *reply_data; struct tsinfo_req_info *req_info; void *ehdr = NULL; int ret = 0; if (!ops->get_ts_info) return -EOPNOTSUPP; reply_data = ctx->reply_data; req_info = ctx->req_info; for (; ctx->pos_phcqualifier < HWTSTAMP_PROVIDER_QUALIFIER_CNT; ctx->pos_phcqualifier++) { if (!net_support_hwtstamp_qualifier(dev, ctx->pos_phcqualifier)) continue; ehdr = ethnl_tsinfo_prepare_dump(skb, dev, reply_data, cb); if (IS_ERR(ehdr)) { ret = PTR_ERR(ehdr); goto err; } reply_data->ts_info.phc_qualifier = ctx->pos_phcqualifier; ret = ops->get_ts_info(dev, &reply_data->ts_info); if (ret < 0) goto err; ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, ehdr); if (ret < 0) goto err; } return ret; err: genlmsg_cancel(skb, ehdr); return ret; } static int ethnl_tsinfo_dump_one_net_topo(struct sk_buff *skb, struct net_device *dev, struct netlink_callback *cb) { struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; struct phy_device_node *pdn; int ret = 0; if (!ctx->netdev_dump_done) { ret = ethnl_tsinfo_dump_one_netdev(skb, dev, cb); if (ret < 0 && ret != -EOPNOTSUPP) return ret; ctx->netdev_dump_done = true; } if (!dev->link_topo) { if (phy_has_tsinfo(dev->phydev)) { ret = ethnl_tsinfo_dump_one_phydev(skb, dev, dev->phydev, cb); if (ret < 0 && ret != -EOPNOTSUPP) return ret; } return 0; } xa_for_each_start(&dev->link_topo->phys, ctx->pos_phyindex, pdn, ctx->pos_phyindex) { if (phy_has_tsinfo(pdn->phy)) { ret = ethnl_tsinfo_dump_one_phydev(skb, dev, pdn->phy, cb); if (ret < 0 && ret != -EOPNOTSUPP) return ret; } } return ret; } int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); struct net_device *dev; int ret = 0; rtnl_lock(); if (ctx->req_info->base.dev) { dev = ctx->req_info->base.dev; netdev_lock_ops(dev); ret = ethnl_tsinfo_dump_one_net_topo(skb, dev, cb); netdev_unlock_ops(dev); } else { for_each_netdev_dump(net, dev, ctx->pos_ifindex) { netdev_lock_ops(dev); ret = ethnl_tsinfo_dump_one_net_topo(skb, dev, cb); netdev_unlock_ops(dev); if (ret < 0 && ret != -EOPNOTSUPP) break; ctx->pos_phyindex = 0; ctx->netdev_dump_done = false; ctx->pos_phcqualifier = HWTSTAMP_PROVIDER_QUALIFIER_PRECISE; } } rtnl_unlock(); return ret; } int ethnl_tsinfo_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; struct nlattr **tb = info->info.attrs; struct tsinfo_reply_data *reply_data; struct tsinfo_req_info *req_info; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); req_info = kzalloc(sizeof(*req_info), GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kzalloc(sizeof(*reply_data), GFP_KERNEL); if (!reply_data) { ret = -ENOMEM; goto free_req_info; } ret = ethnl_parse_header_dev_get(&req_info->base, tb[ETHTOOL_A_TSINFO_HEADER], sock_net(cb->skb->sk), cb->extack, false); if (ret < 0) goto free_reply_data; ctx->req_info = req_info; ctx->reply_data = reply_data; ctx->pos_ifindex = 0; ctx->pos_phyindex = 0; ctx->netdev_dump_done = false; ctx->pos_phcqualifier = HWTSTAMP_PROVIDER_QUALIFIER_PRECISE; return 0; free_reply_data: kfree(reply_data); free_req_info: kfree(req_info); return ret; } int ethnl_tsinfo_done(struct netlink_callback *cb) { struct ethnl_tsinfo_dump_ctx *ctx = (void *)cb->ctx; struct tsinfo_req_info *req_info = ctx->req_info; ethnl_parse_header_dev_put(&req_info->base); kfree(ctx->reply_data); kfree(ctx->req_info); return 0; } const struct ethnl_request_ops ethnl_tsinfo_request_ops = { .request_cmd = ETHTOOL_MSG_TSINFO_GET, .reply_cmd = ETHTOOL_MSG_TSINFO_GET_REPLY, .hdr_attr = ETHTOOL_A_TSINFO_HEADER, .req_info_size = sizeof(struct tsinfo_req_info), .reply_data_size = sizeof(struct tsinfo_reply_data), .parse_request = tsinfo_parse_request, .prepare_data = tsinfo_prepare_data, .reply_size = tsinfo_reply_size, .fill_reply = tsinfo_fill_reply, }; |
| 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 | /* * include/linux/ktime.h * * ktime_t - nanosecond-resolution time format. * * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes and macros. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * * Roman Zippel provided the ideas and primary code snippets of * the ktime_t union and further simplifications of the original * code. * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_KTIME_H #define _LINUX_KTIME_H #include <asm/bug.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/types.h> /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value * @secs: seconds to set * @nsecs: nanoseconds to set * * Return: The ktime_t representation of the value. */ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) { if (unlikely(secs >= KTIME_SEC_MAX)) return KTIME_MAX; return secs * NSEC_PER_SEC + (s64)nsecs; } /* Subtract two ktime_t variables. rem = lhs -rhs: */ #define ktime_sub(lhs, rhs) ((lhs) - (rhs)) /* Add two ktime_t variables. res = lhs + rhs: */ #define ktime_add(lhs, rhs) ((lhs) + (rhs)) /* * Same as ktime_add(), but avoids undefined behaviour on overflow; however, * this means that you must check the result for overflow yourself. */ #define ktime_add_unsafe(lhs, rhs) ((u64) (lhs) + (rhs)) /* * Add a ktime_t variable and a scalar nanosecond value. * res = kt + nsval: */ #define ktime_add_ns(kt, nsval) ((kt) + (nsval)) /* * Subtract a scalar nanosecod from a ktime_t variable * res = kt - nsval: */ #define ktime_sub_ns(kt, nsval) ((kt) - (nsval)) /* convert a timespec64 to ktime_t format: */ static inline ktime_t timespec64_to_ktime(struct timespec64 ts) { return ktime_set(ts.tv_sec, ts.tv_nsec); } /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec64(kt) ns_to_timespec64((kt)) /* Convert ktime_t to nanoseconds */ static inline s64 ktime_to_ns(const ktime_t kt) { return kt; } /** * ktime_compare - Compares two ktime_t variables for less, greater or equal * @cmp1: comparable1 * @cmp2: comparable2 * * Return: ... * cmp1 < cmp2: return <0 * cmp1 == cmp2: return 0 * cmp1 > cmp2: return >0 */ static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2) { if (cmp1 < cmp2) return -1; if (cmp1 > cmp2) return 1; return 0; } /** * ktime_after - Compare if a ktime_t value is bigger than another one. * @cmp1: comparable1 * @cmp2: comparable2 * * Return: true if cmp1 happened after cmp2. */ static inline bool ktime_after(const ktime_t cmp1, const ktime_t cmp2) { return ktime_compare(cmp1, cmp2) > 0; } /** * ktime_before - Compare if a ktime_t value is smaller than another one. * @cmp1: comparable1 * @cmp2: comparable2 * * Return: true if cmp1 happened before cmp2. */ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) { return ktime_compare(cmp1, cmp2) < 0; } #if BITS_PER_LONG < 64 extern s64 __ktime_divns(const ktime_t kt, s64 div); static inline s64 ktime_divns(const ktime_t kt, s64 div) { /* * Negative divisors could cause an inf loop, * so bug out here. */ BUG_ON(div < 0); if (__builtin_constant_p(div) && !(div >> 32)) { s64 ns = kt; u64 tmp = ns < 0 ? -ns : ns; do_div(tmp, div); return ns < 0 ? -tmp : tmp; } else { return __ktime_divns(kt, div); } } #else /* BITS_PER_LONG < 64 */ static inline s64 ktime_divns(const ktime_t kt, s64 div) { /* * 32-bit implementation cannot handle negative divisors, * so catch them on 64bit as well. */ WARN_ON(div < 0); return kt / div; } #endif static inline s64 ktime_to_us(const ktime_t kt) { return ktime_divns(kt, NSEC_PER_USEC); } static inline s64 ktime_to_ms(const ktime_t kt) { return ktime_divns(kt, NSEC_PER_MSEC); } static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) { return ktime_to_us(ktime_sub(later, earlier)); } static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier) { return ktime_to_ms(ktime_sub(later, earlier)); } static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) { return ktime_add_ns(kt, usec * NSEC_PER_USEC); } static inline ktime_t ktime_add_ms(const ktime_t kt, const u64 msec) { return ktime_add_ns(kt, msec * NSEC_PER_MSEC); } static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) { return ktime_sub_ns(kt, usec * NSEC_PER_USEC); } static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) { return ktime_sub_ns(kt, msec * NSEC_PER_MSEC); } extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); /** * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 * format only if the variable contains data * @kt: the ktime_t variable to convert * @ts: the timespec variable to store the result in * * Return: %true if there was a successful conversion, %false if kt was 0. */ static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, struct timespec64 *ts) { if (kt) { *ts = ktime_to_timespec64(kt); return true; } else { return false; } } #include <vdso/ktime.h> static inline ktime_t ns_to_ktime(u64 ns) { return ns; } static inline ktime_t us_to_ktime(u64 us) { return us * NSEC_PER_USEC; } static inline ktime_t ms_to_ktime(u64 ms) { return ms * NSEC_PER_MSEC; } # include <linux/timekeeping.h> #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H #include <linux/jump_label.h> #include <linux/psi_types.h> #include <linux/sched.h> #include <linux/poll.h> #include <linux/cgroup-defs.h> #include <linux/cgroup.h> struct seq_file; struct css_set; #ifdef CONFIG_PSI extern struct static_key_false psi_disabled; extern struct psi_group psi_system; void psi_init(void); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, enum psi_res res, struct file *file, struct kernfs_open_file *of); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; } int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} #ifdef CONFIG_CGROUPS static inline int psi_cgroup_alloc(struct cgroup *cgrp) { return 0; } static inline void psi_cgroup_free(struct cgroup *cgrp) { } static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */ |
| 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ppp_deflate.c - interface the zlib procedures for Deflate compression * and decompression (as used by gzip) to the PPP code. * * Copyright 1994-1998 Paul Mackerras. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/string.h> #include <linux/ppp_defs.h> #include <linux/ppp-comp.h> #include <linux/zlib.h> #include <linux/unaligned.h> /* * State for a Deflate (de)compressor. */ struct ppp_deflate_state { int seqno; int w_size; int unit; int mru; int debug; z_stream strm; struct compstat stats; }; #define DEFLATE_OVHD 2 /* Deflate overhead/packet */ static void *z_comp_alloc(unsigned char *options, int opt_len); static void *z_decomp_alloc(unsigned char *options, int opt_len); static void z_comp_free(void *state); static void z_decomp_free(void *state); static int z_comp_init(void *state, unsigned char *options, int opt_len, int unit, int hdrlen, int debug); static int z_decomp_init(void *state, unsigned char *options, int opt_len, int unit, int hdrlen, int mru, int debug); static int z_compress(void *state, unsigned char *rptr, unsigned char *obuf, int isize, int osize); static void z_incomp(void *state, unsigned char *ibuf, int icnt); static int z_decompress(void *state, unsigned char *ibuf, int isize, unsigned char *obuf, int osize); static void z_comp_reset(void *state); static void z_decomp_reset(void *state); static void z_comp_stats(void *state, struct compstat *stats); /** * z_comp_free - free the memory used by a compressor * @arg: pointer to the private state for the compressor. */ static void z_comp_free(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (state) { zlib_deflateEnd(&state->strm); vfree(state->strm.workspace); kfree(state); } } /** * z_comp_alloc - allocate space for a compressor. * @options: pointer to CCP option data * @opt_len: length of the CCP option at @options. * * The @options pointer points to the a buffer containing the * CCP option data for the compression being negotiated. It is * formatted according to RFC1979, and describes the window * size that the peer is requesting that we use in compressing * data to be sent to it. * * Returns the pointer to the private state for the compressor, * or NULL if we could not allocate enough memory. */ static void *z_comp_alloc(unsigned char *options, int opt_len) { struct ppp_deflate_state *state; int w_size; if (opt_len != CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || options[3] != DEFLATE_CHK_SEQUENCE) return NULL; w_size = DEFLATE_SIZE(options[2]); if (w_size < DEFLATE_MIN_SIZE || w_size > DEFLATE_MAX_SIZE) return NULL; state = kzalloc(sizeof(*state), GFP_KERNEL); if (state == NULL) return NULL; state->strm.next_in = NULL; state->w_size = w_size; state->strm.workspace = vmalloc(zlib_deflate_workspacesize(-w_size, 8)); if (state->strm.workspace == NULL) goto out_free; if (zlib_deflateInit2(&state->strm, Z_DEFAULT_COMPRESSION, DEFLATE_METHOD_VAL, -w_size, 8, Z_DEFAULT_STRATEGY) != Z_OK) goto out_free; return (void *) state; out_free: z_comp_free(state); return NULL; } /** * z_comp_init - initialize a previously-allocated compressor. * @arg: pointer to the private state for the compressor * @options: pointer to the CCP option data describing the * compression that was negotiated with the peer * @opt_len: length of the CCP option data at @options * @unit: PPP unit number for diagnostic messages * @hdrlen: ignored (present for backwards compatibility) * @debug: debug flag; if non-zero, debug messages are printed. * * The CCP options described by @options must match the options * specified when the compressor was allocated. The compressor * history is reset. Returns 0 for failure (CCP options don't * match) or 1 for success. */ static int z_comp_init(void *arg, unsigned char *options, int opt_len, int unit, int hdrlen, int debug) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (opt_len < CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || DEFLATE_SIZE(options[2]) != state->w_size || options[3] != DEFLATE_CHK_SEQUENCE) return 0; state->seqno = 0; state->unit = unit; state->debug = debug; zlib_deflateReset(&state->strm); return 1; } /** * z_comp_reset - reset a previously-allocated compressor. * @arg: pointer to private state for the compressor. * * This clears the history for the compressor and makes it * ready to start emitting a new compressed stream. */ static void z_comp_reset(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; state->seqno = 0; zlib_deflateReset(&state->strm); } /** * z_compress - compress a PPP packet with Deflate compression. * @arg: pointer to private state for the compressor * @rptr: uncompressed packet (input) * @obuf: compressed packet (output) * @isize: size of uncompressed packet * @osize: space available at @obuf * * Returns the length of the compressed packet, or 0 if the * packet is incompressible. */ static int z_compress(void *arg, unsigned char *rptr, unsigned char *obuf, int isize, int osize) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; int r, proto, off, olen, oavail; unsigned char *wptr; /* * Check that the protocol is in the range we handle. */ proto = PPP_PROTOCOL(rptr); if (proto > 0x3fff || proto == 0xfd || proto == 0xfb) return 0; /* Don't generate compressed packets which are larger than the uncompressed packet. */ if (osize > isize) osize = isize; wptr = obuf; /* * Copy over the PPP header and store the 2-byte sequence number. */ wptr[0] = PPP_ADDRESS(rptr); wptr[1] = PPP_CONTROL(rptr); put_unaligned_be16(PPP_COMP, wptr + 2); wptr += PPP_HDRLEN; put_unaligned_be16(state->seqno, wptr); wptr += DEFLATE_OVHD; olen = PPP_HDRLEN + DEFLATE_OVHD; state->strm.next_out = wptr; state->strm.avail_out = oavail = osize - olen; ++state->seqno; off = (proto > 0xff) ? 2 : 3; /* skip 1st proto byte if 0 */ rptr += off; state->strm.next_in = rptr; state->strm.avail_in = (isize - off); for (;;) { r = zlib_deflate(&state->strm, Z_PACKET_FLUSH); if (r != Z_OK) { if (state->debug) printk(KERN_ERR "z_compress: deflate returned %d\n", r); break; } if (state->strm.avail_out == 0) { olen += oavail; state->strm.next_out = NULL; state->strm.avail_out = oavail = 1000000; } else { break; /* all done */ } } olen += oavail - state->strm.avail_out; /* * See if we managed to reduce the size of the packet. */ if (olen < isize && olen <= osize) { state->stats.comp_bytes += olen; state->stats.comp_packets++; } else { state->stats.inc_bytes += isize; state->stats.inc_packets++; olen = 0; } state->stats.unc_bytes += isize; state->stats.unc_packets++; return olen; } /** * z_comp_stats - return compression statistics for a compressor * or decompressor. * @arg: pointer to private space for the (de)compressor * @stats: pointer to a struct compstat to receive the result. */ static void z_comp_stats(void *arg, struct compstat *stats) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; *stats = state->stats; } /** * z_decomp_free - Free the memory used by a decompressor. * @arg: pointer to private space for the decompressor. */ static void z_decomp_free(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (state) { vfree(state->strm.workspace); kfree(state); } } /** * z_decomp_alloc - allocate space for a decompressor. * @options: pointer to CCP option data * @opt_len: length of the CCP option at @options. * * The @options pointer points to the a buffer containing the * CCP option data for the compression being negotiated. It is * formatted according to RFC1979, and describes the window * size that we are requesting the peer to use in compressing * data to be sent to us. * * Returns the pointer to the private state for the decompressor, * or NULL if we could not allocate enough memory. */ static void *z_decomp_alloc(unsigned char *options, int opt_len) { struct ppp_deflate_state *state; int w_size; if (opt_len != CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || options[3] != DEFLATE_CHK_SEQUENCE) return NULL; w_size = DEFLATE_SIZE(options[2]); if (w_size < DEFLATE_MIN_SIZE || w_size > DEFLATE_MAX_SIZE) return NULL; state = kzalloc(sizeof(*state), GFP_KERNEL); if (state == NULL) return NULL; state->w_size = w_size; state->strm.next_out = NULL; state->strm.workspace = vmalloc(zlib_inflate_workspacesize()); if (state->strm.workspace == NULL) goto out_free; if (zlib_inflateInit2(&state->strm, -w_size) != Z_OK) goto out_free; return (void *) state; out_free: z_decomp_free(state); return NULL; } /** * z_decomp_init - initialize a previously-allocated decompressor. * @arg: pointer to the private state for the decompressor * @options: pointer to the CCP option data describing the * compression that was negotiated with the peer * @opt_len: length of the CCP option data at @options * @unit: PPP unit number for diagnostic messages * @hdrlen: ignored (present for backwards compatibility) * @mru: maximum length of decompressed packets * @debug: debug flag; if non-zero, debug messages are printed. * * The CCP options described by @options must match the options * specified when the decompressor was allocated. The decompressor * history is reset. Returns 0 for failure (CCP options don't * match) or 1 for success. */ static int z_decomp_init(void *arg, unsigned char *options, int opt_len, int unit, int hdrlen, int mru, int debug) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (opt_len < CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || DEFLATE_SIZE(options[2]) != state->w_size || options[3] != DEFLATE_CHK_SEQUENCE) return 0; state->seqno = 0; state->unit = unit; state->debug = debug; state->mru = mru; zlib_inflateReset(&state->strm); return 1; } /** * z_decomp_reset - reset a previously-allocated decompressor. * @arg: pointer to private state for the decompressor. * * This clears the history for the decompressor and makes it * ready to receive a new compressed stream. */ static void z_decomp_reset(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; state->seqno = 0; zlib_inflateReset(&state->strm); } /** * z_decompress - decompress a Deflate-compressed packet. * @arg: pointer to private state for the decompressor * @ibuf: pointer to input (compressed) packet data * @isize: length of input packet * @obuf: pointer to space for output (decompressed) packet * @osize: amount of space available at @obuf * * Because of patent problems, we return DECOMP_ERROR for errors * found by inspecting the input data and for system problems, but * DECOMP_FATALERROR for any errors which could possibly be said to * be being detected "after" decompression. For DECOMP_ERROR, * we can issue a CCP reset-request; for DECOMP_FATALERROR, we may be * infringing a patent of Motorola's if we do, so we take CCP down * instead. * * Given that the frame has the correct sequence number and a good FCS, * errors such as invalid codes in the input most likely indicate a * bug, so we return DECOMP_FATALERROR for them in order to turn off * compression, even though they are detected by inspecting the input. */ static int z_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, int osize) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; int olen, seq, r; int decode_proto, overflow; unsigned char overflow_buf[1]; if (isize <= PPP_HDRLEN + DEFLATE_OVHD) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: short pkt (%d)\n", state->unit, isize); return DECOMP_ERROR; } /* Check the sequence number. */ seq = get_unaligned_be16(ibuf + PPP_HDRLEN); if (seq != (state->seqno & 0xffff)) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: bad seq # %d, expected %d\n", state->unit, seq, state->seqno & 0xffff); return DECOMP_ERROR; } ++state->seqno; /* * Fill in the first part of the PPP header. The protocol field * comes from the decompressed data. */ obuf[0] = PPP_ADDRESS(ibuf); obuf[1] = PPP_CONTROL(ibuf); obuf[2] = 0; /* * Set up to call inflate. We set avail_out to 1 initially so we can * look at the first byte of the output and decide whether we have * a 1-byte or 2-byte protocol field. */ state->strm.next_in = ibuf + PPP_HDRLEN + DEFLATE_OVHD; state->strm.avail_in = isize - (PPP_HDRLEN + DEFLATE_OVHD); state->strm.next_out = obuf + 3; state->strm.avail_out = 1; decode_proto = 1; overflow = 0; /* * Call inflate, supplying more input or output as needed. */ for (;;) { r = zlib_inflate(&state->strm, Z_PACKET_FLUSH); if (r != Z_OK) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: inflate returned %d (%s)\n", state->unit, r, (state->strm.msg? state->strm.msg: "")); return DECOMP_FATALERROR; } if (state->strm.avail_out != 0) break; /* all done */ if (decode_proto) { state->strm.avail_out = osize - PPP_HDRLEN; if ((obuf[3] & 1) == 0) { /* 2-byte protocol field */ obuf[2] = obuf[3]; --state->strm.next_out; ++state->strm.avail_out; } decode_proto = 0; } else if (!overflow) { /* * We've filled up the output buffer; the only way to * find out whether inflate has any more characters * left is to give it another byte of output space. */ state->strm.next_out = overflow_buf; state->strm.avail_out = 1; overflow = 1; } else { if (state->debug) printk(KERN_DEBUG "z_decompress%d: ran out of mru\n", state->unit); return DECOMP_FATALERROR; } } if (decode_proto) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: didn't get proto\n", state->unit); return DECOMP_ERROR; } olen = osize + overflow - state->strm.avail_out; state->stats.unc_bytes += olen; state->stats.unc_packets++; state->stats.comp_bytes += isize; state->stats.comp_packets++; return olen; } /** * z_incomp - add incompressible input data to the history. * @arg: pointer to private state for the decompressor * @ibuf: pointer to input packet data * @icnt: length of input data. */ static void z_incomp(void *arg, unsigned char *ibuf, int icnt) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; int proto, r; /* * Check that the protocol is one we handle. */ proto = PPP_PROTOCOL(ibuf); if (proto > 0x3fff || proto == 0xfd || proto == 0xfb) return; ++state->seqno; /* * We start at the either the 1st or 2nd byte of the protocol field, * depending on whether the protocol value is compressible. */ state->strm.next_in = ibuf + 3; state->strm.avail_in = icnt - 3; if (proto > 0xff) { --state->strm.next_in; ++state->strm.avail_in; } r = zlib_inflateIncomp(&state->strm); if (r != Z_OK) { /* gak! */ if (state->debug) { printk(KERN_DEBUG "z_incomp%d: inflateIncomp returned %d (%s)\n", state->unit, r, (state->strm.msg? state->strm.msg: "")); } return; } /* * Update stats. */ state->stats.inc_bytes += icnt; state->stats.inc_packets++; state->stats.unc_bytes += icnt; state->stats.unc_packets++; } /************************************************************* * Module interface table *************************************************************/ /* These are in ppp_generic.c */ extern int ppp_register_compressor (struct compressor *cp); extern void ppp_unregister_compressor (struct compressor *cp); /* * Procedures exported to if_ppp.c. */ static struct compressor ppp_deflate = { .compress_proto = CI_DEFLATE, .comp_alloc = z_comp_alloc, .comp_free = z_comp_free, .comp_init = z_comp_init, .comp_reset = z_comp_reset, .compress = z_compress, .comp_stat = z_comp_stats, .decomp_alloc = z_decomp_alloc, .decomp_free = z_decomp_free, .decomp_init = z_decomp_init, .decomp_reset = z_decomp_reset, .decompress = z_decompress, .incomp = z_incomp, .decomp_stat = z_comp_stats, .owner = THIS_MODULE }; static struct compressor ppp_deflate_draft = { .compress_proto = CI_DEFLATE_DRAFT, .comp_alloc = z_comp_alloc, .comp_free = z_comp_free, .comp_init = z_comp_init, .comp_reset = z_comp_reset, .compress = z_compress, .comp_stat = z_comp_stats, .decomp_alloc = z_decomp_alloc, .decomp_free = z_decomp_free, .decomp_init = z_decomp_init, .decomp_reset = z_decomp_reset, .decompress = z_decompress, .incomp = z_incomp, .decomp_stat = z_comp_stats, .owner = THIS_MODULE }; static int __init deflate_init(void) { int rc; rc = ppp_register_compressor(&ppp_deflate); if (rc) return rc; rc = ppp_register_compressor(&ppp_deflate_draft); if (rc) { ppp_unregister_compressor(&ppp_deflate); return rc; } pr_info("PPP Deflate Compression module registered\n"); return 0; } static void __exit deflate_cleanup(void) { ppp_unregister_compressor(&ppp_deflate); ppp_unregister_compressor(&ppp_deflate_draft); } module_init(deflate_init); module_exit(deflate_cleanup); MODULE_DESCRIPTION("PPP Deflate compression module"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE)); MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE_DRAFT)); |
| 1382 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_alloc_contig_migrate_range_info, TP_PROTO(unsigned long start, unsigned long end, unsigned long nr_migrated, unsigned long nr_reclaimed, unsigned long nr_mapped, int migratetype), TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned long, nr_migrated) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_mapped) __field(int, migratetype) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->nr_migrated = nr_migrated; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_mapped = nr_mapped; __entry->migratetype = migratetype; ), TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu", __entry->start, __entry->end, __entry->migratetype, __entry->nr_migrated, __entry->nr_reclaimed, __entry->nr_mapped) ); TRACE_EVENT(mm_setup_per_zone_wmarks, TP_PROTO(struct zone *zone), TP_ARGS(zone), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __field(unsigned long, watermark_min) __field(unsigned long, watermark_low) __field(unsigned long, watermark_high) __field(unsigned long, watermark_promo) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __entry->watermark_min = zone->_watermark[WMARK_MIN]; __entry->watermark_low = zone->_watermark[WMARK_LOW]; __entry->watermark_high = zone->_watermark[WMARK_HIGH]; __entry->watermark_promo = zone->_watermark[WMARK_PROMO]; ), TP_printk("node_id=%d zone name=%s watermark min=%lu low=%lu high=%lu promo=%lu", __entry->node_id, __get_str(name), __entry->watermark_min, __entry->watermark_low, __entry->watermark_high, __entry->watermark_promo) ); TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), TP_ARGS(zone, upper_zone, lowmem_reserve), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __string(upper_name, upper_zone->name) __field(long, lowmem_reserve) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __assign_str(upper_name); __entry->lowmem_reserve = lowmem_reserve; ), TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", __entry->node_id, __get_str(name), __get_str(upper_name), __entry->lowmem_reserve) ); TRACE_EVENT(mm_calculate_totalreserve_pages, TP_PROTO(unsigned long totalreserve_pages), TP_ARGS(totalreserve_pages), TP_STRUCT__entry( __field(unsigned long, totalreserve_pages) ), TP_fast_assign( __entry->totalreserve_pages = totalreserve_pages; ), TP_printk("totalreserve_pages=%lu", __entry->totalreserve_pages) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/stddef.h> #include <linux/err.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_bridge.h> #include <net/netfilter/nf_log.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/sysctl.h> #include <net/route.h> #include <net/ip.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <linux/ipv6.h> #include <linux/in6.h> #include <net/ipv6.h> #include <net/inet_frag.h> static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL __printf(4, 5) void nf_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_hook_state *state, u8 protonum, const char *fmt, ...) { struct net *net = state->net; struct va_format vaf; va_list args; if (net->ct.sysctl_log_invalid != protonum && net->ct.sysctl_log_invalid != IPPROTO_RAW) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; nf_log_packet(net, state->pf, 0, skb, state->in, state->out, NULL, "nf_ct_proto_%d: %pV ", protonum, &vaf); va_end(args); } EXPORT_SYMBOL_GPL(nf_l4proto_log_invalid); __printf(4, 5) void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, const struct nf_hook_state *state, const char *fmt, ...) { struct va_format vaf; struct net *net; va_list args; net = nf_ct_net(ct); if (likely(net->ct.sysctl_log_invalid == 0)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; nf_l4proto_log_invalid(skb, state, nf_ct_protonum(ct), "%pV", &vaf); va_end(args); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_log_invalid); #endif const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto) { switch (l4proto) { case IPPROTO_UDP: return &nf_conntrack_l4proto_udp; case IPPROTO_TCP: return &nf_conntrack_l4proto_tcp; case IPPROTO_ICMP: return &nf_conntrack_l4proto_icmp; #ifdef CONFIG_NF_CT_PROTO_DCCP case IPPROTO_DCCP: return &nf_conntrack_l4proto_dccp; #endif #ifdef CONFIG_NF_CT_PROTO_SCTP case IPPROTO_SCTP: return &nf_conntrack_l4proto_sctp; #endif #ifdef CONFIG_NF_CT_PROTO_UDPLITE case IPPROTO_UDPLITE: return &nf_conntrack_l4proto_udplite; #endif #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: return &nf_conntrack_l4proto_gre; #endif #if IS_ENABLED(CONFIG_IPV6) case IPPROTO_ICMPV6: return &nf_conntrack_l4proto_icmpv6; #endif /* CONFIG_IPV6 */ } return &nf_conntrack_l4proto_generic; }; EXPORT_SYMBOL_GPL(nf_ct_l4proto_find); static bool in_vrf_postrouting(const struct nf_hook_state *state) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (state->hook == NF_INET_POST_ROUTING && netif_is_l3_master(state->out)) return true; #endif return false; } unsigned int nf_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn_help *help; enum ip_conntrack_info ctinfo; unsigned int protoff; struct nf_conn *ct; bool seqadj_needed; __be16 frag_off; int start; u8 pnum; ct = nf_ct_get(skb, &ctinfo); if (!ct || in_vrf_postrouting(state)) return NF_ACCEPT; help = nfct_help(ct); seqadj_needed = test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb); if (!help && !seqadj_needed) return nf_conntrack_confirm(skb); /* helper->help() do not expect ICMP packets */ if (ctinfo == IP_CT_RELATED_REPLY) return nf_conntrack_confirm(skb); switch (nf_ct_l3num(ct)) { case NFPROTO_IPV4: protoff = skb_network_offset(skb) + ip_hdrlen(skb); break; case NFPROTO_IPV6: pnum = ipv6_hdr(skb)->nexthdr; start = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); if (start < 0 || (frag_off & htons(~0x7)) != 0) return nf_conntrack_confirm(skb); protoff = start; break; default: return nf_conntrack_confirm(skb); } if (help) { const struct nf_conntrack_helper *helper; int ret; /* rcu_read_lock()ed by nf_hook */ helper = rcu_dereference(help->helper); if (helper) { ret = helper->help(skb, protoff, ct, ctinfo); if (ret != NF_ACCEPT) return ret; } } if (seqadj_needed && !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); return NF_DROP; } /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); } EXPORT_SYMBOL_GPL(nf_confirm); static unsigned int ipv4_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return nf_conntrack_in(skb, state); } static unsigned int ipv4_conntrack_local(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */ enum ip_conntrack_info ctinfo; struct nf_conn *tmpl; tmpl = nf_ct_get(skb, &ctinfo); if (tmpl && nf_ct_is_template(tmpl)) { /* when skipping ct, clear templates to avoid fooling * later targets/matches */ skb->_nfct = 0; nf_ct_put(tmpl); } return NF_ACCEPT; } return nf_conntrack_in(skb, state); } /* Connection tracking may drop packets, but never alters them, so * make it the first hook. */ static const struct nf_hook_ops ipv4_conntrack_ops[] = { { .hook = ipv4_conntrack_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK, }, { .hook = ipv4_conntrack_local, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_CONNTRACK, }, { .hook = nf_confirm, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, { .hook = nf_confirm, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, }; /* Fast function for those who don't want to parse /proc (and I don't * blame them). * Reversing the socket's dst/src point of view gives us the reply * mapping. */ static int getorigdst(struct sock *sk, int optval, void __user *user, int *len) { const struct inet_sock *inet = inet_sk(sk); const struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; memset(&tuple, 0, sizeof(tuple)); lock_sock(sk); tuple.src.u3.ip = inet->inet_rcv_saddr; tuple.src.u.tcp.port = inet->inet_sport; tuple.dst.u3.ip = inet->inet_daddr; tuple.dst.u.tcp.port = inet->inet_dport; tuple.src.l3num = PF_INET; tuple.dst.protonum = sk->sk_protocol; release_sock(sk); /* We only do TCP and SCTP at the moment: is there a better way? */ if (tuple.dst.protonum != IPPROTO_TCP && tuple.dst.protonum != IPPROTO_SCTP) return -ENOPROTOOPT; if ((unsigned int)*len < sizeof(struct sockaddr_in)) return -EINVAL; h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); if (h) { struct sockaddr_in sin; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); sin.sin_family = AF_INET; sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL] .tuple.dst.u.tcp.port; sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL] .tuple.dst.u3.ip; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); nf_ct_put(ct); if (copy_to_user(user, &sin, sizeof(sin)) != 0) return -EFAULT; else return 0; } return -ENOENT; } static struct nf_sockopt_ops so_getorigdst = { .pf = PF_INET, .get_optmin = SO_ORIGINAL_DST, .get_optmax = SO_ORIGINAL_DST + 1, .get = getorigdst, .owner = THIS_MODULE, }; #if IS_ENABLED(CONFIG_IPV6) static int ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) { struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; const struct ipv6_pinfo *inet6 = inet6_sk(sk); const struct inet_sock *inet = inet_sk(sk); const struct nf_conntrack_tuple_hash *h; struct sockaddr_in6 sin6; struct nf_conn *ct; __be32 flow_label; int bound_dev_if; lock_sock(sk); tuple.src.u3.in6 = sk->sk_v6_rcv_saddr; tuple.src.u.tcp.port = inet->inet_sport; tuple.dst.u3.in6 = sk->sk_v6_daddr; tuple.dst.u.tcp.port = inet->inet_dport; tuple.dst.protonum = sk->sk_protocol; bound_dev_if = sk->sk_bound_dev_if; flow_label = inet6->flow_label; release_sock(sk); if (tuple.dst.protonum != IPPROTO_TCP && tuple.dst.protonum != IPPROTO_SCTP) return -ENOPROTOOPT; if (*len < 0 || (unsigned int)*len < sizeof(sin6)) return -EINVAL; h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); sin6.sin6_family = AF_INET6; sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; sin6.sin6_flowinfo = flow_label & IPV6_FLOWINFO_MASK; memcpy(&sin6.sin6_addr, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, sizeof(sin6.sin6_addr)); nf_ct_put(ct); sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, bound_dev_if); return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; } static struct nf_sockopt_ops so_getorigdst6 = { .pf = NFPROTO_IPV6, .get_optmin = IP6T_SO_ORIGINAL_DST, .get_optmax = IP6T_SO_ORIGINAL_DST + 1, .get = ipv6_getorigdst, .owner = THIS_MODULE, }; static unsigned int ipv6_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return nf_conntrack_in(skb, state); } static unsigned int ipv6_conntrack_local(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return nf_conntrack_in(skb, state); } static const struct nf_hook_ops ipv6_conntrack_ops[] = { { .hook = ipv6_conntrack_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = ipv6_conntrack_local, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = nf_confirm, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, { .hook = nf_confirm, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_LAST - 1, }, }; #endif static int nf_ct_tcp_fixup(struct nf_conn *ct, void *_nfproto) { u8 nfproto = (unsigned long)_nfproto; if (nf_ct_l3num(ct) != nfproto) return 0; if (nf_ct_protonum(ct) == IPPROTO_TCP && ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED) { ct->proto.tcp.seen[0].td_maxwin = 0; ct->proto.tcp.seen[1].td_maxwin = 0; } return 0; } static struct nf_ct_bridge_info *nf_ct_bridge_info; static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); bool fixup_needed = false, retry = true; int err = 0; retry: mutex_lock(&nf_ct_proto_mutex); switch (nfproto) { case NFPROTO_IPV4: cnet->users4++; if (cnet->users4 > 1) goto out_unlock; err = nf_defrag_ipv4_enable(net); if (err) { cnet->users4 = 0; goto out_unlock; } err = nf_register_net_hooks(net, ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); if (err) cnet->users4 = 0; else fixup_needed = true; break; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: cnet->users6++; if (cnet->users6 > 1) goto out_unlock; err = nf_defrag_ipv6_enable(net); if (err < 0) { cnet->users6 = 0; goto out_unlock; } err = nf_register_net_hooks(net, ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); if (err) cnet->users6 = 0; else fixup_needed = true; break; #endif case NFPROTO_BRIDGE: if (!nf_ct_bridge_info) { if (!retry) { err = -EPROTO; goto out_unlock; } mutex_unlock(&nf_ct_proto_mutex); request_module("nf_conntrack_bridge"); retry = false; goto retry; } if (!try_module_get(nf_ct_bridge_info->me)) { err = -EPROTO; goto out_unlock; } cnet->users_bridge++; if (cnet->users_bridge > 1) goto out_unlock; err = nf_register_net_hooks(net, nf_ct_bridge_info->ops, nf_ct_bridge_info->ops_size); if (err) cnet->users_bridge = 0; else fixup_needed = true; break; default: err = -EPROTO; break; } out_unlock: mutex_unlock(&nf_ct_proto_mutex); if (fixup_needed) { struct nf_ct_iter_data iter_data = { .net = net, .data = (void *)(unsigned long)nfproto, }; nf_ct_iterate_cleanup_net(nf_ct_tcp_fixup, &iter_data); } return err; } static void nf_ct_netns_do_put(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); mutex_lock(&nf_ct_proto_mutex); switch (nfproto) { case NFPROTO_IPV4: if (cnet->users4 && (--cnet->users4 == 0)) { nf_unregister_net_hooks(net, ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); nf_defrag_ipv4_disable(net); } break; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: if (cnet->users6 && (--cnet->users6 == 0)) { nf_unregister_net_hooks(net, ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); nf_defrag_ipv6_disable(net); } break; #endif case NFPROTO_BRIDGE: if (!nf_ct_bridge_info) break; if (cnet->users_bridge && (--cnet->users_bridge == 0)) nf_unregister_net_hooks(net, nf_ct_bridge_info->ops, nf_ct_bridge_info->ops_size); module_put(nf_ct_bridge_info->me); break; } mutex_unlock(&nf_ct_proto_mutex); } static int nf_ct_netns_inet_get(struct net *net) { int err; err = nf_ct_netns_do_get(net, NFPROTO_IPV4); #if IS_ENABLED(CONFIG_IPV6) if (err < 0) goto err1; err = nf_ct_netns_do_get(net, NFPROTO_IPV6); if (err < 0) goto err2; return err; err2: nf_ct_netns_put(net, NFPROTO_IPV4); err1: #endif return err; } int nf_ct_netns_get(struct net *net, u8 nfproto) { int err; switch (nfproto) { case NFPROTO_INET: err = nf_ct_netns_inet_get(net); break; case NFPROTO_BRIDGE: err = nf_ct_netns_do_get(net, NFPROTO_BRIDGE); if (err < 0) return err; err = nf_ct_netns_inet_get(net); if (err < 0) { nf_ct_netns_put(net, NFPROTO_BRIDGE); return err; } break; default: err = nf_ct_netns_do_get(net, nfproto); break; } return err; } EXPORT_SYMBOL_GPL(nf_ct_netns_get); void nf_ct_netns_put(struct net *net, uint8_t nfproto) { switch (nfproto) { case NFPROTO_BRIDGE: nf_ct_netns_do_put(net, NFPROTO_BRIDGE); fallthrough; case NFPROTO_INET: nf_ct_netns_do_put(net, NFPROTO_IPV4); nf_ct_netns_do_put(net, NFPROTO_IPV6); break; default: nf_ct_netns_do_put(net, nfproto); break; } } EXPORT_SYMBOL_GPL(nf_ct_netns_put); void nf_ct_bridge_register(struct nf_ct_bridge_info *info) { WARN_ON(nf_ct_bridge_info); mutex_lock(&nf_ct_proto_mutex); nf_ct_bridge_info = info; mutex_unlock(&nf_ct_proto_mutex); } EXPORT_SYMBOL_GPL(nf_ct_bridge_register); void nf_ct_bridge_unregister(struct nf_ct_bridge_info *info) { WARN_ON(!nf_ct_bridge_info); mutex_lock(&nf_ct_proto_mutex); nf_ct_bridge_info = NULL; mutex_unlock(&nf_ct_proto_mutex); } EXPORT_SYMBOL_GPL(nf_ct_bridge_unregister); int nf_conntrack_proto_init(void) { int ret; ret = nf_register_sockopt(&so_getorigdst); if (ret < 0) return ret; #if IS_ENABLED(CONFIG_IPV6) ret = nf_register_sockopt(&so_getorigdst6); if (ret < 0) goto cleanup_sockopt; #endif return ret; #if IS_ENABLED(CONFIG_IPV6) cleanup_sockopt: nf_unregister_sockopt(&so_getorigdst); #endif return ret; } void nf_conntrack_proto_fini(void) { nf_unregister_sockopt(&so_getorigdst); #if IS_ENABLED(CONFIG_IPV6) nf_unregister_sockopt(&so_getorigdst6); #endif } void nf_conntrack_proto_pernet_init(struct net *net) { nf_conntrack_generic_init_net(net); nf_conntrack_udp_init_net(net); nf_conntrack_tcp_init_net(net); nf_conntrack_icmp_init_net(net); #if IS_ENABLED(CONFIG_IPV6) nf_conntrack_icmpv6_init_net(net); #endif #ifdef CONFIG_NF_CT_PROTO_DCCP nf_conntrack_dccp_init_net(net); #endif #ifdef CONFIG_NF_CT_PROTO_SCTP nf_conntrack_sctp_init_net(net); #endif #ifdef CONFIG_NF_CT_PROTO_GRE nf_conntrack_gre_init_net(net); #endif } module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); MODULE_ALIAS("ip_conntrack"); MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv4 and IPv6 connection tracking"); |
| 79 8 8 8 71 71 79 79 4 3 17 21 280 283 282 283 281 232 233 233 232 233 232 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. These functions are needed by GSO/GRO implementation. */ #include <linux/export.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> #include <net/secure_seq.h> #include <linux/netfilter.h> static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { return get_random_u32_above(0); } /* This function exists only for tap drivers that must support broken * clients requesting UFO without specifying an IPv6 fragment ID. * * This is similar to ipv6_select_ident() but we use an independent hash * seed to limit information leakage. * * The network header must be set before calling this. */ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { struct in6_addr buf[2]; struct in6_addr *addrs; u32 id; addrs = skb_header_pointer(skb, skb_network_offset(skb) + offsetof(struct ipv6hdr, saddr), sizeof(buf), buf); if (!addrs) return 0; id = __ipv6_select_ident(net, &addrs[1], &addrs[0]); return htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) { u32 id; id = __ipv6_select_ident(net, daddr, saddr); return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; switch (**nexthdr) { case NEXTHDR_HOP: break; case NEXTHDR_ROUTING: found_rhdr = 1; break; case NEXTHDR_DEST: #if IS_ENABLED(CONFIG_IPV6_MIP6) if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) break; #endif if (found_rhdr) return offset; break; default: return offset; } if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) return -EINVAL; exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); offset += ipv6_optlen(exthdr); if (offset > IPV6_MAXPLEN) return -EINVAL; *nexthdr = &exthdr->nexthdr; } return -EINVAL; } EXPORT_SYMBOL(ip6_find_1stfragopt); #if IS_ENABLED(CONFIG_IPV6) int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); if (hoplimit == 0) { struct net_device *dev = dst->dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) hoplimit = READ_ONCE(idev->cnf.hop_limit); else hoplimit = READ_ONCE(dev_net(dev)->ipv6.devconf_all->hop_limit); rcu_read_unlock(); } return hoplimit; } EXPORT_SYMBOL(ip6_dst_hoplimit); #endif int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int len; len = skb->len - sizeof(struct ipv6hdr); if (len > IPV6_MAXPLEN) len = 0; ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IPV6); return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } EXPORT_SYMBOL_GPL(__ip6_local_out); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip6_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip6_local_out); |
| 1836 1845 1842 1845 1161 1163 4174 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell * * This code is licenced under the GPL. */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <linux/cc_platform.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * struct cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @fail: Current CPU hotplug callback state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * struct cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step * @multi_instance: State has multiple instances which get added afterwards */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; /* private: */ struct hlist_head list; /* public: */ bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step) { return bringup ? !step->startup.single : !step->teardown.single; } /** * cpuhp_invoke_callback - Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. * * Return: %0 on success or a negative errno code */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; return -EAGAIN; } if (cpuhp_step_empty(bringup, step)) { WARN_ON_ONCE(1); return 0; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } /* Synchronization state management */ enum cpuhp_sync_state { SYNC_STATE_DEAD, SYNC_STATE_KICKED, SYNC_STATE_SHOULD_DIE, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE, SYNC_STATE_ONLINE, }; #ifdef CONFIG_HOTPLUG_CORE_SYNC /** * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown * @state: The synchronization state to set * * No synchronization point. Just update of the synchronization state, but implies * a full barrier so that the AP changes are visible before the control CPU proceeds. */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); (void)atomic_xchg(st, state); } void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, enum cpuhp_sync_state next_state) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); ktime_t now, end, start = ktime_get(); int sync; end = start + 10ULL * NSEC_PER_SEC; sync = atomic_read(st); while (1) { if (sync == state) { if (!atomic_try_cmpxchg(st, &sync, next_state)) continue; return true; } now = ktime_get(); if (now > end) { /* Timeout. Leave the state unchanged */ return false; } else if (now - start < NSEC_PER_MSEC) { /* Poll for one millisecond */ arch_cpuhp_sync_state_poll(); } else { usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); } sync = atomic_read(st); } return true; } #else /* CONFIG_HOTPLUG_CORE_SYNC */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD /** * cpuhp_ap_report_dead - Update synchronization state to DEAD * * No synchronization point. Just update of the synchronization state. */ void cpuhp_ap_report_dead(void) { cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); } void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } /* * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down * because the AP cannot issue complete() at this stage. */ static void cpuhp_bp_sync_dead(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); do { /* CPU can have reported dead already. Don't overwrite that! */ if (sync == SYNC_STATE_DEAD) break; } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { /* CPU reached dead state. Invoke the cleanup function */ arch_cpuhp_cleanup_dead_cpu(cpu); return; } /* No further action possible. Emit message and give up. */ pr_err("CPU%u failed to report dead state\n", cpu); } #else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL /** * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive * * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits * for the BP to release it. */ void cpuhp_ap_sync_alive(void) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); /* Wait for the control CPU to release it. */ while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) cpu_relax(); } static bool cpuhp_can_boot_ap(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); again: switch (sync) { case SYNC_STATE_DEAD: /* CPU is properly dead */ break; case SYNC_STATE_KICKED: /* CPU did not come up in previous attempt */ break; case SYNC_STATE_ALIVE: /* CPU is stuck cpuhp_ap_sync_alive(). */ break; default: /* CPU failed to report online or dead and is in limbo state. */ return false; } /* Prepare for booting */ if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) goto again; return true; } void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } /* * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up * because the AP cannot issue complete() so early in the bringup. */ static int cpuhp_bp_sync_alive(unsigned int cpu) { int ret = 0; if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) return 0; if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { pr_err("CPU%u failed to report alive state\n", cpu); ret = -EIO; } /* Let the architecture cleanup the kick alive mechanics. */ arch_cpuhp_cleanup_kick_cpu(cpu); return ret; } #else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); static bool cpu_hotplug_offline_disabled __ro_after_init; void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(lockdep_assert_cpus_held); #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) { return percpu_rwsem_is_held(&cpu_hotplug_lock); } #endif static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } /* Declare CPU offlining not supported */ void cpu_hotplug_disable_offlining(void) { cpu_maps_update_begin(); cpu_hotplug_offline_disabled = true; cpu_maps_update_done(); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; static unsigned int cpu_smt_max_threads __ro_after_init; unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } cpu_smt_num_threads = 1; } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_set_num_threads(unsigned int num_threads, unsigned int max_threads) { WARN_ON(!num_threads || (num_threads > max_threads)); if (max_threads == 1) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; cpu_smt_max_threads = max_threads; /* * If SMT has been disabled via the kernel command line or SMT is * not supported, set cpu_smt_num_threads to 1 for consistency. * If enabled, take the architecture requested number of threads * to bring up into account. */ if (cpu_smt_control != CPU_SMT_ENABLED) cpu_smt_num_threads = 1; else if (num_threads < cpu_smt_num_threads) cpu_smt_num_threads = num_threads; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); /* * For Archicture supporting partial SMT states check if the thread is allowed. * Otherwise this has already been checked through cpu_smt_max_threads when * setting the SMT level. */ static inline bool cpu_smt_thread_allowed(unsigned int cpu) { #ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC return topology_smt_thread_allowed(cpu); #else return true; #endif } static inline bool cpu_bootable(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) return true; /* All CPUs are bootable if controls are not configured */ if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) return true; /* All CPUs are bootable if CPU is not SMT capable */ if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is supported and not forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); return prev_state; } static inline void cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { bool bringup = !st->bringup; st->target = prev_state; /* * Already rolling back. No need invert the bringup value or to change * the current state. */ if (st->rollback) return; st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap_online(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_bootable() check will now return false if this is not the * primary sibling. */ if (!cpu_bootable(cpu)) return -ECANCELED; return 0; } #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP static int cpuhp_kick_ap_alive(unsigned int cpu) { if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); } static int cpuhp_bringup_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #else static int bringup_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle = idle_thread_get(cpu); int ret; if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * * Prevent irq alloc/free across the bringup by acquiring the * sparse irq lock. Hold it until the upcoming CPU completes the * startup in cpuhp_online_idle() which allows to avoid * intermediate synchronization points in the architecture code. */ irq_lock_sparse(); ret = __cpu_up(cpu, idle); if (ret) goto out_unlock; ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #endif static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * sched_force_init_mm() ensured the use of &init_mm, * drop that refcount now that the CPU has stopped. */ WARN_ON(mm != &init_mm); idle->active_mm = NULL; mmdrop_lazy_tlb(mm); return 0; } /* * Hotplug state machine related functions */ /* * Get the next state to run. Empty ones will be skipped. Returns true if a * state must be run. * * st->state will be modified ahead of time, to match state_to_run, as if it * has already ran. */ static bool cpuhp_next_state(bool bringup, enum cpuhp_state *state_to_run, struct cpuhp_cpu_state *st, enum cpuhp_state target) { do { if (bringup) { if (st->state >= target) return false; *state_to_run = ++st->state; } else { if (st->state <= target) return false; *state_to_run = st->state--; } if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run))) break; } while (true); return true; } static int __cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target, bool nofail) { enum cpuhp_state state; int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { int err; err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); if (!err) continue; if (nofail) { pr_warn("CPU %u %s state %s (%d) failed (%d)\n", cpu, bringup ? "UP" : "DOWN", cpuhp_get_step(st->state)->name, st->state, err); ret = -1; } else { ret = err; break; } } return ret; } static inline int cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); } static inline void cpuhp_invoke_callback_range_nofail(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(true, cpu, st, target); if (ret) { pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { st->should_run = cpuhp_next_state(bringup, &state, st, st->target); if (!st->should_run) goto end; } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } end: cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; static __init void cpuhp_init_state(void) { struct cpuhp_cpu_state *st; int cpu; for_each_possible_cpu(cpu) { st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } } void __init cpuhp_threads_init(void) { cpuhp_init_state(); BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going * down, that the current state is CPUHP_TEARDOWN_CPU - 1. */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); /* * Invoke the former CPU_DYING callbacks. DYING must not fail! */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); /* * So now all preempt/rcu users must observe !cpu_active(). */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); cpuhp_bp_sync_dead(cpu); lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu)); /* * Callbacks must be re-integrated right away to the RCU state machine. * Otherwise an RCU callback could block a further teardown function * waiting for its completion. */ rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); tick_assert_timekeeping_handover(); rcutree_report_cpu_dead(); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcutree_report_cpu_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(false, cpu, st, target); if (ret) { pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, prev_state)); } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); } } out: cpus_write_unlock(); arch_smt_update(); return ret; } struct cpu_down_work { unsigned int cpu; enum cpuhp_state target; }; static long __cpu_down_maps_locked(void *arg) { struct cpu_down_work *work = arg; return _cpu_down(work->cpu, 0, work->target); } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { struct cpu_down_work work = { .cpu = cpu, .target = target, }; /* * If the platform does not support hotplug, report it explicitly to * differentiate it from a transient offlining failure. */ if (cpu_hotplug_offline_disabled) return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; /* * Ensure that the control task does not run on the to be offlined * CPU to prevent a deadlock against cfs_b->period_timer. * Also keep at least one housekeeping cpu onlined to avoid generating * an empty sched_domain span. */ for_each_cpu_and(cpu, cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) { if (cpu != work.cpu) return work_on_cpu(cpu, __cpu_down_maps_locked, &work); } return -EBUSY; } static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } /** * cpu_device_down - Bring down a cpu device * @dev: Pointer to the cpu device to offline * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use remove_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_down(struct device *dev) { return cpu_down(dev->id, CPUHP_OFFLINE); } int remove_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_offline(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(remove_cpu); void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { unsigned int cpu; int error; cpu_maps_update_begin(); /* * Make certain the cpu I'm about to reboot on is online. * * This is inline to what migrate_to_reboot_cpu() already do. */ if (!cpu_online(primary_cpu)) primary_cpu = cpumask_first(cpu_online_mask); for_each_online_cpu(cpu) { if (cpu == primary_cpu) continue; error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (error) { pr_err("Failed to offline CPU%d - error=%d", cpu, error); break; } } /* * Ensure all but the reboot CPU are offline. */ BUG_ON(num_online_cpus() > 1); /* * Make sure the CPUs won't be enabled by someone else after this * point. Kexec will reboot to a new kernel shortly resetting * everything along the way. */ cpu_hotplug_disabled++; cpu_maps_update_done(); } #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); /* * STARTING must not fail! */ cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); /* * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of cpu_up() might have raced with another * caller. Nothing to do. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } /* * Reset stale stack state from the last time this CPU was online. */ scs_task_reset(idle); kasan_unpoison_task_stack(idle); } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); return ret; } static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); return -EINVAL; } err = try_online_node(cpu_to_node(cpu)); if (err) return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } /** * cpu_device_up - Bring up a cpu device * @dev: Pointer to the cpu device to online * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use add_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_up(struct device *dev) { return cpu_up(dev->id, CPUHP_ONLINE); } int add_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_online(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_cpu); /** * bringup_hibernate_cpu - Bring up the CPU that we hibernated on * @sleep_cpu: The cpu we hibernated on and should be brought up. * * On some architectures like arm64, we can hibernate on any CPU, but on * wake up the CPU we hibernated on might be offline as a side effect of * using maxcpus= for example. * * Return: %0 on success or a negative errno code */ int bringup_hibernate_cpu(unsigned int sleep_cpu) { int ret; if (!cpu_online(sleep_cpu)) { pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); ret = cpu_up(sleep_cpu, CPUHP_ONLINE); if (ret) { pr_err("Failed to bring hibernate-CPU up!\n"); return ret; } } return 0; } static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, enum cpuhp_state target) { unsigned int cpu; for_each_cpu(cpu, mask) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); if (cpu_up(cpu, target) && can_rollback_cpu(st)) { /* * If this failed then cpu_up() might have only * rolled back to CPUHP_BP_KICK_AP for the final * online. Clean it up. NOOP if already rolled back. */ WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); } if (!--ncpus) break; } } #ifdef CONFIG_HOTPLUG_PARALLEL static bool __cpuhp_parallel_bringup __ro_after_init = true; static int __init parallel_bringup_parse_param(char *arg) { return kstrtobool(arg, &__cpuhp_parallel_bringup); } early_param("cpuhp.parallel", parallel_bringup_parse_param); #ifdef CONFIG_HOTPLUG_SMT static inline bool cpuhp_smt_aware(void) { return cpu_smt_max_threads > 1; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_primary_thread_mask; } #else static inline bool cpuhp_smt_aware(void) { return false; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_none_mask; } #endif bool __weak arch_cpuhp_init_parallel_bringup(void) { return true; } /* * On architectures which have enabled parallel bringup this invokes all BP * prepare states for each of the to be onlined APs first. The last state * sends the startup IPI to the APs. The APs proceed through the low level * bringup code in parallel and then wait for the control CPU to release * them one by one for the final onlining procedure. * * This avoids waiting for each AP to respond to the startup IPI in * CPUHP_BRINGUP_CPU. */ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) { const struct cpumask *mask = cpu_present_mask; if (__cpuhp_parallel_bringup) __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); if (!__cpuhp_parallel_bringup) return false; if (cpuhp_smt_aware()) { const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); static struct cpumask tmp_mask __initdata; /* * X86 requires to prevent that SMT siblings stopped while * the primary thread does a microcode update for various * reasons. Bring the primary threads up first. */ cpumask_and(&tmp_mask, mask, pmask); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); /* Account for the online CPUs */ ncpus -= num_online_cpus(); if (!ncpus) return true; /* Create the mask for secondary CPUs */ cpumask_andnot(&tmp_mask, mask, pmask); mask = &tmp_mask; } /* Bring the not-yet started CPUs up */ cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); return true; } #else static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } #endif /* CONFIG_HOTPLUG_PARALLEL */ void __init bringup_nonboot_cpus(unsigned int max_cpus) { if (!max_cpus) return; /* Try parallel bringup optimization if enabled */ if (cpuhp_bringup_cpus_parallel(max_cpus)) return; /* Full per CPU serialized bringup */ cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE); } #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int freeze_secondary_cpus(int primary) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for (cpu = nr_cpu_ids - 1; cpu >= 0; cpu--) { if (!cpu_online(cpu) || cpu == primary) continue; if (pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all freeze_secondary_cpus() users are * supposed to do thaw_secondary_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_thaw_secondary_cpus_begin(void) { } void __weak arch_thaw_secondary_cpus_end(void) { } void thaw_secondary_cpus(void) { int cpu, error; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_thaw_secondary_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_thaw_secondary_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_PERF_PREPARE] = { .name = "perf:prepare", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_RANDOM_PREPARE] = { .name = "random:prepare", .startup.single = random_prepare_cpu, .teardown.single = NULL, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP /* * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until * the next step will release it. */ [CPUHP_BP_KICK_AP] = { .name = "cpu:kick_ap", .startup.single = cpuhp_kick_ap_alive, }, /* * Waits for the AP to reach cpuhp_ap_sync_alive() and then * releases it for the complete bringup. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = cpuhp_bringup_ap, .teardown.single = finish_cpu, .cant_stop = true, }, #else /* * All-in-one CPU bringup state which includes the kick alive. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, #endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, [CPUHP_AP_HRTIMERS_DYING] = { .name = "hrtimers:dying", .startup.single = hrtimers_cpu_starting, .teardown.single = hrtimers_cpu_dying, }, [CPUHP_AP_TICK_DYING] = { .name = "tick:dying", .startup.single = NULL, .teardown.single = tick_cpu_dying, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on control processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, [CPUHP_AP_SCHED_WAIT_EMPTY] = { .name = "sched:waitempty", .startup.single = NULL, .teardown.single = sched_cpu_wait_empty, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RANDOM_ONLINE] = { .name = "random:online", .startup.single = random_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if (cpuhp_step_empty(bringup, sp)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @name: Name of the step * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Return: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN; * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN, * return the dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; /* * Disable can be called with CPU_SMT_ENABLED when changing * from a higher to lower number of SMT threads per core. */ if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } /* Check if the core a CPU belongs to is online */ #if !defined(topology_is_core_online) static inline bool topology_is_core_online(unsigned int cpu) { return true; } #endif int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu)) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR_RO(state); static ssize_t target_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = cpu_up(dev->id, target); else if (st->state > target) ret = cpu_down(dev->id, target); else if (WARN_ON(st->target != target)) st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t target_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR_RW(target); static ssize_t fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail == CPUHP_INVALID) { st->fail = fail; return count; } if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * DEAD callbacks cannot fail... * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter * triggering STARTING callbacks, a failure in this state would * hinder rollback. */ if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR_RW(fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", }; static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR_RO(states); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", }; #ifdef CONFIG_HOTPLUG_SMT static bool cpu_smt_num_threads_valid(unsigned int threads) { if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC)) return threads >= 1 && threads <= cpu_smt_max_threads; return threads == 1 || threads == cpu_smt_max_threads; } static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret, num_threads, orig_threads; bool force_off; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; if (sysfs_streq(buf, "on")) { ctrlval = CPU_SMT_ENABLED; num_threads = cpu_smt_max_threads; } else if (sysfs_streq(buf, "off")) { ctrlval = CPU_SMT_DISABLED; num_threads = 1; } else if (sysfs_streq(buf, "forceoff")) { ctrlval = CPU_SMT_FORCE_DISABLED; num_threads = 1; } else if (kstrtoint(buf, 10, &num_threads) == 0) { if (num_threads == 1) ctrlval = CPU_SMT_DISABLED; else if (cpu_smt_num_threads_valid(num_threads)) ctrlval = CPU_SMT_ENABLED; else return -EINVAL; } else { return -EINVAL; } ret = lock_device_hotplug_sysfs(); if (ret) return ret; orig_threads = cpu_smt_num_threads; cpu_smt_num_threads = num_threads; force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED; if (num_threads > orig_threads) ret = cpuhp_smt_enable(); else if (num_threads < orig_threads || force_off) ret = cpuhp_smt_disable(ctrlval); unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; #ifdef CONFIG_HOTPLUG_SMT /* * If SMT is enabled but not all threads are enabled then show the * number of threads. If all threads are enabled show "on". Otherwise * show the state name. */ if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_num_threads != cpu_smt_max_threads) return sysfs_emit(buf, "%d\n", cpu_smt_num_threads); #endif return sysfs_emit(buf, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", }; static int __init cpu_smt_sysfs_init(void) { struct device *dev_root; int ret = -ENODEV; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group); put_device(dev_root); } return ret; } static int __init cpuhp_sysfs_init(void) { struct device *dev_root; int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group); put_device(dev_root); if (ret) return ret; } for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __ro_after_init = {CPU_BITS_ALL}; #else struct cpumask __cpu_possible_mask __ro_after_init; #endif EXPORT_SYMBOL(__cpu_possible_mask); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_enabled_mask __read_mostly; EXPORT_SYMBOL(__cpu_enabled_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); struct cpumask __cpu_dying_mask __read_mostly; EXPORT_SYMBOL(__cpu_dying_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } #ifdef CONFIG_CPU_MITIGATIONS /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) cpu_mitigations = CPU_MITIGATIONS_OFF; else if (!strcmp(arg, "auto")) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; else pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); #else static int __init mitigations_parse_cmdline(char *arg) { pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); return 0; } #endif early_param("mitigations", mitigations_parse_cmdline); |
| 4 4 4 4 4 4 4 15 15 15 32 12 12 20 19 1 20 20 20 20 1 20 10 10 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "socket.h" #include "timers.h" #include "device.h" #include "ratelimiter.h" #include "peer.h" #include "messages.h" #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> #include <net/dst_metadata.h> #include <net/gso.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> #include <net/addrconf.h> static LIST_HEAD(device_list); static int wg_open(struct net_device *dev) { struct in_device *dev_v4 = __in_dev_get_rtnl(dev); struct inet6_dev *dev_v6 = __in6_dev_get(dev); struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; int ret; if (dev_v4) { /* At some point we might put this check near the ip_rt_send_ * redirect call of ip_forward in net/ipv4/ip_forward.c, similar * to the current secpath check. */ IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; } if (dev_v6) dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; mutex_lock(&wg->device_update_lock); ret = wg_socket_init(wg, wg->incoming_port); if (ret < 0) goto out; list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_send_staged_packets(peer); if (peer->persistent_keepalive_interval) wg_packet_send_keepalive(peer); } out: mutex_unlock(&wg->device_update_lock); return ret; } static int wg_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { struct wg_device *wg; struct wg_peer *peer; /* If the machine is constantly suspending and resuming, as part of * its normal operation rather than as a somewhat rare event, then we * don't actually want to clear keys. */ if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)) return 0; if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE) return 0; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { timer_delete(&peer->timer_zero_key_material); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); } mutex_unlock(&wg->device_update_lock); } rtnl_unlock(); rcu_barrier(); return 0; } static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification }; static int wg_vm_notification(struct notifier_block *nb, unsigned long action, void *data) { struct wg_device *wg; struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) wg_noise_expire_current_peer_keypairs(peer); mutex_unlock(&wg->device_update_lock); } rtnl_unlock(); return 0; } static struct notifier_block vm_notifier = { .notifier_call = wg_vm_notification }; static int wg_stop(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; struct sk_buff *skb; mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_purge_staged_packets(peer); wg_timers_stop(peer); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); } mutex_unlock(&wg->device_update_lock); while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL) kfree_skb(skb); atomic_set(&wg->handshake_queue_len, 0); wg_socket_reinit(wg, NULL, NULL); return 0; } static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct sk_buff_head packets; struct wg_peer *peer; struct sk_buff *next; sa_family_t family; u32 mtu; int ret; if (unlikely(!wg_check_packet_protocol(skb))) { ret = -EPROTONOSUPPORT; net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name); goto err; } peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb); if (unlikely(!peer)) { ret = -ENOKEY; if (skb->protocol == htons(ETH_P_IP)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n", dev->name, &ip_hdr(skb)->daddr); else if (skb->protocol == htons(ETH_P_IPV6)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", dev->name, &ipv6_hdr(skb)->daddr); goto err_icmp; } family = READ_ONCE(peer->endpoint.addr.sa_family); if (unlikely(family != AF_INET && family != AF_INET6)) { ret = -EDESTADDRREQ; net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n", dev->name, peer->internal_id); goto err_peer; } mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { skb_mark_not_on_list(skb); } else { struct sk_buff *segs = skb_gso_segment(skb, 0); if (IS_ERR(segs)) { ret = PTR_ERR(segs); goto err_peer; } dev_kfree_skb(skb); skb = segs; } skb_list_walk_safe(skb, skb, next) { skb_mark_not_on_list(skb); skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) continue; /* We only need to keep the original dst around for icmp, * so at this point we're in a position to drop it. */ skb_dst_drop(skb); PACKET_CB(skb)->mtu = mtu; __skb_queue_tail(&packets, skb); } spin_lock_bh(&peer->staged_packet_queue.lock); /* If the queue is getting too big, we start removing the oldest packets * until it's small again. We do this before adding the new packet, so * we don't remove GSO segments that are in excess. */ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); DEV_STATS_INC(dev, tx_dropped); } skb_queue_splice_tail(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); wg_packet_send_staged_packets(peer); wg_peer_put(peer); return NETDEV_TX_OK; err_peer: wg_peer_put(peer); err_icmp: if (skb->protocol == htons(ETH_P_IP)) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return ret; } static const struct net_device_ops netdev_ops = { .ndo_open = wg_open, .ndo_stop = wg_stop, .ndo_start_xmit = wg_xmit, }; static void wg_destruct(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); rtnl_lock(); list_del(&wg->device_list); rtnl_unlock(); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg->incoming_port = 0; wg_socket_reinit(wg, NULL, NULL); /* The final references are cleared in the below calls to destroy_workqueue. */ wg_peer_remove_all(wg); destroy_workqueue(wg->handshake_receive_wq); destroy_workqueue(wg->handshake_send_wq); destroy_workqueue(wg->packet_crypt_wq); wg_packet_queue_free(&wg->handshake_queue, true); wg_packet_queue_free(&wg->decrypt_queue, false); wg_packet_queue_free(&wg->encrypt_queue, false); rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); kvfree(wg->index_hashtable); kvfree(wg->peer_hashtable); mutex_unlock(&wg->device_update_lock); pr_debug("%s: Interface destroyed\n", dev->name); free_netdev(dev); } static const struct device_type device_type = { .name = KBUILD_MODNAME }; static void wg_setup(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->hard_header_len = 0; dev->addr_len = 0; dev->needed_headroom = DATA_PACKET_HEAD_ROOM; dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE); dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; dev->mtu = ETH_DATA_LEN - overhead; dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; SET_NETDEV_DEVTYPE(dev, &device_type); /* We need to keep the dst around in case of icmp replies. */ netif_keep_dst(dev); netif_set_tso_max_size(dev, GSO_MAX_SIZE); wg->dev = dev; } static int wg_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct wg_device *wg = netdev_priv(dev); int ret = -ENOMEM; rcu_assign_pointer(wg->creating_net, link_net); init_rwsem(&wg->static_identity.lock); mutex_init(&wg->socket_update_lock); mutex_init(&wg->device_update_lock); wg_allowedips_init(&wg->peer_allowedips); wg_cookie_checker_init(&wg->cookie_checker, wg); INIT_LIST_HEAD(&wg->peer_list); wg->device_update_gen = 1; wg->peer_hashtable = wg_pubkey_hashtable_alloc(); if (!wg->peer_hashtable) return ret; wg->index_hashtable = wg_index_hashtable_alloc(); if (!wg->index_hashtable) goto err_free_peer_hashtable; wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_receive_wq) goto err_free_index_hashtable; wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_send_wq) goto err_destroy_handshake_receive; wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name); if (!wg->packet_crypt_wq) goto err_destroy_handshake_send; ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_destroy_packet_crypt; ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_free_encrypt_queue; ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker, MAX_QUEUED_INCOMING_HANDSHAKES); if (ret < 0) goto err_free_decrypt_queue; ret = wg_ratelimiter_init(); if (ret < 0) goto err_free_handshake_queue; ret = register_netdevice(dev); if (ret < 0) goto err_uninit_ratelimiter; list_add(&wg->device_list, &device_list); /* We wait until the end to assign priv_destructor, so that * register_netdevice doesn't call it for us if it fails. */ dev->priv_destructor = wg_destruct; pr_debug("%s: Interface created\n", dev->name); return ret; err_uninit_ratelimiter: wg_ratelimiter_uninit(); err_free_handshake_queue: wg_packet_queue_free(&wg->handshake_queue, false); err_free_decrypt_queue: wg_packet_queue_free(&wg->decrypt_queue, false); err_free_encrypt_queue: wg_packet_queue_free(&wg->encrypt_queue, false); err_destroy_packet_crypt: destroy_workqueue(wg->packet_crypt_wq); err_destroy_handshake_send: destroy_workqueue(wg->handshake_send_wq); err_destroy_handshake_receive: destroy_workqueue(wg->handshake_receive_wq); err_free_index_hashtable: kvfree(wg->index_hashtable); err_free_peer_hashtable: kvfree(wg->peer_hashtable); return ret; } static struct rtnl_link_ops link_ops __read_mostly = { .kind = KBUILD_MODNAME, .priv_size = sizeof(struct wg_device), .setup = wg_setup, .newlink = wg_newlink, }; static void wg_netns_pre_exit(struct net *net) { struct wg_device *wg; struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { if (rcu_access_pointer(wg->creating_net) == net) { pr_debug("%s: Creating namespace exiting\n", wg->dev->name); netif_carrier_off(wg->dev); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg_socket_reinit(wg, NULL, NULL); list_for_each_entry(peer, &wg->peer_list, peer_list) wg_socket_clear_peer_endpoint_src(peer); mutex_unlock(&wg->device_update_lock); } } rtnl_unlock(); } static struct pernet_operations pernet_ops = { .pre_exit = wg_netns_pre_exit }; int __init wg_device_init(void) { int ret; ret = register_pm_notifier(&pm_notifier); if (ret) return ret; ret = register_random_vmfork_notifier(&vm_notifier); if (ret) goto error_pm; ret = register_pernet_device(&pernet_ops); if (ret) goto error_vm; ret = rtnl_link_register(&link_ops); if (ret) goto error_pernet; return 0; error_pernet: unregister_pernet_device(&pernet_ops); error_vm: unregister_random_vmfork_notifier(&vm_notifier); error_pm: unregister_pm_notifier(&pm_notifier); return ret; } void wg_device_uninit(void) { rtnl_link_unregister(&link_ops); unregister_pernet_device(&pernet_ops); unregister_random_vmfork_notifier(&vm_notifier); unregister_pm_notifier(&pm_notifier); rcu_barrier(); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Copyright 2023 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ #ifndef __BLUETOOTH_H #define __BLUETOOTH_H #include <linux/poll.h> #include <net/sock.h> #include <linux/seq_file.h> #define BT_SUBSYS_VERSION 2 #define BT_SUBSYS_REVISION 22 #ifndef AF_BLUETOOTH #define AF_BLUETOOTH 31 #define PF_BLUETOOTH AF_BLUETOOTH #endif /* Bluetooth versions */ #define BLUETOOTH_VER_1_1 1 #define BLUETOOTH_VER_1_2 2 #define BLUETOOTH_VER_2_0 3 #define BLUETOOTH_VER_2_1 4 #define BLUETOOTH_VER_4_0 6 /* Reserv for core and drivers use */ #define BT_SKB_RESERVE 8 #define BTPROTO_L2CAP 0 #define BTPROTO_HCI 1 #define BTPROTO_SCO 2 #define BTPROTO_RFCOMM 3 #define BTPROTO_BNEP 4 #define BTPROTO_CMTP 5 #define BTPROTO_HIDP 6 #define BTPROTO_AVDTP 7 #define BTPROTO_ISO 8 #define BTPROTO_LAST BTPROTO_ISO #define SOL_HCI 0 #define SOL_L2CAP 6 #define SOL_SCO 17 #define SOL_RFCOMM 18 #define BT_SECURITY 4 struct bt_security { __u8 level; __u8 key_size; }; #define BT_SECURITY_SDP 0 #define BT_SECURITY_LOW 1 #define BT_SECURITY_MEDIUM 2 #define BT_SECURITY_HIGH 3 #define BT_SECURITY_FIPS 4 #define BT_DEFER_SETUP 7 #define BT_FLUSHABLE 8 #define BT_FLUSHABLE_OFF 0 #define BT_FLUSHABLE_ON 1 #define BT_POWER 9 struct bt_power { __u8 force_active; }; #define BT_POWER_FORCE_ACTIVE_OFF 0 #define BT_POWER_FORCE_ACTIVE_ON 1 #define BT_CHANNEL_POLICY 10 /* BR/EDR only (default policy) * AMP controllers cannot be used. * Channel move requests from the remote device are denied. * If the L2CAP channel is currently using AMP, move the channel to BR/EDR. */ #define BT_CHANNEL_POLICY_BREDR_ONLY 0 /* BR/EDR Preferred * Allow use of AMP controllers. * If the L2CAP channel is currently on AMP, move it to BR/EDR. * Channel move requests from the remote device are allowed. */ #define BT_CHANNEL_POLICY_BREDR_PREFERRED 1 /* AMP Preferred * Allow use of AMP controllers * If the L2CAP channel is currently on BR/EDR and AMP controller * resources are available, initiate a channel move to AMP. * Channel move requests from the remote device are allowed. * If the L2CAP socket has not been connected yet, try to create * and configure the channel directly on an AMP controller rather * than BR/EDR. */ #define BT_CHANNEL_POLICY_AMP_PREFERRED 2 #define BT_VOICE 11 struct bt_voice { __u16 setting; }; #define BT_VOICE_TRANSPARENT 0x0003 #define BT_VOICE_CVSD_16BIT 0x0060 #define BT_VOICE_TRANSPARENT_16BIT 0x0063 #define BT_SNDMTU 12 #define BT_RCVMTU 13 #define BT_PHY 14 #define BT_PHY_BR_1M_1SLOT 0x00000001 #define BT_PHY_BR_1M_3SLOT 0x00000002 #define BT_PHY_BR_1M_5SLOT 0x00000004 #define BT_PHY_EDR_2M_1SLOT 0x00000008 #define BT_PHY_EDR_2M_3SLOT 0x00000010 #define BT_PHY_EDR_2M_5SLOT 0x00000020 #define BT_PHY_EDR_3M_1SLOT 0x00000040 #define BT_PHY_EDR_3M_3SLOT 0x00000080 #define BT_PHY_EDR_3M_5SLOT 0x00000100 #define BT_PHY_LE_1M_TX 0x00000200 #define BT_PHY_LE_1M_RX 0x00000400 #define BT_PHY_LE_2M_TX 0x00000800 #define BT_PHY_LE_2M_RX 0x00001000 #define BT_PHY_LE_CODED_TX 0x00002000 #define BT_PHY_LE_CODED_RX 0x00004000 #define BT_MODE 15 #define BT_MODE_BASIC 0x00 #define BT_MODE_ERTM 0x01 #define BT_MODE_STREAMING 0x02 #define BT_MODE_LE_FLOWCTL 0x03 #define BT_MODE_EXT_FLOWCTL 0x04 #define BT_PKT_STATUS 16 #define BT_SCM_PKT_STATUS 0x03 #define BT_SCM_ERROR 0x04 #define BT_ISO_QOS 17 #define BT_ISO_QOS_CIG_UNSET 0xff #define BT_ISO_QOS_CIS_UNSET 0xff #define BT_ISO_QOS_BIG_UNSET 0xff #define BT_ISO_QOS_BIS_UNSET 0xff #define BT_ISO_SYNC_TIMEOUT 0x07d0 /* 20 secs */ struct bt_iso_io_qos { __u32 interval; __u16 latency; __u16 sdu; __u8 phy; __u8 rtn; }; struct bt_iso_ucast_qos { __u8 cig; __u8 cis; __u8 sca; __u8 packing; __u8 framing; struct bt_iso_io_qos in; struct bt_iso_io_qos out; }; struct bt_iso_bcast_qos { __u8 big; __u8 bis; __u8 sync_factor; __u8 packing; __u8 framing; struct bt_iso_io_qos in; struct bt_iso_io_qos out; __u8 encryption; __u8 bcode[16]; __u8 options; __u16 skip; __u16 sync_timeout; __u8 sync_cte_type; __u8 mse; __u16 timeout; }; struct bt_iso_qos { union { struct bt_iso_ucast_qos ucast; struct bt_iso_bcast_qos bcast; }; }; #define BT_ISO_PHY_1M 0x01 #define BT_ISO_PHY_2M 0x02 #define BT_ISO_PHY_CODED 0x04 #define BT_ISO_PHY_ANY (BT_ISO_PHY_1M | BT_ISO_PHY_2M | \ BT_ISO_PHY_CODED) #define BT_CODEC 19 struct bt_codec_caps { __u8 len; __u8 data[]; } __packed; struct bt_codec { __u8 id; __u16 cid; __u16 vid; __u8 data_path; __u8 num_caps; } __packed; struct bt_codecs { __u8 num_codecs; struct bt_codec codecs[]; } __packed; #define BT_CODEC_CVSD 0x02 #define BT_CODEC_TRANSPARENT 0x03 #define BT_CODEC_MSBC 0x05 #define BT_ISO_BASE 20 __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) void bt_warn(const char *fmt, ...); __printf(1, 2) void bt_err(const char *fmt, ...); #if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) void bt_dbg_set(bool enable); bool bt_dbg_get(void); __printf(1, 2) void bt_dbg(const char *fmt, ...); #endif __printf(1, 2) void bt_warn_ratelimited(const char *fmt, ...); __printf(1, 2) void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) #define BT_WARN(fmt, ...) bt_warn(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) #define BT_DBG(fmt, ...) bt_dbg(fmt "\n", ##__VA_ARGS__) #else #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) #endif #define bt_dev_name(hdev) ((hdev) ? (hdev)->name : "null") #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_warn(hdev, fmt, ...) \ BT_WARN("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ BT_ERR("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_dbg(hdev, fmt, ...) \ BT_DBG("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_warn_ratelimited(hdev, fmt, ...) \ bt_warn_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_err_ratelimited(hdev, fmt, ...) \ bt_err_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) /* Connection and socket states */ enum bt_sock_state { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ BT_OPEN, BT_BOUND, BT_LISTEN, BT_CONNECT, BT_CONNECT2, BT_CONFIG, BT_DISCONN, BT_CLOSED }; /* If unused will be removed by compiler */ static inline const char *state_to_string(int state) { switch (state) { case BT_CONNECTED: return "BT_CONNECTED"; case BT_OPEN: return "BT_OPEN"; case BT_BOUND: return "BT_BOUND"; case BT_LISTEN: return "BT_LISTEN"; case BT_CONNECT: return "BT_CONNECT"; case BT_CONNECT2: return "BT_CONNECT2"; case BT_CONFIG: return "BT_CONFIG"; case BT_DISCONN: return "BT_DISCONN"; case BT_CLOSED: return "BT_CLOSED"; } return "invalid state"; } /* BD Address */ typedef struct { __u8 b[6]; } __packed bdaddr_t; /* BD Address type */ #define BDADDR_BREDR 0x00 #define BDADDR_LE_PUBLIC 0x01 #define BDADDR_LE_RANDOM 0x02 static inline bool bdaddr_type_is_valid(u8 type) { switch (type) { case BDADDR_BREDR: case BDADDR_LE_PUBLIC: case BDADDR_LE_RANDOM: return true; } return false; } static inline bool bdaddr_type_is_le(u8 type) { switch (type) { case BDADDR_LE_PUBLIC: case BDADDR_LE_RANDOM: return true; } return false; } #define BDADDR_ANY (&(bdaddr_t) {{0, 0, 0, 0, 0, 0}}) #define BDADDR_NONE (&(bdaddr_t) {{0xff, 0xff, 0xff, 0xff, 0xff, 0xff}}) /* Copy, swap, convert BD Address */ static inline int bacmp(const bdaddr_t *ba1, const bdaddr_t *ba2) { return memcmp(ba1, ba2, sizeof(bdaddr_t)); } static inline void bacpy(bdaddr_t *dst, const bdaddr_t *src) { memcpy(dst, src, sizeof(bdaddr_t)); } void baswap(bdaddr_t *dst, const bdaddr_t *src); /* Common socket structures and functions */ #define bt_sk(__sk) ((struct bt_sock *) __sk) struct bt_sock { struct sock sk; struct list_head accept_q; struct sock *parent; unsigned long flags; void (*skb_msg_name)(struct sk_buff *, void *, int *); void (*skb_put_cmsg)(struct sk_buff *, struct msghdr *, struct sock *); }; enum { BT_SK_DEFER_SETUP, BT_SK_SUSPEND, BT_SK_PKT_STATUS }; struct bt_sock_list { struct hlist_head head; rwlock_t lock; #ifdef CONFIG_PROC_FS int (* custom_seq_show)(struct seq_file *, void *); #endif }; int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); bool bt_sock_linked(struct bt_sock_list *l, struct sock *s); struct sock *bt_sock_alloc(struct net *net, struct socket *sock, struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); __poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); int bt_sock_wait_ready(struct sock *sk, unsigned int msg_flags); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh); void bt_accept_unlink(struct sock *sk); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock); /* Skb helpers */ struct l2cap_ctrl { u8 sframe:1, poll:1, final:1, fcs:1, sar:2, super:2; u16 reqseq; u16 txseq; u8 retries; __le16 psm; bdaddr_t bdaddr; struct l2cap_chan *chan; }; struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb); void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb); #define HCI_REQ_START BIT(0) #define HCI_REQ_SKB BIT(1) struct hci_ctrl { struct sock *sk; u16 opcode; u8 req_flags; u8 req_event; union { hci_req_complete_t req_complete; hci_req_complete_skb_t req_complete_skb; }; }; struct mgmt_ctrl { struct hci_dev *hdev; u16 opcode; }; struct bt_skb_cb { u8 pkt_type; u8 force_active; u16 expect; u8 incoming:1; u8 pkt_status:2; union { struct l2cap_ctrl l2cap; struct hci_ctrl hci; struct mgmt_ctrl mgmt; struct scm_creds creds; }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) #define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type #define hci_skb_pkt_status(skb) bt_cb((skb))->pkt_status #define hci_skb_expect(skb) bt_cb((skb))->expect #define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode #define hci_skb_event(skb) bt_cb((skb))->hci.req_event #define hci_skb_sk(skb) bt_cb((skb))->hci.sk static inline struct sk_buff *bt_skb_alloc(unsigned int len, gfp_t how) { struct sk_buff *skb; skb = alloc_skb(len + BT_SKB_RESERVE, how); if (skb) skb_reserve(skb, BT_SKB_RESERVE); return skb; } static inline struct sk_buff *bt_skb_send_alloc(struct sock *sk, unsigned long len, int nb, int *err) { struct sk_buff *skb; skb = sock_alloc_send_skb(sk, len + BT_SKB_RESERVE, nb, err); if (skb) skb_reserve(skb, BT_SKB_RESERVE); if (!skb && *err) return NULL; *err = sock_error(sk); if (*err) goto out; if (sk->sk_shutdown) { *err = -ECONNRESET; goto out; } return skb; out: kfree_skb(skb); return NULL; } /* Shall not be called with lock_sock held */ static inline struct sk_buff *bt_skb_sendmsg(struct sock *sk, struct msghdr *msg, size_t len, size_t mtu, size_t headroom, size_t tailroom) { struct sk_buff *skb; size_t size = min_t(size_t, len, mtu); int err; skb = bt_skb_send_alloc(sk, size + headroom + tailroom, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) return ERR_PTR(err); skb_reserve(skb, headroom); skb_tailroom_reserve(skb, mtu, tailroom); if (!copy_from_iter_full(skb_put(skb, size), size, &msg->msg_iter)) { kfree_skb(skb); return ERR_PTR(-EFAULT); } skb->priority = READ_ONCE(sk->sk_priority); return skb; } /* Similar to bt_skb_sendmsg but can split the msg into multiple fragments * accourding to the MTU. */ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, struct msghdr *msg, size_t len, size_t mtu, size_t headroom, size_t tailroom) { struct sk_buff *skb, **frag; skb = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); if (IS_ERR(skb)) return skb; len -= skb->len; if (!len) return skb; /* Add remaining data over MTU as continuation fragments */ frag = &skb_shinfo(skb)->frag_list; while (len) { struct sk_buff *tmp; tmp = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); if (IS_ERR(tmp)) { return skb; } len -= tmp->len; *frag = tmp; frag = &(*frag)->next; } return skb; } int bt_to_errno(u16 code); __u8 bt_status(int err); void hci_sock_set_flag(struct sock *sk, int nr); void hci_sock_clear_flag(struct sock *sk, int nr); int hci_sock_test_flag(struct sock *sk, int nr); unsigned short hci_sock_get_channel(struct sock *sk); u32 hci_sock_get_cookie(struct sock *sk); int hci_sock_init(void); void hci_sock_cleanup(void); int bt_sysfs_init(void); void bt_sysfs_cleanup(void); int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (*seq_show)(struct seq_file *, void *)); void bt_procfs_cleanup(struct net *net, const char *name); extern struct dentry *bt_debugfs; int l2cap_init(void); void l2cap_exit(void); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_init(void); void sco_exit(void); #else static inline int sco_init(void) { return 0; } static inline void sco_exit(void) { } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_init(void); int iso_exit(void); bool iso_enabled(void); #else static inline int iso_init(void) { return 0; } static inline int iso_exit(void) { return 0; } static inline bool iso_enabled(void) { return false; } #endif int mgmt_init(void); void mgmt_exit(void); void mgmt_cleanup(struct sock *sk); void bt_sock_reclassify_lock(struct sock *sk, int proto); #endif /* __BLUETOOTH_H */ |
| 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kernfs.h - pseudo filesystem decoupled from vfs locking */ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/idr.h> #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/types.h> #include <linux/uidgid.h> #include <linux/wait.h> #include <linux/rwsem.h> #include <linux/cache.h> struct file; struct dentry; struct iattr; struct seq_file; struct vm_area_struct; struct vm_operations_struct; struct super_block; struct file_system_type; struct poll_table_struct; struct fs_context; struct kernfs_fs_context; struct kernfs_open_node; struct kernfs_iattrs; /* * NR_KERNFS_LOCK_BITS determines size (NR_KERNFS_LOCKS) of hash * table of locks. * Having a small hash table would impact scalability, since * more and more kernfs_node objects will end up using same lock * and having a very large hash table would waste memory. * * At the moment size of hash table of locks is being set based on * the number of CPUs as follows: * * NR_CPU NR_KERNFS_LOCK_BITS NR_KERNFS_LOCKS * 1 1 2 * 2-3 2 4 * 4-7 4 16 * 8-15 6 64 * 16-31 8 256 * 32 and more 10 1024 * * The above relation between NR_CPU and number of locks is based * on some internal experimentation which involved booting qemu * with different values of smp, performing some sysfs operations * on all CPUs and observing how increase in number of locks impacts * completion time of these sysfs operations on each CPU. */ #ifdef CONFIG_SMP #define NR_KERNFS_LOCK_BITS (2 * (ilog2(NR_CPUS < 32 ? NR_CPUS : 32))) #else #define NR_KERNFS_LOCK_BITS 1 #endif #define NR_KERNFS_LOCKS (1 << NR_KERNFS_LOCK_BITS) /* * There's one kernfs_open_file for each open file and one kernfs_open_node * for each kernfs_node with one or more open files. * * filp->private_data points to seq_file whose ->private points to * kernfs_open_file. * * kernfs_open_files are chained at kernfs_open_node->files, which is * protected by kernfs_global_locks.open_file_mutex[i]. * * To reduce possible contention in sysfs access, arising due to single * locks, use an array of locks (e.g. open_file_mutex) and use kernfs_node * object address as hash keys to get the index of these locks. * * Hashed mutexes are safe to use here because operations using these don't * rely on global exclusion. * * In future we intend to replace other global locks with hashed ones as well. * kernfs_global_locks acts as a holder for all such hash tables. */ struct kernfs_global_locks { struct mutex open_file_mutex[NR_KERNFS_LOCKS]; }; enum kernfs_node_type { KERNFS_DIR = 0x0001, KERNFS_FILE = 0x0002, KERNFS_LINK = 0x0004, }; #define KERNFS_TYPE_MASK 0x000f #define KERNFS_FLAG_MASK ~KERNFS_TYPE_MASK #define KERNFS_MAX_USER_XATTRS 128 #define KERNFS_USER_XATTR_SIZE_LIMIT (128 << 10) enum kernfs_node_flag { KERNFS_ACTIVATED = 0x0010, KERNFS_NS = 0x0020, KERNFS_HAS_SEQ_SHOW = 0x0040, KERNFS_HAS_MMAP = 0x0080, KERNFS_LOCKDEP = 0x0100, KERNFS_HIDDEN = 0x0200, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, KERNFS_HAS_RELEASE = 0x2000, KERNFS_REMOVING = 0x4000, }; /* @flags for kernfs_create_root() */ enum kernfs_root_flag { /* * kernfs_nodes are created in the deactivated state and invisible. * They require explicit kernfs_activate() to become visible. This * can be used to make related nodes become visible atomically * after all nodes are created successfully. */ KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, /* * For regular files, if the opener has CAP_DAC_OVERRIDE, open(2) * succeeds regardless of the RW permissions. sysfs had an extra * layer of enforcement where open(2) fails with -EACCES regardless * of CAP_DAC_OVERRIDE if the permission doesn't have the * respective read or write access at all (none of S_IRUGO or * S_IWUGO) or the respective operation isn't implemented. The * following flag enables that behavior. */ KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, /* * The filesystem supports exportfs operation, so userspace can use * fhandle to access nodes of the fs. */ KERNFS_ROOT_SUPPORT_EXPORTOP = 0x0004, /* * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, /* * Renames must not change the parent node. */ KERNFS_ROOT_INVARIANT_PARENT = 0x0010, }; /* type-specific structures for kernfs_node union members */ struct kernfs_elem_dir { unsigned long subdirs; /* children rbtree starts here and goes through kn->rb */ struct rb_root children; /* * The kernfs hierarchy this directory belongs to. This fits * better directly in kernfs_node but is here to save space. */ struct kernfs_root *root; /* * Monotonic revision counter, used to identify if a directory * node has changed during negative dentry revalidation. */ unsigned long rev; }; struct kernfs_elem_symlink { struct kernfs_node *target_kn; }; struct kernfs_elem_attr { const struct kernfs_ops *ops; struct kernfs_open_node __rcu *open; loff_t size; struct kernfs_node *notify_next; /* for kernfs_notify() */ }; /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are * private to kernfs and shouldn't be accessed directly by kernfs users. * * As long as count reference is held, the kernfs_node itself is * accessible. Dereferencing elem or any other outer entity requires * active reference. */ struct kernfs_node { atomic_t count; atomic_t active; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* * Use kernfs_get_parent() and kernfs_name/path() instead of * accessing the following two fields directly. If the node is * never moved to a different parent, it is safe to access the * parent directly. */ struct kernfs_node __rcu *__parent; const char __rcu *name; struct rb_node rb; const void *ns; /* namespace tag */ unsigned int hash; /* ns + name hash */ unsigned short flags; umode_t mode; union { struct kernfs_elem_dir dir; struct kernfs_elem_symlink symlink; struct kernfs_elem_attr attr; }; /* * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, * the low 32bits are ino and upper generation. */ u64 id; void *priv; struct kernfs_iattrs *iattr; struct rcu_head rcu; }; /* * kernfs_syscall_ops may be specified on kernfs_create_root() to support * syscalls. These optional callbacks are invoked on the matching syscalls * and can perform any kernfs operations which don't necessarily have to be * the exact operation requested. An active reference is held for each * kernfs_node parameter. */ struct kernfs_syscall_ops { int (*show_options)(struct seq_file *sf, struct kernfs_root *root); int (*mkdir)(struct kernfs_node *parent, const char *name, umode_t mode); int (*rmdir)(struct kernfs_node *kn); int (*rename)(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name); int (*show_path)(struct seq_file *sf, struct kernfs_node *kn, struct kernfs_root *root); }; struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root); struct kernfs_open_file { /* published fields */ struct kernfs_node *kn; struct file *file; struct seq_file *seq_file; void *priv; /* private fields, do not use outside kernfs proper */ struct mutex mutex; struct mutex prealloc_mutex; int event; struct list_head list; char *prealloc_buf; size_t atomic_write_len; bool mmapped:1; bool released:1; const struct vm_operations_struct *vm_ops; }; struct kernfs_ops { /* * Optional open/release methods. Both are called with * @of->seq_file populated. */ int (*open)(struct kernfs_open_file *of); void (*release)(struct kernfs_open_file *of); /* * Read is handled by either seq_file or raw_read(). * * If seq_show() is present, seq_file path is active. Other seq * operations are optional and if not implemented, the behavior is * equivalent to single_open(). @sf->private points to the * associated kernfs_open_file. * * read() is bounced through kernel buffer and a read larger than * PAGE_SIZE results in partial operation of PAGE_SIZE. */ int (*seq_show)(struct seq_file *sf, void *v); void *(*seq_start)(struct seq_file *sf, loff_t *ppos); void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); void (*seq_stop)(struct seq_file *sf, void *v); ssize_t (*read)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); /* * write() is bounced through kernel buffer. If atomic_write_len * is not set, a write larger than PAGE_SIZE results in partial * operations of PAGE_SIZE chunks. If atomic_write_len is set, * writes upto the specified size are executed atomically but * larger ones are rejected with -E2BIG. */ size_t atomic_write_len; /* * "prealloc" causes a buffer to be allocated at open for * all read/write requests. As ->seq_show uses seq_read() * which does its own allocation, it is incompatible with * ->prealloc. Provide ->read and ->write with ->prealloc. */ bool prealloc; ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence); }; /* * The kernfs superblock creation/mount parameter context. */ struct kernfs_fs_context { struct kernfs_root *root; /* Root of the hierarchy being mounted */ void *ns_tag; /* Namespace tag of the mount (or NULL) */ unsigned long magic; /* File system specific magic number */ /* The following are set/used by kernfs_mount() */ bool new_sb_created; /* Set to T if we allocated a new sb */ }; #ifdef CONFIG_KERNFS static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return kn->flags & KERNFS_TYPE_MASK; } static inline ino_t kernfs_id_ino(u64 id) { /* id is ino if ino_t is 64bit; otherwise, low 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return id; else return (u32)id; } static inline u32 kernfs_id_gen(u64 id) { /* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return 1; else return id >> 32; } static inline ino_t kernfs_ino(struct kernfs_node *kn) { return kernfs_id_ino(kn->id); } static inline ino_t kernfs_gen(struct kernfs_node *kn) { return kernfs_id_gen(kn->id); } /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty * * This is to be called right after @kn is created to enable namespace * under it. All children of @kn must have non-NULL namespace tags and * only the ones which match the super_block's tag will be visible. */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); WARN_ON_ONCE(!RB_EMPTY_ROOT(&kn->dir.children)); kn->flags |= KERNFS_NS; } /** * kernfs_ns_enabled - test whether namespace is enabled * @kn: the node to test * * Test whether namespace filtering is enabled for the children of @ns. */ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return kn->flags & KERNFS_NS; } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); int kernfs_path_from_node(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn); struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns); struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns); void kernfs_get(struct kernfs_node *kn); void kernfs_put(struct kernfs_node *kn); struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct super_block *sb); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); unsigned int kernfs_root_flags(struct kernfs_node *kn); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns); struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key); struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target); void kernfs_activate(struct kernfs_node *kn); void kernfs_show(struct kernfs_node *kn, bool show); void kernfs_remove(struct kernfs_node *kn); void kernfs_break_active_protection(struct kernfs_node *kn); void kernfs_unbreak_active_protection(struct kernfs_node *kn); bool kernfs_remove_self(struct kernfs_node *kn); int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns); int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); __poll_t kernfs_generic_poll(struct kernfs_open_file *of, struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size); int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags); const void *kernfs_super_ns(struct super_block *sb); int kernfs_get_tree(struct fs_context *fc); void kernfs_free_fs_context(struct fs_context *fc); void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return 0; } /* whatever */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { } static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return false; } static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { } static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { return NULL; } static inline struct kernfs_node * kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { return NULL; } static inline struct kernfs_node * kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { return NULL; } static inline void kernfs_get(struct kernfs_node *kn) { } static inline void kernfs_put(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { return NULL; } static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { return NULL; } static inline struct inode * kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) { return NULL; } static inline struct kernfs_root * kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } static inline unsigned int kernfs_root_flags(struct kernfs_node *kn) { return 0; } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target) { return ERR_PTR(-ENOSYS); } static inline void kernfs_activate(struct kernfs_node *kn) { } static inline void kernfs_remove(struct kernfs_node *kn) { } static inline bool kernfs_remove_self(struct kernfs_node *kn) { return false; } static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn, const char *name, const void *ns) { return -ENOSYS; } static inline int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { return -ENOSYS; } static inline int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { return -ENOSYS; } static inline __poll_t kernfs_generic_poll(struct kernfs_open_file *of, struct poll_table_struct *pt) { return -ENOSYS; } static inline void kernfs_notify(struct kernfs_node *kn) { } static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size) { return -ENOSYS; } static inline int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags) { return -ENOSYS; } static inline const void *kernfs_super_ns(struct super_block *sb) { return NULL; } static inline int kernfs_get_tree(struct fs_context *fc) { return -ENOSYS; } static inline void kernfs_free_fs_context(struct fs_context *fc) { } static inline void kernfs_kill_sb(struct super_block *sb) { } static inline void kernfs_init(void) { } #endif /* CONFIG_KERNFS */ /** * kernfs_path - build full path of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * If @kn is NULL result will be "(null)". * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { return kernfs_path_from_node(kn, NULL, buf, buflen); } static inline struct kernfs_node * kernfs_find_and_get(struct kernfs_node *kn, const char *name) { return kernfs_find_and_get_ns(kn, name, NULL); } static inline struct kernfs_node * kernfs_walk_and_get(struct kernfs_node *kn, const char *path) { return kernfs_walk_and_get_ns(kn, path, NULL); } static inline struct kernfs_node * kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, void *priv) { return kernfs_create_dir_ns(parent, name, mode, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, priv, NULL); } static inline int kernfs_remove_by_name(struct kernfs_node *parent, const char *name) { return kernfs_remove_by_name_ns(parent, name, NULL); } static inline int kernfs_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name) { return kernfs_rename_ns(kn, new_parent, new_name, NULL); } #endif /* __LINUX_KERNFS_H */ |
| 2174 2169 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Detect hard and soft lockups on a system * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * * Note: Most of this code is borrowed heavily from the original softlockup * detector, so thanks to Ingo for the initial implementation. * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ #define pr_fmt(fmt) "watchdog: " fmt #include <linux/cpu.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/kvm_para.h> #include <linux/math64.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/nmi.h> #include <linux/stop_machine.h> #include <linux/sysctl.h> #include <linux/tick.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <asm/irq_regs.h> static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64) # define WATCHDOG_HARDLOCKUP_DEFAULT 1 #else # define WATCHDOG_HARDLOCKUP_DEFAULT 0 #endif #define NUM_SAMPLE_PERIODS 5 unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = 1; static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT; static int __read_mostly watchdog_softlockup_user_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly watchdog_hardlockup_available; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #ifdef CONFIG_HARDLOCKUP_DETECTOR # ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; # endif /* CONFIG_SMP */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ unsigned int __read_mostly hardlockup_panic = IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC); /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these * cases this function can be called to disable hard lockup detection. This * function should only be executed once by the boot processor before the * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ void __init hardlockup_detector_disable(void) { watchdog_hardlockup_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) { next: if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) watchdog_hardlockup_user_enabled = 0; else if (!strncmp(str, "1", 1)) watchdog_hardlockup_user_enabled = 1; else if (!strncmp(str, "r", 1)) hardlockup_config_perf_event(str + 1); while (*(str++)) { if (*str == ',') { str++; goto next; } } return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); #endif /* CONFIG_HARDLOCKUP_DETECTOR */ #if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER) static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts); static DEFINE_PER_CPU(int, hrtimer_interrupts_saved); static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned); static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched); static unsigned long hard_lockup_nmi_warn; notrace void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have * preemption enabled. If preemption is enabled * then interrupts should be enabled too, in which * case we shouldn't have to worry about the watchdog * going off. */ raw_cpu_write(watchdog_hardlockup_touched, true); } EXPORT_SYMBOL(arch_touch_nmi_watchdog); void watchdog_hardlockup_touch_cpu(unsigned int cpu) { per_cpu(watchdog_hardlockup_touched, cpu) = true; } static bool is_hardlockup(unsigned int cpu) { int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu)); if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint) return true; /* * NOTE: we don't need any fancy atomic_t or READ_ONCE/WRITE_ONCE * for hrtimer_interrupts_saved. hrtimer_interrupts_saved is * written/read by a single CPU. */ per_cpu(hrtimer_interrupts_saved, cpu) = hrint; return false; } static void watchdog_hardlockup_kick(void) { int new_interrupts; new_interrupts = atomic_inc_return(this_cpu_ptr(&hrtimer_interrupts)); watchdog_buddy_check_hardlockup(new_interrupts); } void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) { if (per_cpu(watchdog_hardlockup_touched, cpu)) { per_cpu(watchdog_hardlockup_touched, cpu) = false; return; } /* * Check for a hardlockup by making sure the CPU's timer * interrupt is incrementing. The timer interrupt should have * fired multiple times before we overflow'd. If it hasn't * then this is a good indication the cpu is stuck */ if (is_hardlockup(cpu)) { unsigned int this_cpu = smp_processor_id(); unsigned long flags; /* Only print hardlockups once. */ if (per_cpu(watchdog_hardlockup_warned, cpu)) return; /* * Prevent multiple hard-lockup reports if one cpu is already * engaged in dumping all cpu back traces. */ if (sysctl_hardlockup_all_cpu_backtrace) { if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn)) return; } /* * NOTE: we call printk_cpu_sync_get_irqsave() after printing * the lockup message. While it would be nice to serialize * that printout, we really want to make sure that if some * other CPU somehow locked up while holding the lock associated * with printk_cpu_sync_get_irqsave() that we can still at least * get the message about the lockup out. */ pr_emerg("CPU%u: Watchdog detected hard LOCKUP on cpu %u\n", this_cpu, cpu); printk_cpu_sync_get_irqsave(flags); print_modules(); print_irqtrace_events(current); if (cpu == this_cpu) { if (regs) show_regs(regs); else dump_stack(); printk_cpu_sync_put_irqrestore(flags); } else { printk_cpu_sync_put_irqrestore(flags); trigger_single_cpu_backtrace(cpu); } if (sysctl_hardlockup_all_cpu_backtrace) { trigger_allbutcpu_cpu_backtrace(cpu); if (!hardlockup_panic) clear_bit_unlock(0, &hard_lockup_nmi_warn); } if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); per_cpu(watchdog_hardlockup_warned, cpu) = true; } else { per_cpu(watchdog_hardlockup_warned, cpu) = false; } } #else /* CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ static inline void watchdog_hardlockup_kick(void) { } #endif /* !CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ /* * These functions can be overridden based on the configured hardlockdup detector. * * watchdog_hardlockup_enable/disable can be implemented to start and stop when * softlockup watchdog start and stop. The detector must select the * SOFTLOCKUP_DETECTOR Kconfig. */ void __weak watchdog_hardlockup_enable(unsigned int cpu) { } void __weak watchdog_hardlockup_disable(unsigned int cpu) { } /* * Watchdog-detector specific API. * * Return 0 when hardlockup watchdog is available, negative value otherwise. * Note that the negative value means that a delayed probe might * succeed later. */ int __weak __init watchdog_hardlockup_probe(void) { return -ENODEV; } /** * watchdog_hardlockup_stop - Stop the watchdog for reconfiguration * * The reconfiguration steps are: * watchdog_hardlockup_stop(); * update_variables(); * watchdog_hardlockup_start(); */ void __weak watchdog_hardlockup_stop(void) { } /** * watchdog_hardlockup_start - Start the watchdog after reconfiguration * * Counterpart to watchdog_hardlockup_stop(). * * The following variables have been updated in update_variables() and * contain the currently valid configuration: * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask */ void __weak watchdog_hardlockup_start(void) { } /** * lockup_detector_update_enable - Update the sysctl enable bit * * Caller needs to make sure that the hard watchdogs are off, so this * can't race with watchdog_hardlockup_disable(). */ static void lockup_detector_update_enable(void) { watchdog_enabled = 0; if (!watchdog_user_enabled) return; if (watchdog_hardlockup_available && watchdog_hardlockup_user_enabled) watchdog_enabled |= WATCHDOG_HARDLOCKUP_ENABLED; if (watchdog_softlockup_user_enabled) watchdog_enabled |= WATCHDOG_SOFTOCKUP_ENABLED; } #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * Delay the soflockup report when running a known slow code. * It does _not_ affect the timestamp of the last successdul reschedule. */ #define SOFTLOCKUP_DELAY_REPORT ULONG_MAX #ifdef CONFIG_SMP int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif static struct cpumask watchdog_allowed_mask __read_mostly; /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = IS_ENABLED(CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC); static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; /* Timestamp taken after the last successful reschedule. */ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); /* Timestamp of the last softlockup report. */ static DEFINE_PER_CPU(unsigned long, watchdog_report_ts); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static unsigned long soft_lockup_nmi_warn; static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { watchdog_softlockup_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); static int __init watchdog_thresh_setup(char *str) { get_option(&str, &watchdog_thresh); return 1; } __setup("watchdog_thresh=", watchdog_thresh_setup); #ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM enum stats_per_group { STATS_SYSTEM, STATS_SOFTIRQ, STATS_HARDIRQ, STATS_IDLE, NUM_STATS_PER_GROUP, }; static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = { CPUTIME_SYSTEM, CPUTIME_SOFTIRQ, CPUTIME_IRQ, CPUTIME_IDLE, }; static DEFINE_PER_CPU(u16, cpustat_old[NUM_STATS_PER_GROUP]); static DEFINE_PER_CPU(u8, cpustat_util[NUM_SAMPLE_PERIODS][NUM_STATS_PER_GROUP]); static DEFINE_PER_CPU(u8, cpustat_tail); /* * We don't need nanosecond resolution. A granularity of 16ms is * sufficient for our precision, allowing us to use u16 to store * cpustats, which will roll over roughly every ~1000 seconds. * 2^24 ~= 16 * 10^6 */ static u16 get_16bit_precision(u64 data_ns) { return data_ns >> 24LL; /* 2^24ns ~= 16.8ms */ } static void update_cpustat(void) { int i; u8 util; u16 old_stat, new_stat; struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u8 tail = __this_cpu_read(cpustat_tail); u16 sample_period_16 = get_16bit_precision(sample_period); kcpustat_cpu_fetch(&kcpustat, smp_processor_id()); for (i = 0; i < NUM_STATS_PER_GROUP; i++) { old_stat = __this_cpu_read(cpustat_old[i]); new_stat = get_16bit_precision(cpustat[tracked_stats[i]]); util = DIV_ROUND_UP(100 * (new_stat - old_stat), sample_period_16); __this_cpu_write(cpustat_util[tail][i], util); __this_cpu_write(cpustat_old[i], new_stat); } __this_cpu_write(cpustat_tail, (tail + 1) % NUM_SAMPLE_PERIODS); } static void print_cpustat(void) { int i, group; u8 tail = __this_cpu_read(cpustat_tail); u64 sample_period_second = sample_period; do_div(sample_period_second, NSEC_PER_SEC); /* * Outputting the "watchdog" prefix on every line is redundant and not * concise, and the original alarm information is sufficient for * positioning in logs, hence here printk() is used instead of pr_crit(). */ printk(KERN_CRIT "CPU#%d Utilization every %llus during lockup:\n", smp_processor_id(), sample_period_second); for (i = 0; i < NUM_SAMPLE_PERIODS; i++) { group = (tail + i) % NUM_SAMPLE_PERIODS; printk(KERN_CRIT "\t#%d: %3u%% system,\t%3u%% softirq,\t" "%3u%% hardirq,\t%3u%% idle\n", i + 1, __this_cpu_read(cpustat_util[group][STATS_SYSTEM]), __this_cpu_read(cpustat_util[group][STATS_SOFTIRQ]), __this_cpu_read(cpustat_util[group][STATS_HARDIRQ]), __this_cpu_read(cpustat_util[group][STATS_IDLE])); } } #define HARDIRQ_PERCENT_THRESH 50 #define NUM_HARDIRQ_REPORT 5 struct irq_counts { int irq; u32 counts; }; static DEFINE_PER_CPU(bool, snapshot_taken); /* Tabulate the most frequent interrupts. */ static void tabulate_irq_count(struct irq_counts *irq_counts, int irq, u32 counts, int rank) { int i; struct irq_counts new_count = {irq, counts}; for (i = 0; i < rank; i++) { if (counts > irq_counts[i].counts) swap(new_count, irq_counts[i]); } } /* * If the hardirq time exceeds HARDIRQ_PERCENT_THRESH% of the sample_period, * then the cause of softlockup might be interrupt storm. In this case, it * would be useful to start interrupt counting. */ static bool need_counting_irqs(void) { u8 util; int tail = __this_cpu_read(cpustat_tail); tail = (tail + NUM_HARDIRQ_REPORT - 1) % NUM_HARDIRQ_REPORT; util = __this_cpu_read(cpustat_util[tail][STATS_HARDIRQ]); return util > HARDIRQ_PERCENT_THRESH; } static void start_counting_irqs(void) { if (!__this_cpu_read(snapshot_taken)) { kstat_snapshot_irqs(); __this_cpu_write(snapshot_taken, true); } } static void stop_counting_irqs(void) { __this_cpu_write(snapshot_taken, false); } static void print_irq_counts(void) { unsigned int i, count; struct irq_counts irq_counts_sorted[NUM_HARDIRQ_REPORT] = { {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0} }; if (__this_cpu_read(snapshot_taken)) { for_each_active_irq(i) { count = kstat_get_irq_since_snapshot(i); tabulate_irq_count(irq_counts_sorted, i, count, NUM_HARDIRQ_REPORT); } /* * Outputting the "watchdog" prefix on every line is redundant and not * concise, and the original alarm information is sufficient for * positioning in logs, hence here printk() is used instead of pr_crit(). */ printk(KERN_CRIT "CPU#%d Detect HardIRQ Time exceeds %d%%. Most frequent HardIRQs:\n", smp_processor_id(), HARDIRQ_PERCENT_THRESH); for (i = 0; i < NUM_HARDIRQ_REPORT; i++) { if (irq_counts_sorted[i].irq == -1) break; printk(KERN_CRIT "\t#%u: %-10u\tirq#%d\n", i + 1, irq_counts_sorted[i].counts, irq_counts_sorted[i].irq); } /* * If the hardirq time is less than HARDIRQ_PERCENT_THRESH% in the last * sample_period, then we suspect the interrupt storm might be subsiding. */ if (!need_counting_irqs()) stop_counting_irqs(); } } static void report_cpu_status(void) { print_cpustat(); print_irq_counts(); } #else static inline void update_cpustat(void) { } static inline void report_cpu_status(void) { } static inline bool need_counting_irqs(void) { return false; } static inline void start_counting_irqs(void) { } static inline void stop_counting_irqs(void) { } #endif /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally * want a higher threshold for soft lockups than for hard lockups. So we couple * the thresholds with a factor: we make the soft threshold twice the amount of * time the hard threshold is. */ static int get_softlockup_thresh(void) { return watchdog_thresh * 2; } /* * Returns seconds, approximately. We don't need nanosecond * resolution, and we don't need to waste time with a big divide when * 2^30ns == 1.074s. */ static unsigned long get_timestamp(void) { return running_clock() >> 30LL; /* 2^30 ~= 10^9 */ } static void set_sample_period(void) { /* * convert watchdog_thresh from seconds to ns * the divide by 5 is to give hrtimer several chances (two * or three with the current relation between the soft * and hard thresholds) to increment before the * hardlockup detector generates a warning */ sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / NUM_SAMPLE_PERIODS); watchdog_update_hrtimer_threshold(sample_period); } static void update_report_ts(void) { __this_cpu_write(watchdog_report_ts, get_timestamp()); } /* Commands for resetting the watchdog */ static void update_touch_ts(void) { __this_cpu_write(watchdog_touch_ts, get_timestamp()); update_report_ts(); } /** * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls * * Call when the scheduler may have stalled for legitimate reasons * preventing the watchdog task from executing - e.g. the scheduler * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ notrace void touch_softlockup_watchdog_sched(void) { /* * Preemption can be enabled. It doesn't matter which CPU's watchdog * report period gets restarted here, so use the raw_ operation. */ raw_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } notrace void touch_softlockup_watchdog(void) { touch_softlockup_watchdog_sched(); wq_watchdog_touch(raw_smp_processor_id()); } EXPORT_SYMBOL(touch_softlockup_watchdog); void touch_all_softlockup_watchdogs(void) { int cpu; /* * watchdog_mutex cannpt be taken here, as this might be called * from (soft)interrupt context, so the access to * watchdog_allowed_cpumask might race with a concurrent update. * * The watchdog time stamp can race against a concurrent real * update as well, the only side effect might be a cycle delay for * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) { per_cpu(watchdog_report_ts, cpu) = SOFTLOCKUP_DELAY_REPORT; wq_watchdog_touch(cpu); } } void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); __this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } static int is_softlockup(unsigned long touch_ts, unsigned long period_ts, unsigned long now) { if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) { /* * If period_ts has not been updated during a sample_period, then * in the subsequent few sample_periods, period_ts might also not * be updated, which could indicate a potential softlockup. In * this case, if we suspect the cause of the potential softlockup * might be interrupt storm, then we need to count the interrupts * to find which interrupt is storming. */ if (time_after_eq(now, period_ts + get_softlockup_thresh() / NUM_SAMPLE_PERIODS) && need_counting_irqs()) start_counting_irqs(); /* * A poorly behaving BPF scheduler can live-lock the system into * soft lockups. Tell sched_ext to try ejecting the BPF * scheduler when close to a soft lockup. */ if (time_after_eq(now, period_ts + get_softlockup_thresh() * 3 / 4)) scx_softlockup(now - touch_ts); /* Warn about unreasonable delays. */ if (time_after(now, period_ts + get_softlockup_thresh())) return now - touch_ts; } return 0; } /* watchdog detector functions */ static DEFINE_PER_CPU(struct completion, softlockup_completion); static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); /* * The watchdog feed function - touches the timestamp. * * It only runs once every sample_period seconds (4 seconds by * default) to reset the softlockup timestamp. If this gets delayed * for more than 2*watchdog_thresh seconds then the debug-printout * triggers in watchdog_timer_fn(). */ static int softlockup_fn(void *data) { update_touch_ts(); stop_counting_irqs(); complete(this_cpu_ptr(&softlockup_completion)); return 0; } /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts, period_ts, now; struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; unsigned long flags; if (!watchdog_enabled) return HRTIMER_NORESTART; watchdog_hardlockup_kick(); /* kick the softlockup detector */ if (completion_done(this_cpu_ptr(&softlockup_completion))) { reinit_completion(this_cpu_ptr(&softlockup_completion)); stop_one_cpu_nowait(smp_processor_id(), softlockup_fn, NULL, this_cpu_ptr(&softlockup_stop_work)); } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); /* * Read the current timestamp first. It might become invalid anytime * when a virtual machine is stopped by the host or when the watchog * is touched from NMI. */ now = get_timestamp(); /* * If a virtual machine is stopped by the host it can look to * the watchdog like a soft lockup. This function touches the watchdog. */ kvm_check_and_clear_guest_paused(); /* * The stored timestamp is comparable with @now only when not touched. * It might get touched anytime from NMI. Make sure that is_softlockup() * uses the same (valid) value. */ period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); update_cpustat(); /* Reset the interval when touched by known problematic code. */ if (period_ts == SOFTLOCKUP_DELAY_REPORT) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically * make sure the scheduler tick is up to date. */ __this_cpu_write(softlockup_touch_sync, false); sched_clock_tick(); } update_report_ts(); return HRTIMER_RESTART; } /* Check for a softlockup. */ touch_ts = __this_cpu_read(watchdog_touch_ts); duration = is_softlockup(touch_ts, period_ts, now); if (unlikely(duration)) { /* * Prevent multiple soft-lockup reports if one cpu is already * engaged in dumping all cpu back traces. */ if (softlockup_all_cpu_backtrace) { if (test_and_set_bit_lock(0, &soft_lockup_nmi_warn)) return HRTIMER_RESTART; } /* Start period for the next softlockup warning. */ update_report_ts(); printk_cpu_sync_get_irqsave(flags); pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); report_cpu_status(); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); printk_cpu_sync_put_irqrestore(flags); if (softlockup_all_cpu_backtrace) { trigger_allbutcpu_cpu_backtrace(smp_processor_id()); if (!softlockup_panic) clear_bit_unlock(0, &soft_lockup_nmi_warn); } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); if (softlockup_panic) panic("softlockup: hung tasks"); } return HRTIMER_RESTART; } static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); struct completion *done = this_cpu_ptr(&softlockup_completion); WARN_ON_ONCE(cpu != smp_processor_id()); init_completion(done); complete(done); /* * Start the timer first to prevent the hardlockup watchdog triggering * before the timer has a chance to fire. */ hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED_HARD); /* Initialize timestamp */ update_touch_ts(); /* Enable the hardlockup detector */ if (watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED) watchdog_hardlockup_enable(cpu); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); WARN_ON_ONCE(cpu != smp_processor_id()); /* * Disable the hardlockup detector first. That prevents that a large * delay between disabling the timer and disabling the hardlockup * detector causes a false positive. */ watchdog_hardlockup_disable(cpu); hrtimer_cancel(hrtimer); wait_for_completion(this_cpu_ptr(&softlockup_completion)); } static int softlockup_stop_fn(void *data) { watchdog_disable(smp_processor_id()); return 0; } static void softlockup_stop_all(void) { int cpu; if (!softlockup_initialized) return; for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); cpumask_clear(&watchdog_allowed_mask); } static int softlockup_start_fn(void *data) { watchdog_enable(smp_processor_id()); return 0; } static void softlockup_start_all(void) { int cpu; cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } int lockup_detector_online_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_disable(cpu); return 0; } static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_hardlockup_stop(); softlockup_stop_all(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) softlockup_start_all(); watchdog_hardlockup_start(); cpus_read_unlock(); } void lockup_detector_reconfigure(void) { mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(); mutex_unlock(&watchdog_mutex); } /* * Create the watchdog infrastructure and configure the detector(s). */ static __init void lockup_detector_setup(void) { /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. */ lockup_detector_update_enable(); if (!IS_ENABLED(CONFIG_SYSCTL) && !(watchdog_enabled && watchdog_thresh)) return; mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(); softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_hardlockup_stop(); lockup_detector_update_enable(); watchdog_hardlockup_start(); cpus_read_unlock(); } void lockup_detector_reconfigure(void) { __lockup_detector_reconfigure(); } static inline void lockup_detector_setup(void) { __lockup_detector_reconfigure(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ /** * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) * * Special interface for parisc. It prevents lockup detector warnings from * the default pm_poweroff() function which busy loops forever. */ void lockup_detector_soft_poweroff(void) { watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL /* Propagate any changes to the watchdog infrastructure */ static void proc_watchdog_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); __lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * * caller | table->data points to | 'which' * -------------------|----------------------------------|------------------------------- * proc_watchdog | watchdog_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED | * | | WATCHDOG_SOFTOCKUP_ENABLED * -------------------|----------------------------------|------------------------------- * proc_nmi_watchdog | watchdog_hardlockup_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED * -------------------|----------------------------------|------------------------------- * proc_soft_watchdog | watchdog_softlockup_user_enabled | WATCHDOG_SOFTOCKUP_ENABLED */ static int proc_watchdog_common(int which, const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old, *param = table->data; mutex_lock(&watchdog_mutex); old = *param; if (!write) { /* * On read synchronize the userspace interface. This is a * racy snapshot. */ *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); *param = old; } else { err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && old != READ_ONCE(*param)) proc_watchdog_update(); } mutex_unlock(&watchdog_mutex); return err; } /* * /proc/sys/kernel/watchdog */ static int proc_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED | WATCHDOG_SOFTOCKUP_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/nmi_watchdog */ static int proc_nmi_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!watchdog_hardlockup_available && write) return -ENOTSUPP; return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED, table, write, buffer, lenp, ppos); } #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * /proc/sys/kernel/soft_watchdog */ static int proc_soft_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED, table, write, buffer, lenp, ppos); } #endif /* * /proc/sys/kernel/watchdog_thresh */ static int proc_watchdog_thresh(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old; mutex_lock(&watchdog_mutex); old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && write && old != READ_ONCE(watchdog_thresh)) proc_watchdog_update(); mutex_unlock(&watchdog_mutex); return err; } /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ static int proc_watchdog_cpumask(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err; mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) proc_watchdog_update(); mutex_unlock(&watchdog_mutex); return err; } static const int sixty = 60; static const struct ctl_table watchdog_sysctls[] = { { .procname = "watchdog", .data = &watchdog_user_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_watchdog, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "watchdog_thresh", .data = &watchdog_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_watchdog_thresh, .extra1 = SYSCTL_ZERO, .extra2 = (void *)&sixty, }, { .procname = "watchdog_cpumask", .data = &watchdog_cpumask_bits, .maxlen = NR_CPUS, .mode = 0644, .proc_handler = proc_watchdog_cpumask, }, #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", .data = &watchdog_softlockup_user_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "softlockup_panic", .data = &softlockup_panic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_SMP { .procname = "softlockup_all_cpu_backtrace", .data = &sysctl_softlockup_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_SMP */ #endif #ifdef CONFIG_HARDLOCKUP_DETECTOR { .procname = "hardlockup_panic", .data = &hardlockup_panic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_SMP { .procname = "hardlockup_all_cpu_backtrace", .data = &sysctl_hardlockup_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_SMP */ #endif }; static struct ctl_table watchdog_hardlockup_sysctl[] = { { .procname = "nmi_watchdog", .data = &watchdog_hardlockup_user_enabled, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_nmi_watchdog, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static void __init watchdog_sysctl_init(void) { register_sysctl_init("kernel", watchdog_sysctls); if (watchdog_hardlockup_available) watchdog_hardlockup_sysctl[0].mode = 0644; register_sysctl_init("kernel", watchdog_hardlockup_sysctl); } #else #define watchdog_sysctl_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static void __init lockup_detector_delay_init(struct work_struct *work); static bool allow_lockup_detector_init_retry __initdata; static struct work_struct detector_work __initdata = __WORK_INITIALIZER(detector_work, lockup_detector_delay_init); static void __init lockup_detector_delay_init(struct work_struct *work) { int ret; ret = watchdog_hardlockup_probe(); if (ret) { if (ret == -ENODEV) pr_info("NMI not fully supported\n"); else pr_info("Delayed init of the lockup detector failed: %d\n", ret); pr_info("Hard watchdog permanently disabled\n"); return; } allow_lockup_detector_init_retry = false; watchdog_hardlockup_available = true; lockup_detector_setup(); } /* * lockup_detector_retry_init - retry init lockup detector if possible. * * Retry hardlockup detector init. It is useful when it requires some * functionality that has to be initialized later on a particular * platform. */ void __init lockup_detector_retry_init(void) { /* Must be called before late init calls */ if (!allow_lockup_detector_init_retry) return; schedule_work(&detector_work); } /* * Ensure that optional delayed hardlockup init is proceed before * the init code and memory is freed. */ static int __init lockup_detector_check(void) { /* Prevent any later retry. */ allow_lockup_detector_init_retry = false; /* Make sure no work is pending. */ flush_work(&detector_work); watchdog_sysctl_init(); return 0; } late_initcall_sync(lockup_detector_check); void __init lockup_detector_init(void) { if (tick_nohz_full_enabled()) pr_info("Disabling watchdog on nohz_full cores by default\n"); cpumask_copy(&watchdog_cpumask, housekeeping_cpumask(HK_TYPE_TIMER)); if (!watchdog_hardlockup_probe()) watchdog_hardlockup_available = true; else allow_lockup_detector_init_retry = true; lockup_detector_setup(); } |
| 333 188 33 87 30 87 334 312 308 320 24 13 311 12 184 7 9 7 142 150 151 112 13 19 6 75 51 51 76 9 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 | // SPDX-License-Identifier: GPL-2.0 /* * Convert integer string representation to an integer. * If an integer doesn't fit into specified type, -E is returned. * * Integer starts with optional sign. * kstrtou*() functions do not accept sign "-". * * Radix 0 means autodetection: leading "0x" implies radix 16, * leading "0" implies radix 8, otherwise radix is 10. * Autodetection hints work after optional sign, but not before. * * If -E is returned, result is not touched. */ #include <linux/ctype.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/kstrtox.h> #include <linux/math64.h> #include <linux/types.h> #include <linux/uaccess.h> #include "kstrtox.h" noinline const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) { if (*base == 0) { if (s[0] == '0') { if (_tolower(s[1]) == 'x' && isxdigit(s[2])) *base = 16; else *base = 8; } else *base = 10; } if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x') s += 2; return s; } /* * Convert non-negative integer string representation in explicitly given radix * to an integer. A maximum of max_chars characters will be converted. * * Return number of characters consumed maybe or-ed with overflow bit. * If overflow occurs, result integer (incorrect) is still returned. * * Don't you dare use this function. */ noinline unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p, size_t max_chars) { unsigned long long res; unsigned int rv; res = 0; rv = 0; while (max_chars--) { unsigned int c = *s; unsigned int lc = _tolower(c); unsigned int val; if ('0' <= c && c <= '9') val = c - '0'; else if ('a' <= lc && lc <= 'f') val = lc - 'a' + 10; else break; if (val >= base) break; /* * Check for overflow only if we are within range of * it in the max base we support (16) */ if (unlikely(res & (~0ull << 60))) { if (res > div_u64(ULLONG_MAX - val, base)) rv |= KSTRTOX_OVERFLOW; } res = res * base + val; rv++; s++; } *p = res; return rv; } noinline unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) { return _parse_integer_limit(s, base, p, INT_MAX); } static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) { unsigned long long _res; unsigned int rv; s = _parse_integer_fixup_radix(s, &base); rv = _parse_integer(s, base, &_res); if (rv & KSTRTOX_OVERFLOW) return -ERANGE; if (rv == 0) return -EINVAL; s += rv; if (*s == '\n') s++; if (*s) return -EINVAL; *res = _res; return 0; } /** * kstrtoull - convert a string to an unsigned long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoull(). Return code must be checked. */ noinline int kstrtoull(const char *s, unsigned int base, unsigned long long *res) { if (s[0] == '+') s++; return _kstrtoull(s, base, res); } EXPORT_SYMBOL(kstrtoull); /** * kstrtoll - convert a string to a long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoll(). Return code must be checked. */ noinline int kstrtoll(const char *s, unsigned int base, long long *res) { unsigned long long tmp; int rv; if (s[0] == '-') { rv = _kstrtoull(s + 1, base, &tmp); if (rv < 0) return rv; if ((long long)-tmp > 0) return -ERANGE; *res = -tmp; } else { rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if ((long long)tmp < 0) return -ERANGE; *res = tmp; } return 0; } EXPORT_SYMBOL(kstrtoll); /* Internal, do not use. */ int _kstrtoul(const char *s, unsigned int base, unsigned long *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtoul); /* Internal, do not use. */ int _kstrtol(const char *s, unsigned int base, long *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtol); /** * kstrtouint - convert a string to an unsigned int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoul(). Return code must be checked. */ noinline int kstrtouint(const char *s, unsigned int base, unsigned int *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtouint); /** * kstrtoint - convert a string to an int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtol(). Return code must be checked. */ noinline int kstrtoint(const char *s, unsigned int base, int *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtoint); noinline int kstrtou16(const char *s, unsigned int base, u16 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou16); noinline int kstrtos16(const char *s, unsigned int base, s16 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos16); noinline int kstrtou8(const char *s, unsigned int base, u8 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou8); noinline int kstrtos8(const char *s, unsigned int base, s8 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos8); /** * kstrtobool - convert common user inputs into boolean values * @s: input string * @res: result * * This routine returns 0 iff the first character is one of 'YyTt1NnFf0', or * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ noinline int kstrtobool(const char *s, bool *res) { if (!s) return -EINVAL; switch (s[0]) { case 'y': case 'Y': case 't': case 'T': case '1': *res = true; return 0; case 'n': case 'N': case 'f': case 'F': case '0': *res = false; return 0; case 'o': case 'O': switch (s[1]) { case 'n': case 'N': *res = true; return 0; case 'f': case 'F': *res = false; return 0; default: break; } break; default: break; } return -EINVAL; } EXPORT_SYMBOL(kstrtobool); /* * Since "base" would be a nonsense argument, this open-codes the * _from_user helper instead of using the helper macro below. */ int kstrtobool_from_user(const char __user *s, size_t count, bool *res) { /* Longest string needed to differentiate, newline, terminator */ char buf[4]; count = min(count, sizeof(buf) - 1); if (copy_from_user(buf, s, count)) return -EFAULT; buf[count] = '\0'; return kstrtobool(buf, res); } EXPORT_SYMBOL(kstrtobool_from_user); #define kstrto_from_user(f, g, type) \ int f(const char __user *s, size_t count, unsigned int base, type *res) \ { \ /* sign, base 2 representation, newline, terminator */ \ char buf[1 + sizeof(type) * 8 + 1 + 1]; \ \ count = min(count, sizeof(buf) - 1); \ if (copy_from_user(buf, s, count)) \ return -EFAULT; \ buf[count] = '\0'; \ return g(buf, base, res); \ } \ EXPORT_SYMBOL(f) kstrto_from_user(kstrtoull_from_user, kstrtoull, unsigned long long); kstrto_from_user(kstrtoll_from_user, kstrtoll, long long); kstrto_from_user(kstrtoul_from_user, kstrtoul, unsigned long); kstrto_from_user(kstrtol_from_user, kstrtol, long); kstrto_from_user(kstrtouint_from_user, kstrtouint, unsigned int); kstrto_from_user(kstrtoint_from_user, kstrtoint, int); kstrto_from_user(kstrtou16_from_user, kstrtou16, u16); kstrto_from_user(kstrtos16_from_user, kstrtos16, s16); kstrto_from_user(kstrtou8_from_user, kstrtou8, u8); kstrto_from_user(kstrtos8_from_user, kstrtos8, s8); |
| 245 64 2 184 184 184 27 8 5 177 177 177 176 1 4 177 177 238 239 238 239 2 1 1 1 198 80 80 80 80 192 192 192 156 156 156 201 75 75 75 75 75 75 75 75 20 143 143 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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. * * Implementation of the Transmission Control Protocol(TCP). * * IPv4 specific functions * * code split from: * linux/ipv4/tcp.c * linux/ipv4/tcp_input.c * linux/ipv4/tcp_output.c * * See tcp.c for author information */ /* * Changes: * David S. Miller : New socket lookup architecture. * This code is dedicated to John Dyson. * David S. Miller : Change semantics of established hash, * half is devoted to TIME_WAIT sockets * and the rest go in the other half. * Andi Kleen : Add support for syncookies and fixed * some bugs: ip options weren't passed to * the TCP layer, missed a check for an * ACK bit. * Andi Kleen : Implemented fast path mtu discovery. * Fixed many serious bugs in the * request_sock handling and moved * most of it into the af independent code. * Added tail drop and some other bugfixes. * Added new listen semantics. * Mike McLagan : Routing by source * Juan Jose Ciarlante: ip_dynaddr bits * Andi Kleen: various fixes. * Vitaly E. Lavrov : Transparent proxy revived after year * coma. * Andi Kleen : Fix new listen. * Andi Kleen : Fix accept error reporting. * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. */ #define pr_fmt(fmt) "TCP: " fmt #include <linux/bottom_half.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> #include <linux/random.h> #include <linux/cache.h> #include <linux/jhash.h> #include <linux/init.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/sched.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> #include <net/tcp.h> #include <net/transp_v6.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/inet_ecn.h> #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/busy_poll.h> #include <net/rstreason.h> #include <linux/inet.h> #include <linux/ipv6.h> #include <linux/stddef.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <linux/btf_ids.h> #include <linux/skbuff_ref.h> #include <crypto/hash.h> #include <linux/scatterlist.h> #include <trace/events/tcp.h> #ifdef CONFIG_TCP_MD5SIG static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); #endif struct inet_hashinfo tcp_hashinfo; static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; static DEFINE_MUTEX(tcp_exit_batch_mutex); static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); int ts_recent_stamp; u32 reuse_thresh; if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) reuse = 0; if (reuse == 2) { /* Still does not detect *everything* that goes through * lo, since we require a loopback src or dst address * or direct binding to 'lo' interface. */ bool loopback = false; if (tw->tw_bound_dev_if == LOOPBACK_IFINDEX) loopback = true; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { if (ipv6_addr_loopback(&tw->tw_v6_daddr) || ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) || ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) || ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr)) loopback = true; } else #endif { if (ipv4_is_loopback(tw->tw_daddr) || ipv4_is_loopback(tw->tw_rcv_saddr)) loopback = true; } if (!loopback) reuse = 0; } /* With PAWS, it is safe from the viewpoint of data integrity. Even without PAWS it is safe provided sequence spaces do not overlap i.e. at data rates <= 80Mbit/sec. Actually, the idea is close to VJ's one, only timestamp cache is held not per host, but per port pair and TW bucket is used as state holder. If TW bucket has been already destroyed we fall back to VJ's scheme and use initial timestamp retrieved from peer table. */ ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp); reuse_thresh = READ_ONCE(tw->tw_entry_stamp) + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse_delay); if (ts_recent_stamp && (!twp || (reuse && time_after32(tcp_clock_ms(), reuse_thresh)))) { /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk * and releasing the bucket lock. */ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) return 0; /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair * process. * * Without this check re-using a TIME-WAIT socket with TCP * repair would accumulate a -1 on the repair assigned * sequence number. The first time it is reused the sequence * is -1, the second time -2, etc. This fixes that issue * without appearing to create any others. */ if (likely(!tp->repair)) { u32 seq = tcptw->tw_snd_nxt + 65535 + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = READ_ONCE(tcptw->tw_ts_recent); tp->rx_opt.ts_recent_stamp = ts_recent_stamp; } return 1; } return 0; } EXPORT_IPV6_MOD_GPL(tcp_twsk_unique); static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from tcp_v4_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, &addr_len); } /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; orig_dport = usin->sin_port; fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport, orig_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return err; } if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { ip_rt_put(rt); return -ENETUNREACH; } if (!inet_opt || !inet_opt->opt.srr) daddr = fl4->daddr; tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { ip_rt_put(rt); return err; } } else { sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; /* Socket identity is still unknown (sport may be zero). * However we set state to SYN-SENT and not releasing socket * lock select source port, enter ourselves into the hash tables and * complete initialization after this. */ tcp_set_state(sk, TCP_SYN_SENT); err = inet_hash_connect(tcp_death_row, sk); if (err) goto failure; sk_set_txhash(sk); rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto failure; } tp->tcp_usec_ts = dst_tcp_usec_ts(&rt->dst); /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); rt = NULL; if (likely(!tp->repair)) { if (!tp->write_seq) WRITE_ONCE(tp->write_seq, secure_tcp_seq(inet->inet_saddr, inet->inet_daddr, inet->inet_sport, usin->sin_port)); WRITE_ONCE(tp->tsoffset, secure_tcp_ts_off(net, inet->inet_saddr, inet->inet_daddr)); } atomic_set(&inet->inet_id, get_random_u16()); if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto failure; err = tcp_connect(sk); if (err) goto failure; return 0; failure: /* * This unhashes the socket and releases the local port, * if necessary. */ tcp_set_state(sk, TCP_CLOSE); inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; return err; } EXPORT_IPV6_MOD(tcp_v4_connect); /* * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ void tcp_v4_mtu_reduced(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct dst_entry *dst; u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst)) WRITE_ONCE(sk->sk_err_soft, EMSGSIZE); mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && ip_sk_accept_pmtu(sk) && inet_csk(sk)->icsk_pmtu_cookie > mtu) { tcp_sync_mss(sk, mtu); /* Resend the TCP packet because it's * clear that the old packet has been * dropped. This is the new "fast" path mtu * discovery. */ tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } EXPORT_IPV6_MOD(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { struct dst_entry *dst = __sk_dst_check(sk, 0); if (dst) dst->ops->redirect(dst, sk, skb); } /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ if (seq != tcp_rsk(req)->snt_isn) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly * created socket, and POSIX does not want network * errors returned from accept(). */ inet_csk_reqsk_queue_drop(req->rsk_listener, req); tcp_listendrop(req->rsk_listener); } reqsk_put(req); } EXPORT_IPV6_MOD(tcp_req_err); /* TCP-LD (RFC 6069) logic */ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; s32 remaining; u32 delta_us; if (sock_owned_by_user(sk)) return; if (seq != tp->snd_una || !icsk->icsk_retransmits || !icsk->icsk_backoff) return; skb = tcp_rtx_queue_head(sk); if (WARN_ON_ONCE(!skb)) return; icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, tcp_rto_max(sk)); tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us); if (remaining > 0) { tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, false); } else { /* RTO revert clocked out retransmission. * Will retransmit now. */ tcp_retransmit_timer(sk); } } EXPORT_IPV6_MOD(tcp_ld_RTO_revert); /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. After adjustment * header points to the first 8 bytes of the tcp header. We need * to find the appropriate port. * * The locking strategy used here is very "optimistic". When * someone else accesses the socket the ICMP is just dropped * and for some paths there is no check at all. * A more general error queue to queue errors for later handling * is probably better. * */ int tcp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); struct net *net = dev_net_rcu(skb->dev); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct request_sock *fastopen; struct tcp_sock *tp; u32 seq, snd_una; struct sock *sk; int err; sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, iph->daddr, th->dest, iph->saddr, ntohs(th->source), inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { /* To increase the counter of ignored icmps for TCP-AO */ tcp_ao_ignore_icmp(sk, AF_INET, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, type == ICMP_PARAMETERPROB || type == ICMP_TIME_EXCEEDED || (type == ICMP_DEST_UNREACH && (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH))); return 0; } if (tcp_ao_ignore_icmp(sk, AF_INET, type, code)) { sock_put(sk); return 0; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ if (sock_owned_by_user(sk)) { if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); } if (sk->sk_state == TCP_CLOSE) goto out; if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_REDIRECT: if (!sock_owned_by_user(sk)) do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } goto out; } err = icmp_err_convert[code].errno; /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH)) tcp_ld_RTO_revert(sk, seq); break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); if (!sock_owned_by_user(sk)) tcp_done_with_error(sk, err); else WRITE_ONCE(sk->sk_err_soft, err); goto out; } /* If we've already connected we will keep trying * until we time out, or the user gives up. * * rfc1122 4.2.3.9 allows to consider as hard errors * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too, * but it is obsoleted by pmtu discovery). * * Note, that in modern internet, where routing is unreliable * and in each dark corner broken firewalls sit, sending random * errors ordered by their masters even this two messages finally lose * their original sense (even Linux sends invalid PORT_UNREACHs) * * Now we are in compliance with RFCs. * --ANK (980905) */ if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { /* Only an error on timeout */ WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } /* This routine computes an IPv4 TCP checksum. */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } EXPORT_IPV6_MOD(tcp_v4_send_check); #define REPLY_OPTIONS_LEN (MAX_TCP_OPTION_SPACE / sizeof(__be32)) static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb, const struct tcp_ao_hdr *aoh, struct ip_reply_arg *arg, struct tcphdr *reply, __be32 reply_options[REPLY_OPTIONS_LEN]) { #ifdef CONFIG_TCP_AO int sdif = tcp_v4_sdif(skb); int dif = inet_iif(skb); int l3index = sdif ? dif : 0; bool allocated_traffic_key; struct tcp_ao_key *key; char *traffic_key; bool drop = true; u32 ao_sne = 0; u8 keyid; rcu_read_lock(); if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, ntohl(reply->seq), &key, &traffic_key, &allocated_traffic_key, &keyid, &ao_sne)) goto out; reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) | (aoh->rnext_keyid << 8) | keyid); arg->iov[0].iov_len += tcp_ao_len_aligned(key); reply->doff = arg->iov[0].iov_len / 4; if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1], key, traffic_key, (union tcp_ao_addr *)&ip_hdr(skb)->saddr, (union tcp_ao_addr *)&ip_hdr(skb)->daddr, reply, ao_sne)) goto out; drop = false; out: rcu_read_unlock(); if (allocated_traffic_key) kfree(traffic_key); return drop; #else return true; #endif } /* * This routine will send an RST to the other tcp. * * Someone asks: why I NEVER use socket parameters (TOS, TTL etc.) * for reset. * Answer: if a packet caused RST, it is not for a socket * existing in our system, if it is matched to a socket, * it is just duplicate segment or bug in other side's TCP. * So that we build reply only basing on parameters * arrived with segment. * Exception: precedence violation. We do not implement it in any case. */ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[REPLY_OPTIONS_LEN]; } rep; const __u8 *md5_hash_location = NULL; const struct tcp_ao_hdr *aoh; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key = NULL; unsigned char newhash[16]; struct sock *sk1 = NULL; int genhash; #endif u64 transmit_time = 0; struct sock *ctl_sk; struct net *net; u32 txhash = 0; /* Never send a reset in response to a reset. */ if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ memset(&rep, 0, sizeof(rep)); rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = sizeof(struct tcphdr) / 4; rep.th.rst = 1; if (th->ack) { rep.th.seq = th->ack_seq; } else { rep.th.ack = 1; rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2)); } memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh)) return; if (aoh && tcp_v4_ao_sign_reset(sk, skb, aoh, &arg, &rep.th, rep.opt)) return; #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); if (sk && sk_fullsock(sk)) { const union tcp_md5_addr *addr; int l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and inet_iif is set to it. */ l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } else if (md5_hash_location) { const union tcp_md5_addr *addr; int sdif = tcp_v4_sdif(skb); int dif = inet_iif(skb); int l3index; /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, ntohs(th->source), dif, sdif); /* don't send rst if it can't find key */ if (!sk1) goto out; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to it. */ l3index = sdif ? dif : 0; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET); if (!key) goto out; genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) goto out; } if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* Update length and the length the header thinks exists */ arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len / 4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1], key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif /* Can't co-exist with TCPMD5, hence check rep.opt[0] */ if (rep.opt[0] == 0) { __be32 mrst = mptcp_reset_option(skb); if (mrst) { rep.opt[0] = mrst; arg.iov[0].iov_len += sizeof(mrst); rep.th.doff = arg.iov[0].iov_len / 4; } } arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0; /* When socket is gone, all binding information is lost. * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. */ if (sk) arg.bound_dev_if = sk->sk_bound_dev_if; trace_tcp_send_reset(sk, skb, reason); BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); /* ECN bits of TW reset are cleared */ arg.tos = ip_hdr(skb)->tos & ~INET_ECN_MASK; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); txhash = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_txhash : sk->sk_txhash; } else { ctl_sk->sk_mark = 0; ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time, txhash); xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); #ifdef CONFIG_TCP_MD5SIG out: rcu_read_unlock(); #endif } /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states outside socket context is ugly, certainly. What can I do? */ static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_key *key, int reply_flags, u8 tos, u32 txhash) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[(MAX_TCP_OPTION_SPACE >> 2)]; } rep; struct net *net = sock_net(sk); struct ip_reply_arg arg; struct sock *ctl_sk; u64 transmit_time; memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); rep.opt[1] = htonl(tsval); rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } /* Swap the send and the receive. */ rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = arg.iov[0].iov_len / 4; rep.th.seq = htonl(seq); rep.th.ack_seq = htonl(ack); rep.th.ack = 1; rep.th.window = htons(win); #ifdef CONFIG_TCP_MD5SIG if (tcp_key_is_md5(key)) { int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len/4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset], key->md5_key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif #ifdef CONFIG_TCP_AO if (tcp_key_is_ao(key)) { int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | key->rcv_next); arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key); rep.th.doff = arg.iov[0].iov_len / 4; tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset], key->ao_key, key->traffic_key, (union tcp_ao_addr *)&ip_hdr(skb)->saddr, (union tcp_ao_addr *)&ip_hdr(skb)->daddr, &rep.th, key->sne); } #endif arg.flags = reply_flags; arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; if (oif) arg.bound_dev_if = oif; arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time, txhash); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); } static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb, enum tcp_tw_status tw_status) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); struct tcp_key key = {}; u8 tos = tw->tw_tos; /* Cleaning only ECN bits of TW ACKs of oow data or is paws_reject, * while not cleaning ECN bits of other TW ACKs to avoid these ACKs * being placed in a different service queues (Classic rather than L4S) */ if (tw_status == TCP_TW_ACK_OOW) tos &= ~INET_ECN_MASK; #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; if (static_branch_unlikely(&tcp_ao_needed.key)) { /* FIXME: the segment to-be-acked is not verified yet */ ao_info = rcu_dereference(tcptw->ao_info); if (ao_info) { const struct tcp_ao_hdr *aoh; if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) { inet_twsk_put(tw); return; } if (aoh) key.ao_key = tcp_ao_established_key(sk, ao_info, aoh->rnext_keyid, -1); } } if (key.ao_key) { struct tcp_ao_key *rnext_key; key.traffic_key = snd_other_key(key.ao_key); key.sne = READ_ONCE(ao_info->snd_sne); rnext_key = READ_ONCE(ao_info->rnext_key); key.rcv_next = rnext_key->rcvid; key.type = TCP_KEY_AO; #else if (0) { #endif } else if (static_branch_tcp_md5()) { key.md5_key = tcp_twsk_md5_key(tcptw); if (key.md5_key) key.type = TCP_KEY_MD5; } tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, &key, tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, tos, tw->tw_txhash); inet_twsk_put(tw); } static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_key key = {}; /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; #ifdef CONFIG_TCP_AO if (static_branch_unlikely(&tcp_ao_needed.key) && tcp_rsk_used_ao(req)) { const union tcp_md5_addr *addr; const struct tcp_ao_hdr *aoh; int l3index; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) return; if (!aoh) return; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET, aoh->rnext_keyid, -1); if (unlikely(!key.ao_key)) { /* Send ACK with any matching MKT for the peer */ key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET, -1, -1); /* Matching key disappeared (user removed the key?) * let the handshake timeout. */ if (!key.ao_key) { net_info_ratelimited("TCP-AO key for (%pI4, %d)->(%pI4, %d) suddenly disappeared, won't ACK new connection\n", addr, ntohs(tcp_hdr(skb)->source), &ip_hdr(skb)->daddr, ntohs(tcp_hdr(skb)->dest)); return; } } key.traffic_key = kmalloc(tcp_ao_digest_size(key.ao_key), GFP_ATOMIC); if (!key.traffic_key) return; key.type = TCP_KEY_AO; key.rcv_next = aoh->keyid; tcp_v4_ao_calc_key_rsk(key.ao_key, key.traffic_key, req); #else if (0) { #endif } else if (static_branch_tcp_md5()) { const union tcp_md5_addr *addr; int l3index; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key.md5_key) key.type = TCP_KEY_MD5; } /* Cleaning ECN bits of TW ACKs of oow data or is paws_reject */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), req->ts_recent, 0, &key, inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos & ~INET_ECN_MASK, READ_ONCE(tcp_rsk(req)->txhash)); if (tcp_key_is_ao(&key)) kfree(key.traffic_key); } /* * Send a SYN-ACK after having received a SYN. * This still operates on a request_sock only, not on a big * socket. */ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; struct sk_buff *skb; u8 tos; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); tos = READ_ONCE(inet_sk(sk)->tos); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) tos = (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (tos & INET_ECN_MASK); if (!INET_ECN_is_capable(tos) && tcp_bpf_ca_needs_ecn((struct sock *)req)) tos |= INET_ECN_ECT_0; rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), tos); rcu_read_unlock(); err = net_xmit_eval(err); } return err; } /* * IPv4 request_sock destructor. */ static void tcp_v4_reqsk_destructor(struct request_sock *req) { kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } #ifdef CONFIG_TCP_MD5SIG /* * RFC2385 MD5 checksumming requires a mapping of * IP address->MD5 Key. * We need to maintain these in the sk structure. */ DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ); EXPORT_IPV6_MOD(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) { if (!old) return true; /* l3index always overrides non-l3index */ if (old->l3index && new->l3index == 0) return false; if (old->l3index == 0 && new->l3index) return true; return old->prefixlen < new->prefixlen; } /* Find the Key structure for an address. */ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family, bool any_l3index) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; const struct tcp_md5sig_info *md5sig; __be32 mask; struct tcp_md5sig_key *best_match = NULL; bool match; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; hlist_for_each_entry_rcu(key, &md5sig->head, node, lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (!any_l3index && key->flags & TCP_MD5SIG_FLAG_IFINDEX && key->l3index != l3index) continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); match = (key->addr.a4.s_addr & mask) == (addr->a4.s_addr & mask); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, key->prefixlen); #endif } else { match = false; } if (match && better_md5_match(best_match, key)) best_match = key; } return best_match; } EXPORT_IPV6_MOD(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); const struct tcp_md5sig_info *md5sig; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) size = sizeof(struct in6_addr); #endif hlist_for_each_entry_rcu(key, &md5sig->head, node, lockdep_sock_is_held(sk)) { if (key->family != family) continue; if ((key->flags & TCP_MD5SIG_FLAG_IFINDEX) != (flags & TCP_MD5SIG_FLAG_IFINDEX)) continue; if (key->l3index != l3index) continue; if (!memcmp(&key->addr, addr, size) && key->prefixlen == prefixlen) return key; } return NULL; } struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; int l3index; l3index = l3mdev_master_ifindex_by_index(sock_net(sk), addr_sk->sk_bound_dev_if); addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } EXPORT_IPV6_MOD(tcp_v4_md5_lookup); static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) return -ENOMEM; sk_gso_disable(sk); INIT_HLIST_HEAD(&md5sig->head); rcu_assign_pointer(tp->md5sig_info, md5sig); return 0; } /* This can be called on a newly created socket, from other files */ static int __tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags); if (key) { /* Pre-existing entry - just update that one. * Note that the key might be used concurrently. * data_race() is telling kcsan that we do not care of * key mismatches, since changing MD5 key on live flows * can lead to packet drops. */ data_race(memcpy(key->key, newkey, newkeylen)); /* Pairs with READ_ONCE() in tcp_md5_hash_key(). * Also note that a reader could catch new key->keylen value * but old key->key[], this is the reason we use __GFP_ZERO * at sock_kmalloc() time below these lines. */ WRITE_ONCE(key->keylen, newkeylen); return 0; } md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; key->family = family; key->prefixlen = prefixlen; key->l3index = l3index; key->flags = flags; memcpy(&key->addr, addr, (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen) { struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { if (tcp_md5_alloc_sigpool()) return -ENOMEM; if (tcp_md5sig_info_add(sk, GFP_KERNEL)) { tcp_md5_release_sigpool(); return -ENOMEM; } if (!static_branch_inc(&tcp_md5_needed.key)) { struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); tcp_md5_release_sigpool(); return -EUSERS; } } return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags, newkey, newkeylen, GFP_KERNEL); } EXPORT_IPV6_MOD(tcp_md5_do_add); int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, struct tcp_md5sig_key *key) { struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { tcp_md5_add_sigpool(); if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) { tcp_md5_release_sigpool(); return -ENOMEM; } if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); tcp_md5_release_sigpool(); return -EUSERS; } } return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, key->flags, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } EXPORT_IPV6_MOD(tcp_md5_key_copy); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) { struct tcp_md5sig_key *key; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags); if (!key) return -ENOENT; hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); return 0; } EXPORT_IPV6_MOD(tcp_md5_do_del); void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); } } static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; const union tcp_md5_addr *addr; u8 prefixlen = 32; int l3index = 0; bool l3flag; u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin->sin_family != AF_INET) return -EINVAL; flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 32) return -EINVAL; } if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); if (dev && netif_is_l3_master(dev)) l3index = dev->ifindex; rcu_read_unlock(); /* ok to reference set/not set outside of rcu; * right now device MUST be an L3 master */ if (!dev || !l3index) return -EINVAL; } addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr; if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index, flags); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v4_md5_hash_headers(struct tcp_sigpool *hp, __be32 daddr, __be32 saddr, const struct tcphdr *th, int nbytes) { struct tcp4_pseudohdr *bp; struct scatterlist sg; struct tcphdr *_th; bp = hp->scratch; bp->saddr = saddr; bp->daddr = daddr; bp->pad = 0; bp->protocol = IPPROTO_TCP; bp->len = cpu_to_be16(nbytes); _th = (struct tcphdr *)(bp + 1); memcpy(_th, th, sizeof(*th)); _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); ahash_request_set_crypt(hp->req, &sg, NULL, sizeof(*bp) + sizeof(*th)); return crypto_ahash_update(hp->req); } static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th) { struct tcp_sigpool hp; if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct tcp_sigpool hp; __be32 saddr, daddr; if (sk) { /* valid for establish/request sockets */ saddr = sk->sk_rcv_saddr; daddr = sk->sk_daddr; } else { const struct iphdr *iph = ip_hdr(skb); saddr = iph->saddr; daddr = iph->daddr; } if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) goto clear_hash; if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } EXPORT_IPV6_MOD(tcp_v4_md5_hash_skb); #endif static void tcp_v4_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); struct net *net = sock_net(sk_listener); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn) { tcp_v4_init_req(req, sk, skb); if (security_inet_conn_request(sk, skb, req)) return NULL; return inet_csk_route_req(sk, &fl->u.ip4, req); } struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v4_ao_lookup_rsk, .ao_calc_key = tcp_v4_ao_calc_key_rsk, .ao_synack_hash = tcp_v4_ao_synack_hash, #endif #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, .init_seq = tcp_v4_init_seq, .init_ts_off = tcp_v4_init_ts_off, .send_synack = tcp_v4_send_synack, }; int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; return tcp_conn_request(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, skb); drop: tcp_listendrop(sk); return 0; } EXPORT_IPV6_MOD(tcp_v4_conn_request); /* * The three way handshake has completed - we got a valid synack - * now create the new socket. */ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct inet_request_sock *ireq; bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG const union tcp_md5_addr *addr; struct tcp_md5sig_key *key; int l3index; #endif struct ip_options_rcu *inet_opt; if (sk_acceptq_is_full(sk)) goto exit_overflow; newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; inet_sk_rx_dst_set(newsk, skb); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); inet_opt = rcu_dereference(ireq->ireq_opt); RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; atomic_set(&newinet->inet_id, get_random_u16()); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); if (!dst) goto put_and_exit; } else { /* syncookie case : see end of cookie_v4_check() */ } sk_setup_caps(newsk, dst); tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); /* Copy over the MD5 key from the original socket */ addr = (union tcp_md5_addr *)&newinet->inet_daddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key && !tcp_rsk_used_ao(req)) { if (tcp_md5_key_copy(newsk, addr, AF_INET, 32, l3index, key)) goto put_and_exit; sk_gso_disable(newsk); } #endif #ifdef CONFIG_TCP_AO if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET)) goto put_and_exit; /* OOM, release back memory */ #endif if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { newinet->inet_opt = NULL; if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; exit_overflow: NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); exit_nonewsk: dst_release(dst); exit: tcp_listendrop(sk); return NULL; put_and_exit: newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; } EXPORT_IPV6_MOD(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v4_check(sk, skb); #endif return sk; } u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, th); if (mss) { *cookie = __cookie_v4_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason reason; struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (sk->sk_rx_dst_ifindex != skb->skb_iif || !INDIRECT_CALL_1(dst->ops->check, ipv4_dst_check, dst, 0)) { RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); } } tcp_rcv_established(sk, skb); return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v4_cookie_check(sk, skb); if (!nsk) return 0; if (nsk != sk) { reason = tcp_child_process(sk, nsk, skb); if (reason) { rsk = nsk; goto reset; } return 0; } } else sock_rps_save_rxhash(sk, skb); reason = tcp_rcv_state_process(sk, skb); if (reason) { rsk = sk; goto reset; } return 0; reset: tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason)); discard: sk_skb_reason_drop(sk, skb, reason); /* Be careful here. If this function gets more complicated and * gcc suffers from register pressure on the x86, sk (in %ebx) * might be destroyed here. This current version compiles correctly, * but you have been warned. */ return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } EXPORT_SYMBOL(tcp_v4_do_rcv); int tcp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return 0; sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif, inet_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { u32 tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; struct sk_buff *tail; unsigned int hdrlen; bool fragstolen; u32 gso_segs; u32 gso_size; u64 limit; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), * we can fix skb->truesize to its real value to avoid future drops. * This is valid because skb is not yet charged to the socket. * It has been noticed pure SACK packets were sometimes dropped * (if cooked by drivers without copybreak feature). */ skb_condense(skb); tcp_cleanup_skb(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); trace_tcp_bad_csum(skb); *reason = SKB_DROP_REASON_TCP_CSUM; __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); return true; } /* Attempt coalescing to last skb in backlog, even if we are * above the limits. * This is okay because skb capacity is limited to MAX_SKB_FRAGS. */ th = (const struct tcphdr *)skb->data; hdrlen = th->doff * 4; tail = sk->sk_backlog.tail; if (!tail) goto no_coalesce; thtail = (struct tcphdr *)tail->data; if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq || TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield || ((TCP_SKB_CB(tail)->tcp_flags | TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) || !((TCP_SKB_CB(tail)->tcp_flags & TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)) || !tcp_skb_can_collapse_rx(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; __skb_pull(skb, hdrlen); shinfo = skb_shinfo(skb); gso_size = shinfo->gso_size ?: skb->len; gso_segs = shinfo->gso_segs ?: 1; shinfo = skb_shinfo(tail); tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen); tail_gso_segs = shinfo->gso_segs ?: 1; if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; thtail->window = th->window; } /* We have to update both TCP_SKB_CB(tail)->tcp_flags and * thtail->fin, so that the fast path in tcp_rcv_established() * is not entered if we append a packet with a FIN. * SYN, RST, URG are not present. * ACK is set on both packets. * PSH : we do not really care in TCP stack, * at least for 'GRO' packets. */ thtail->fin |= th->fin; TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; if (TCP_SKB_CB(skb)->has_rxtstamp) { TCP_SKB_CB(tail)->has_rxtstamp = true; tail->tstamp = skb->tstamp; skb_hwtstamps(tail)->hwtstamp = skb_hwtstamps(skb)->hwtstamp; } /* Not as strict as GRO. We only need to carry mss max value */ shinfo->gso_size = max(gso_size, tail_gso_size); shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF); sk->sk_backlog.len += delta; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGCOALESCE); kfree_skb_partial(skb, fragstolen); return false; } __skb_push(skb, hdrlen); no_coalesce: /* sk->sk_backlog.len is reset only at the end of __release_sock(). * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach * sk_rcvbuf in normal conditions. */ limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1; limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1; /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ limit += 64 * 1024; limit = min_t(u64, limit, UINT_MAX); if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); *reason = SKB_DROP_REASON_SOCKET_BACKLOG; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); return true; } return false; } EXPORT_IPV6_MOD(tcp_add_backlog); int tcp_filter(struct sock *sk, struct sk_buff *skb) { struct tcphdr *th = (struct tcphdr *)skb->data; return sk_filter_trim_cap(sk, skb, th->doff * 4); } EXPORT_IPV6_MOD(tcp_filter); static void tcp_v4_restore_cb(struct sk_buff *skb) { memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4, sizeof(struct inet_skb_parm)); } static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, const struct tcphdr *th) { /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() * barrier() makes sure compiler wont play fool^Waliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), sizeof(struct inet_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th); TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } /* * From tcp_input.c */ int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); enum skb_drop_reason drop_reason; enum tcp_tw_status tw_status; int sdif = inet_sdif(skb); int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk = NULL; bool refcounted; int ret; u32 isn; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* Count it even if it's bad */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; } if (!pskb_may_pull(skb, th->doff * 4)) goto discard_it; /* An explanation is required here, I think. * Packet length and doff are validated by header prediction, * provided case of th->doff==0 is eliminated. * So, we defer the checks. */ if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); lookup: sk = __inet_lookup_skb(net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) drop_reason = SKB_DROP_REASON_XFRM_POLICY; else drop_reason = tcp_inbound_hash(sk, req, skb, &iph->saddr, &iph->daddr, AF_INET, dif, sdif); if (unlikely(drop_reason)) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); if (!nsk) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sk = nsk; /* reuseport_migrate_sock() has already held one sk_refcnt * before returning. */ } else { /* We own a reference on the listener, increase it again * as we might lose it too soon. */ sock_hold(sk); } refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen, &drop_reason); } else { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v4_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v4_restore_cb(skb); } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { enum sk_rst_reason rst_reason; rst_reason = sk_rst_convert_drop_reason(drop_reason); tcp_v4_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); return 0; } } process: if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); drop_reason = SKB_DROP_REASON_TCP_MINTTL; goto discard_and_relse; } } if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; } drop_reason = tcp_inbound_hash(sk, NULL, skb, &iph->saddr, &iph->daddr, AF_INET, dif, sdif); if (drop_reason) goto discard_and_relse; nf_reset_ct(skb); if (tcp_filter(sk, skb)) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; } th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v4_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { ret = tcp_v4_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb, &drop_reason)) goto discard_and_relse; } bh_unlock_sock(sk); put_and_return: if (refcounted) sock_put(sk); return ret; no_tcp_socket: drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { csum_error: drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v4_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); /* Discard frame. */ sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: sk_drops_add(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn); switch (tw_status) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb), sdif); if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; __this_cpu_write(tcp_tw_isn, isn); goto process; } } /* to ACK */ fallthrough; case TCP_TW_ACK: case TCP_TW_ACK_OOW: tcp_v4_timewait_ack(sk, skb, tw_status); break; case TCP_TW_RST: tcp_v4_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS:; } goto discard_it; } static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_destructor= tcp_twsk_destructor, }; void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; } } EXPORT_IPV6_MOD(inet_sk_rx_dst_set); const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_IPV6_MOD(ipv4_specific); #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v4_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v4_ao_lookup, .calc_ao_hash = tcp_v4_ao_hash_skb, .ao_parse = tcp_v4_parse_ao, .ao_calc_key_sk = tcp_v4_ao_calc_key_sk, #endif }; #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v4_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv4_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif return 0; } #ifdef CONFIG_TCP_MD5SIG static void tcp_md5sig_info_free_rcu(struct rcu_head *head) { struct tcp_md5sig_info *md5sig; md5sig = container_of(head, struct tcp_md5sig_info, rcu); kfree(md5sig); static_branch_slow_dec_deferred(&tcp_md5_needed); tcp_md5_release_sigpool(); } #endif static void tcp_release_user_frags(struct sock *sk) { #ifdef CONFIG_PAGE_POOL unsigned long index; void *netmem; xa_for_each(&sk->sk_user_frags, index, netmem) WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); #endif } void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); tcp_release_user_frags(sk); xa_destroy(&sk->sk_user_frags); trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); tcp_cleanup_congestion_control(sk); tcp_cleanup_ulp(sk); /* Cleanup up the write buffer. */ tcp_write_queue_purge(sk); /* Check if we want to disable active TFO */ tcp_fastopen_active_disable_ofo_check(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); tcp_clear_md5_list(sk); call_rcu(&md5sig->rcu, tcp_md5sig_info_free_rcu); rcu_assign_pointer(tp->md5sig_info, NULL); } #endif tcp_ao_destroy_sock(sk, false); /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); tcp_fastopen_destroy_cipher(sk); tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); } EXPORT_IPV6_MOD(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ static unsigned short seq_file_family(const struct seq_file *seq); static bool seq_sk_match(struct seq_file *seq, const struct sock *sk) { unsigned short family = seq_file_family(seq); /* AF_UNSPEC is used as a match all */ return ((family == AF_UNSPEC || family == sk->sk_family) && net_eq(sock_net(sk), seq_file_net(seq))); } /* Find a non empty bucket (starting from st->bucket) * and return the first sk from it. */ static void *listening_get_first(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; st->offset = 0; for (; st->bucket <= hinfo->lhash2_mask; st->bucket++) { struct inet_listen_hashbucket *ilb2; struct hlist_nulls_node *node; struct sock *sk; ilb2 = &hinfo->lhash2[st->bucket]; if (hlist_nulls_empty(&ilb2->nulls_head)) continue; spin_lock(&ilb2->lock); sk_nulls_for_each(sk, node, &ilb2->nulls_head) { if (seq_sk_match(seq, sk)) return sk; } spin_unlock(&ilb2->lock); } return NULL; } /* Find the next sk of "cur" within the same bucket (i.e. st->bucket). * If "cur" is the last one in the st->bucket, * call listening_get_first() to return the first sk of the next * non empty bucket. */ static void *listening_get_next(struct seq_file *seq, void *cur) { struct tcp_iter_state *st = seq->private; struct inet_listen_hashbucket *ilb2; struct hlist_nulls_node *node; struct inet_hashinfo *hinfo; struct sock *sk = cur; ++st->num; ++st->offset; sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) return sk; } hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; ilb2 = &hinfo->lhash2[st->bucket]; spin_unlock(&ilb2->lock); ++st->bucket; return listening_get_first(seq); } static void *listening_get_idx(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; st->offset = 0; rc = listening_get_first(seq); while (rc && *pos) { rc = listening_get_next(seq, rc); --*pos; } return rc; } static inline bool empty_bucket(struct inet_hashinfo *hinfo, const struct tcp_iter_state *st) { return hlist_nulls_empty(&hinfo->ehash[st->bucket].chain); } /* * Get first established socket starting from bucket given in st->bucket. * If st->bucket is zero, the very first socket in the hash is returned. */ static void *established_get_first(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; st->offset = 0; for (; st->bucket <= hinfo->ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; spinlock_t *lock = inet_ehash_lockp(hinfo, st->bucket); cond_resched(); /* Lockless fast path for the common case of empty buckets */ if (empty_bucket(hinfo, st)) continue; spin_lock_bh(lock); sk_nulls_for_each(sk, node, &hinfo->ehash[st->bucket].chain) { if (seq_sk_match(seq, sk)) return sk; } spin_unlock_bh(lock); } return NULL; } static void *established_get_next(struct seq_file *seq, void *cur) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; struct hlist_nulls_node *node; struct sock *sk = cur; ++st->num; ++st->offset; sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) return sk; } spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); ++st->bucket; return established_get_first(seq); } static void *established_get_idx(struct seq_file *seq, loff_t pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; rc = established_get_first(seq); while (rc && pos) { rc = established_get_next(seq, rc); --pos; } return rc; } static void *tcp_get_idx(struct seq_file *seq, loff_t pos) { void *rc; struct tcp_iter_state *st = seq->private; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_idx(seq, &pos); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_idx(seq, pos); } return rc; } static void *tcp_seek_last_pos(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; int bucket = st->bucket; int offset = st->offset; int orig_num = st->num; void *rc = NULL; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (st->bucket > hinfo->lhash2_mask) break; rc = listening_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); if (rc) break; st->bucket = 0; st->state = TCP_SEQ_STATE_ESTABLISHED; fallthrough; case TCP_SEQ_STATE_ESTABLISHED: if (st->bucket > hinfo->ehash_mask) break; rc = established_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = established_get_next(seq, rc); } st->num = orig_num; return rc; } void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; if (*pos && *pos == st->last_pos) { rc = tcp_seek_last_pos(seq); if (rc) goto out; } st->state = TCP_SEQ_STATE_LISTENING; st->num = 0; st->bucket = 0; st->offset = 0; rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; out: st->last_pos = *pos; return rc; } EXPORT_IPV6_MOD(tcp_seq_start); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc = NULL; if (v == SEQ_START_TOKEN) { rc = tcp_get_idx(seq, 0); goto out; } switch (st->state) { case TCP_SEQ_STATE_LISTENING: rc = listening_get_next(seq, v); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; st->bucket = 0; st->offset = 0; rc = established_get_first(seq); } break; case TCP_SEQ_STATE_ESTABLISHED: rc = established_get_next(seq, v); break; } out: ++*pos; st->last_pos = *pos; return rc; } EXPORT_IPV6_MOD(tcp_seq_next); void tcp_seq_stop(struct seq_file *seq, void *v) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) spin_unlock(&hinfo->lhash2[st->bucket].lock); break; case TCP_SEQ_STATE_ESTABLISHED: if (v) spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); break; } } EXPORT_IPV6_MOD(tcp_seq_stop); static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i) { const struct inet_request_sock *ireq = inet_rsk(req); long delta = req->rsk_timer.expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", i, ireq->ir_loc_addr, ireq->ir_num, ireq->ir_rmt_addr, ntohs(ireq->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), req->num_timeout, from_kuid_munged(seq_user_ns(f), sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) { int timer_active; unsigned long timer_expires; const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); u8 icsk_pending; int rx_queue; int state; icsk_pending = smp_load_acquire(&icsk->icsk_pending); if (icsk_pending == ICSK_TIME_RETRANS || icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk_timeout(icsk); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = icsk_timeout(icsk); } else if (timer_pending(&sk->sk_timer)) { timer_active = 2; timer_expires = sk->sk_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sk); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sk->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sk), tcp_snd_cwnd(tp), state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } static void get_timewait4_sock(const struct inet_timewait_sock *tw, struct seq_file *f, int i) { long delta = tw->tw_timer.expires - jiffies; __be32 dest, src; __u16 destp, srcp; dest = tw->tw_daddr; src = tw->tw_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } #define TMPSZ 150 static int tcp4_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; seq_setwidth(seq, TMPSZ - 1); if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait4_sock(v, seq, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq4(v, seq, st->num); else get_tcp4_sock(v, seq, st->num); out: seq_pad(seq, '\n'); return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_tcp_iter_state { struct tcp_iter_state state; unsigned int cur_sk; unsigned int end_sk; unsigned int max_sk; struct sock **batch; bool st_bucket_done; }; struct bpf_iter__tcp { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct sock_common *, sk_common); uid_t uid __aligned(8); }; static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) { struct bpf_iter__tcp ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk_common = sk_common; ctx.uid = uid; return bpf_iter_run_prog(prog, &ctx); } static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { while (iter->cur_sk < iter->end_sk) sock_gen_put(iter->batch[iter->cur_sk++]); } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, unsigned int new_batch_sz) { struct sock **new_batch; new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, GFP_USER | __GFP_NOWARN); if (!new_batch) return -ENOMEM; bpf_iter_tcp_put_batch(iter); kvfree(iter->batch); iter->batch = new_batch; iter->max_sk = new_batch_sz; return 0; } static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, struct sock *start_sk) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; sock_hold(start_sk); iter->batch[iter->end_sk++] = start_sk; sk = sk_nulls_next(start_sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); iter->batch[iter->end_sk++] = sk; } expected++; } } spin_unlock(&hinfo->lhash2[st->bucket].lock); return expected; } static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, struct sock *start_sk) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; sock_hold(start_sk); iter->batch[iter->end_sk++] = start_sk; sk = sk_nulls_next(start_sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); iter->batch[iter->end_sk++] = sk; } expected++; } } spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); return expected; } static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; unsigned int expected; bool resized = false; struct sock *sk; /* The st->bucket is done. Directly advance to the next * bucket instead of having the tcp_seek_last_pos() to skip * one by one in the current bucket and eventually find out * it has to advance to the next bucket. */ if (iter->st_bucket_done) { st->offset = 0; st->bucket++; if (st->state == TCP_SEQ_STATE_LISTENING && st->bucket > hinfo->lhash2_mask) { st->state = TCP_SEQ_STATE_ESTABLISHED; st->bucket = 0; } } again: /* Get a new batch */ iter->cur_sk = 0; iter->end_sk = 0; iter->st_bucket_done = false; sk = tcp_seek_last_pos(seq); if (!sk) return NULL; /* Done */ if (st->state == TCP_SEQ_STATE_LISTENING) expected = bpf_iter_tcp_listening_batch(seq, sk); else expected = bpf_iter_tcp_established_batch(seq, sk); if (iter->end_sk == expected) { iter->st_bucket_done = true; return sk; } if (!resized && !bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2)) { resized = true; goto again; } return sk; } static void *bpf_iter_tcp_seq_start(struct seq_file *seq, loff_t *pos) { /* bpf iter does not support lseek, so it always * continue from where it was stop()-ped. */ if (*pos) return bpf_iter_tcp_batch(seq); return SEQ_START_TOKEN; } static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct sock *sk; /* Whenever seq_next() is called, the iter->cur_sk is * done with seq_show(), so advance to the next sk in * the batch. */ if (iter->cur_sk < iter->end_sk) { /* Keeping st->num consistent in tcp_iter_state. * bpf_iter_tcp does not use st->num. * meta.seq_num is used instead. */ st->num++; /* Move st->offset to the next sk in the bucket such that * the future start() will resume at st->offset in * st->bucket. See tcp_seek_last_pos(). */ st->offset++; sock_gen_put(iter->batch[iter->cur_sk++]); } if (iter->cur_sk < iter->end_sk) sk = iter->batch[iter->cur_sk]; else sk = bpf_iter_tcp_batch(seq); ++*pos; /* Keeping st->last_pos consistent in tcp_iter_state. * bpf iter does not do lseek, so st->last_pos always equals to *pos. */ st->last_pos = *pos; return sk; } static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; int ret; if (v == SEQ_START_TOKEN) return 0; if (sk_fullsock(sk)) lock_sock(sk); if (unlikely(sk_unhashed(sk))) { ret = SEQ_SKIP; goto unlock; } if (sk->sk_state == TCP_TIME_WAIT) { uid = 0; } else if (sk->sk_state == TCP_NEW_SYN_RECV) { const struct request_sock *req = v; uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(req->rsk_listener)); } else { uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); } meta.seq = seq; prog = bpf_iter_get_info(&meta, false); ret = tcp_prog_seq_show(prog, &meta, v, uid); unlock: if (sk_fullsock(sk)) release_sock(sk); return ret; } static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) { struct bpf_tcp_iter_state *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)tcp_prog_seq_show(prog, &meta, v, 0); } if (iter->cur_sk < iter->end_sk) { bpf_iter_tcp_put_batch(iter); iter->st_bucket_done = false; } } static const struct seq_operations bpf_iter_tcp_seq_ops = { .show = bpf_iter_tcp_seq_show, .start = bpf_iter_tcp_seq_start, .next = bpf_iter_tcp_seq_next, .stop = bpf_iter_tcp_seq_stop, }; #endif static unsigned short seq_file_family(const struct seq_file *seq) { const struct tcp_seq_afinfo *afinfo; #ifdef CONFIG_BPF_SYSCALL /* Iterated from bpf_iter. Let the bpf prog to filter instead. */ if (seq->op == &bpf_iter_tcp_seq_ops) return AF_UNSPEC; #endif /* Iterated from proc fs */ afinfo = pde_data(file_inode(seq->file)); return afinfo->family; } static const struct seq_operations tcp4_seq_ops = { .show = tcp4_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp4_seq_afinfo = { .family = AF_INET, }; static int __net_init tcp4_proc_init_net(struct net *net) { if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops, sizeof(struct tcp_iter_state), &tcp4_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit tcp4_proc_exit_net(struct net *net) { remove_proc_entry("tcp", net->proc_net); } static struct pernet_operations tcp4_net_ops = { .init = tcp4_proc_init_net, .exit = tcp4_proc_exit_net, }; int __init tcp4_proc_init(void) { return register_pernet_subsys(&tcp4_net_ops); } void tcp4_proc_exit(void) { unregister_pernet_subsys(&tcp4_net_ops); } #endif /* CONFIG_PROC_FS */ /* @wake is one when sk_stream_write_space() calls us. * This sends EPOLLOUT only if notsent_bytes is half the limit. * This mimics the strategy used in sock_def_write_space(). */ bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); u32 notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } EXPORT_SYMBOL(tcp_stream_memory_free); struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v4_pre_connect, .connect = tcp_v4_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v4_init_sock, .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .splice_eof = tcp_splice_eof, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, .h.hashinfo = NULL, .no_autobind = true, .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); } static void __net_init tcp_set_hashinfo(struct net *net) { struct inet_hashinfo *hinfo; unsigned int ehash_entries; struct net *old_net; if (net_eq(net, &init_net)) goto fallback; old_net = current->nsproxy->net_ns; ehash_entries = READ_ONCE(old_net->ipv4.sysctl_tcp_child_ehash_entries); if (!ehash_entries) goto fallback; ehash_entries = roundup_pow_of_two(ehash_entries); hinfo = inet_pernet_hashinfo_alloc(&tcp_hashinfo, ehash_entries); if (!hinfo) { pr_warn("Failed to allocate TCP ehash (entries: %u) " "for a netns, fallback to the global one\n", ehash_entries); fallback: hinfo = &tcp_hashinfo; ehash_entries = tcp_hashinfo.ehash_mask + 1; } net->ipv4.tcp_death_row.hashinfo = hinfo; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = ehash_entries / 2; net->ipv4.sysctl_max_syn_backlog = max(128U, ehash_entries / 128); } static int __net_init tcp_sk_init(struct net *net) { net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; net->ipv4.sysctl_tcp_syncookies = 1; net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; net->ipv4.sysctl_tcp_orphan_retries = 0; net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; net->ipv4.sysctl_tcp_tw_reuse_delay = 1 * MSEC_PER_SEC; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; refcount_set(&net->ipv4.tcp_death_row.tw_refcount, 1); tcp_set_hashinfo(net); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; net->ipv4.sysctl_tcp_early_retrans = 3; net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION; net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */ net->ipv4.sysctl_tcp_retrans_collapse = 1; net->ipv4.sysctl_tcp_max_reordering = 300; net->ipv4.sysctl_tcp_dsack = 1; net->ipv4.sysctl_tcp_app_win = 31; net->ipv4.sysctl_tcp_adv_win_scale = 1; net->ipv4.sysctl_tcp_frto = 2; net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ net->ipv4.sysctl_tcp_tso_win_divisor = 3; /* Default TSQ limit of 16 TSO segments */ net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536; /* rfc5961 challenge ack rate limiting, per net-ns, disabled by default. */ net->ipv4.sysctl_tcp_challenge_ack_limit = INT_MAX; net->ipv4.sysctl_tcp_min_tso_segs = 2; net->ipv4.sysctl_tcp_tso_rtt_log = 9; /* 2^9 = 512 usec */ net->ipv4.sysctl_tcp_min_rtt_wlen = 300; net->ipv4.sysctl_tcp_autocorking = 1; net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2; net->ipv4.sysctl_tcp_pacing_ss_ratio = 200; net->ipv4.sysctl_tcp_pacing_ca_ratio = 120; if (net != &init_net) { memcpy(net->ipv4.sysctl_tcp_rmem, init_net.ipv4.sysctl_tcp_rmem, sizeof(init_net.ipv4.sysctl_tcp_rmem)); memcpy(net->ipv4.sysctl_tcp_wmem, init_net.ipv4.sysctl_tcp_wmem, sizeof(init_net.ipv4.sysctl_tcp_wmem)); } net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_backlog_ack_defer = 1; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); /* Set default values for PLB */ net->ipv4.sysctl_tcp_plb_enabled = 0; /* Disabled by default */ net->ipv4.sysctl_tcp_plb_idle_rehash_rounds = 3; net->ipv4.sysctl_tcp_plb_rehash_rounds = 12; net->ipv4.sysctl_tcp_plb_suspend_rto_sec = 60; /* Default congestion threshold for PLB to mark a round is 50% */ net->ipv4.sysctl_tcp_plb_cong_thresh = (1 << TCP_PLB_SCALE) / 2; /* Reno is always built in */ if (!net_eq(net, &init_net) && bpf_try_module_get(init_net.ipv4.tcp_congestion_control, init_net.ipv4.tcp_congestion_control->owner)) net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; else net->ipv4.tcp_congestion_control = &tcp_reno; net->ipv4.sysctl_tcp_syn_linear_timeouts = 4; net->ipv4.sysctl_tcp_shrink_window = 0; net->ipv4.sysctl_tcp_pingpong_thresh = 1; net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN); net->ipv4.sysctl_tcp_rto_max_ms = TCP_RTO_MAX_SEC * MSEC_PER_SEC; return 0; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work * and failed setup_net error unwinding path are serialized. * * tcp_twsk_purge() handles twsk in any dead netns, not just those in * net_exit_list, the thread that dismantles a particular twsk must * do so without other thread progressing to refcount_dec_and_test() of * tcp_death_row.tw_refcount. */ mutex_lock(&tcp_exit_batch_mutex); tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { inet_pernet_hashinfo_free(net->ipv4.tcp_death_row.hashinfo); WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } mutex_unlock(&tcp_exit_batch_mutex); } static struct pernet_operations __net_initdata tcp_sk_ops = { .init = tcp_sk_init, .exit = tcp_sk_exit, .exit_batch = tcp_sk_exit_batch, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(tcp, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) #define INIT_BATCH_SZ 16 static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) { struct bpf_tcp_iter_state *iter = priv_data; int err; err = bpf_iter_init_seq_net(priv_data, aux); if (err) return err; err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ); if (err) { bpf_iter_fini_seq_net(priv_data); return err; } return 0; } static void bpf_iter_fini_tcp(void *priv_data) { struct bpf_tcp_iter_state *iter = priv_data; bpf_iter_fini_seq_net(priv_data); kvfree(iter->batch); } static const struct bpf_iter_seq_info tcp_seq_info = { .seq_ops = &bpf_iter_tcp_seq_ops, .init_seq_private = bpf_iter_init_tcp, .fini_seq_private = bpf_iter_fini_tcp, .seq_priv_size = sizeof(struct bpf_tcp_iter_state), }; static const struct bpf_func_proto * bpf_iter_tcp_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sk_setsockopt_proto; case BPF_FUNC_getsockopt: return &bpf_sk_getsockopt_proto; default: return NULL; } } static struct bpf_iter_reg tcp_reg_info = { .target = "tcp", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__tcp, sk_common), PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .get_func_proto = bpf_iter_tcp_get_func_proto, .seq_info = &tcp_seq_info, }; static void __init bpf_iter_register(void) { tcp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON]; if (bpf_iter_reg_target(&tcp_reg_info)) pr_warn("Warning: could not register bpf iterator tcp\n"); } #endif void __init tcp_v4_init(void) { int cpu, res; for_each_possible_cpu(cpu) { struct sock *sk; res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, IPPROTO_TCP, &init_net); if (res) panic("Failed to create the TCP control socket.\n"); sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); /* Please enforce IP_DF and IPID==0 for RST and * ACK sent in SYN-RECV and TIME-WAIT state. */ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; sk->sk_clockid = CLOCK_MONOTONIC; per_cpu(ipv4_tcp_sk.sock, cpu) = sk; } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_register(); #endif } |
| 47 47 20 41 19 19 19 19 19 19 19 19 19 19 18 47 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010-2013 Felix Fietkau <nbd@openwrt.org> * Copyright (C) 2019-2022 Intel Corporation */ #include <linux/netdevice.h> #include <linux/types.h> #include <linux/skbuff.h> #include <linux/debugfs.h> #include <linux/random.h> #include <linux/moduleparam.h> #include <linux/ieee80211.h> #include <linux/minmax.h> #include <net/mac80211.h> #include "rate.h" #include "sta_info.h" #include "rc80211_minstrel_ht.h" #define AVG_AMPDU_SIZE 16 #define AVG_PKT_SIZE 1200 /* Number of bits for an average sized packet */ #define MCS_NBITS ((AVG_PKT_SIZE * AVG_AMPDU_SIZE) << 3) /* Number of symbols for a packet with (bps) bits per symbol */ #define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps)) /* Transmission time (nanoseconds) for a packet containing (syms) symbols */ #define MCS_SYMBOL_TIME(sgi, syms) \ (sgi ? \ ((syms) * 18000 + 4000) / 5 : /* syms * 3.6 us */ \ ((syms) * 1000) << 2 /* syms * 4 us */ \ ) /* Transmit duration for the raw data part of an average sized packet */ #define MCS_DURATION(streams, sgi, bps) \ (MCS_SYMBOL_TIME(sgi, MCS_NSYMS((streams) * (bps))) / AVG_AMPDU_SIZE) #define BW_20 0 #define BW_40 1 #define BW_80 2 /* * Define group sort order: HT40 -> SGI -> #streams */ #define GROUP_IDX(_streams, _sgi, _ht40) \ MINSTREL_HT_GROUP_0 + \ MINSTREL_MAX_STREAMS * 2 * _ht40 + \ MINSTREL_MAX_STREAMS * _sgi + \ _streams - 1 #define _MAX(a, b) (((a)>(b))?(a):(b)) #define GROUP_SHIFT(duration) \ _MAX(0, 16 - __builtin_clz(duration)) /* MCS rate information for an MCS group */ #define __MCS_GROUP(_streams, _sgi, _ht40, _s) \ [GROUP_IDX(_streams, _sgi, _ht40)] = { \ .streams = _streams, \ .shift = _s, \ .bw = _ht40, \ .flags = \ IEEE80211_TX_RC_MCS | \ (_sgi ? IEEE80211_TX_RC_SHORT_GI : 0) | \ (_ht40 ? IEEE80211_TX_RC_40_MHZ_WIDTH : 0), \ .duration = { \ MCS_DURATION(_streams, _sgi, _ht40 ? 54 : 26) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 108 : 52) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 162 : 78) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 216 : 104) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 324 : 156) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 432 : 208) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 486 : 234) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 540 : 260) >> _s \ } \ } #define MCS_GROUP_SHIFT(_streams, _sgi, _ht40) \ GROUP_SHIFT(MCS_DURATION(_streams, _sgi, _ht40 ? 54 : 26)) #define MCS_GROUP(_streams, _sgi, _ht40) \ __MCS_GROUP(_streams, _sgi, _ht40, \ MCS_GROUP_SHIFT(_streams, _sgi, _ht40)) #define VHT_GROUP_IDX(_streams, _sgi, _bw) \ (MINSTREL_VHT_GROUP_0 + \ MINSTREL_MAX_STREAMS * 2 * (_bw) + \ MINSTREL_MAX_STREAMS * (_sgi) + \ (_streams) - 1) #define BW2VBPS(_bw, r3, r2, r1) \ (_bw == BW_80 ? r3 : _bw == BW_40 ? r2 : r1) #define __VHT_GROUP(_streams, _sgi, _bw, _s) \ [VHT_GROUP_IDX(_streams, _sgi, _bw)] = { \ .streams = _streams, \ .shift = _s, \ .bw = _bw, \ .flags = \ IEEE80211_TX_RC_VHT_MCS | \ (_sgi ? IEEE80211_TX_RC_SHORT_GI : 0) | \ (_bw == BW_80 ? IEEE80211_TX_RC_80_MHZ_WIDTH : \ _bw == BW_40 ? IEEE80211_TX_RC_40_MHZ_WIDTH : 0), \ .duration = { \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 117, 54, 26)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 234, 108, 52)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 351, 162, 78)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 468, 216, 104)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 702, 324, 156)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 936, 432, 208)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1053, 486, 234)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1170, 540, 260)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1404, 648, 312)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1560, 720, 346)) >> _s \ } \ } #define VHT_GROUP_SHIFT(_streams, _sgi, _bw) \ GROUP_SHIFT(MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 117, 54, 26))) #define VHT_GROUP(_streams, _sgi, _bw) \ __VHT_GROUP(_streams, _sgi, _bw, \ VHT_GROUP_SHIFT(_streams, _sgi, _bw)) #define CCK_DURATION(_bitrate, _short) \ (1000 * (10 /* SIFS */ + \ (_short ? 72 + 24 : 144 + 48) + \ (8 * (AVG_PKT_SIZE + 4) * 10) / (_bitrate))) #define CCK_DURATION_LIST(_short, _s) \ CCK_DURATION(10, _short) >> _s, \ CCK_DURATION(20, _short) >> _s, \ CCK_DURATION(55, _short) >> _s, \ CCK_DURATION(110, _short) >> _s #define __CCK_GROUP(_s) \ [MINSTREL_CCK_GROUP] = { \ .streams = 1, \ .flags = 0, \ .shift = _s, \ .duration = { \ CCK_DURATION_LIST(false, _s), \ CCK_DURATION_LIST(true, _s) \ } \ } #define CCK_GROUP_SHIFT \ GROUP_SHIFT(CCK_DURATION(10, false)) #define CCK_GROUP __CCK_GROUP(CCK_GROUP_SHIFT) #define OFDM_DURATION(_bitrate) \ (1000 * (16 /* SIFS + signal ext */ + \ 16 /* T_PREAMBLE */ + \ 4 /* T_SIGNAL */ + \ 4 * (((16 + 80 * (AVG_PKT_SIZE + 4) + 6) / \ ((_bitrate) * 4))))) #define OFDM_DURATION_LIST(_s) \ OFDM_DURATION(60) >> _s, \ OFDM_DURATION(90) >> _s, \ OFDM_DURATION(120) >> _s, \ OFDM_DURATION(180) >> _s, \ OFDM_DURATION(240) >> _s, \ OFDM_DURATION(360) >> _s, \ OFDM_DURATION(480) >> _s, \ OFDM_DURATION(540) >> _s #define __OFDM_GROUP(_s) \ [MINSTREL_OFDM_GROUP] = { \ .streams = 1, \ .flags = 0, \ .shift = _s, \ .duration = { \ OFDM_DURATION_LIST(_s), \ } \ } #define OFDM_GROUP_SHIFT \ GROUP_SHIFT(OFDM_DURATION(60)) #define OFDM_GROUP __OFDM_GROUP(OFDM_GROUP_SHIFT) static bool minstrel_vht_only = true; module_param(minstrel_vht_only, bool, 0644); MODULE_PARM_DESC(minstrel_vht_only, "Use only VHT rates when VHT is supported by sta."); /* * To enable sufficiently targeted rate sampling, MCS rates are divided into * groups, based on the number of streams and flags (HT40, SGI) that they * use. * * Sortorder has to be fixed for GROUP_IDX macro to be applicable: * BW -> SGI -> #streams */ const struct mcs_group minstrel_mcs_groups[] = { MCS_GROUP(1, 0, BW_20), MCS_GROUP(2, 0, BW_20), MCS_GROUP(3, 0, BW_20), MCS_GROUP(4, 0, BW_20), MCS_GROUP(1, 1, BW_20), MCS_GROUP(2, 1, BW_20), MCS_GROUP(3, 1, BW_20), MCS_GROUP(4, 1, BW_20), MCS_GROUP(1, 0, BW_40), MCS_GROUP(2, 0, BW_40), MCS_GROUP(3, 0, BW_40), MCS_GROUP(4, 0, BW_40), MCS_GROUP(1, 1, BW_40), MCS_GROUP(2, 1, BW_40), MCS_GROUP(3, 1, BW_40), MCS_GROUP(4, 1, BW_40), CCK_GROUP, OFDM_GROUP, VHT_GROUP(1, 0, BW_20), VHT_GROUP(2, 0, BW_20), VHT_GROUP(3, 0, BW_20), VHT_GROUP(4, 0, BW_20), VHT_GROUP(1, 1, BW_20), VHT_GROUP(2, 1, BW_20), VHT_GROUP(3, 1, BW_20), VHT_GROUP(4, 1, BW_20), VHT_GROUP(1, 0, BW_40), VHT_GROUP(2, 0, BW_40), VHT_GROUP(3, 0, BW_40), VHT_GROUP(4, 0, BW_40), VHT_GROUP(1, 1, BW_40), VHT_GROUP(2, 1, BW_40), VHT_GROUP(3, 1, BW_40), VHT_GROUP(4, 1, BW_40), VHT_GROUP(1, 0, BW_80), VHT_GROUP(2, 0, BW_80), VHT_GROUP(3, 0, BW_80), VHT_GROUP(4, 0, BW_80), VHT_GROUP(1, 1, BW_80), VHT_GROUP(2, 1, BW_80), VHT_GROUP(3, 1, BW_80), VHT_GROUP(4, 1, BW_80), }; const s16 minstrel_cck_bitrates[4] = { 10, 20, 55, 110 }; const s16 minstrel_ofdm_bitrates[8] = { 60, 90, 120, 180, 240, 360, 480, 540 }; static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES] __read_mostly; static const u8 minstrel_sample_seq[] = { MINSTREL_SAMPLE_TYPE_INC, MINSTREL_SAMPLE_TYPE_JUMP, MINSTREL_SAMPLE_TYPE_INC, MINSTREL_SAMPLE_TYPE_JUMP, MINSTREL_SAMPLE_TYPE_INC, MINSTREL_SAMPLE_TYPE_SLOW, }; static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi); /* * Some VHT MCSes are invalid (when Ndbps / Nes is not an integer) * e.g for MCS9@20MHzx1Nss: Ndbps=8x52*(5/6) Nes=1 * * Returns the valid mcs map for struct minstrel_mcs_group_data.supported */ static u16 minstrel_get_valid_vht_rates(int bw, int nss, __le16 mcs_map) { u16 mask = 0; if (bw == BW_20) { if (nss != 3 && nss != 6) mask = BIT(9); } else if (bw == BW_80) { if (nss == 3 || nss == 7) mask = BIT(6); else if (nss == 6) mask = BIT(9); } else { WARN_ON(bw != BW_40); } switch ((le16_to_cpu(mcs_map) >> (2 * (nss - 1))) & 3) { case IEEE80211_VHT_MCS_SUPPORT_0_7: mask |= 0x300; break; case IEEE80211_VHT_MCS_SUPPORT_0_8: mask |= 0x200; break; case IEEE80211_VHT_MCS_SUPPORT_0_9: break; default: mask = 0x3ff; } return 0x3ff & ~mask; } static bool minstrel_ht_is_legacy_group(int group) { return group == MINSTREL_CCK_GROUP || group == MINSTREL_OFDM_GROUP; } /* * Look up an MCS group index based on mac80211 rate information */ static int minstrel_ht_get_group_idx(struct ieee80211_tx_rate *rate) { return GROUP_IDX((rate->idx / 8) + 1, !!(rate->flags & IEEE80211_TX_RC_SHORT_GI), !!(rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)); } /* * Look up an MCS group index based on new cfg80211 rate_info. */ static int minstrel_ht_ri_get_group_idx(struct rate_info *rate) { return GROUP_IDX((rate->mcs / 8) + 1, !!(rate->flags & RATE_INFO_FLAGS_SHORT_GI), !!(rate->bw & RATE_INFO_BW_40)); } static int minstrel_vht_get_group_idx(struct ieee80211_tx_rate *rate) { return VHT_GROUP_IDX(ieee80211_rate_get_vht_nss(rate), !!(rate->flags & IEEE80211_TX_RC_SHORT_GI), !!(rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) + 2*!!(rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)); } /* * Look up an MCS group index based on new cfg80211 rate_info. */ static int minstrel_vht_ri_get_group_idx(struct rate_info *rate) { return VHT_GROUP_IDX(rate->nss, !!(rate->flags & RATE_INFO_FLAGS_SHORT_GI), !!(rate->bw & RATE_INFO_BW_40) + 2*!!(rate->bw & RATE_INFO_BW_80)); } static struct minstrel_rate_stats * minstrel_ht_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_tx_rate *rate) { int group, idx; if (rate->flags & IEEE80211_TX_RC_MCS) { group = minstrel_ht_get_group_idx(rate); idx = rate->idx % 8; goto out; } if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { group = minstrel_vht_get_group_idx(rate); idx = ieee80211_rate_get_vht_mcs(rate); goto out; } group = MINSTREL_CCK_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->cck_rates); idx++) { if (!(mi->supported[group] & BIT(idx))) continue; if (rate->idx != mp->cck_rates[idx]) continue; /* short preamble */ if ((mi->supported[group] & BIT(idx + 4)) && (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)) idx += 4; goto out; } group = MINSTREL_OFDM_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->ofdm_rates[0]); idx++) if (rate->idx == mp->ofdm_rates[mi->band][idx]) goto out; idx = 0; out: return &mi->groups[group].rates[idx]; } /* * Get the minstrel rate statistics for specified STA and rate info. */ static struct minstrel_rate_stats * minstrel_ht_ri_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_rate_status *rate_status) { int group, idx; struct rate_info *rate = &rate_status->rate_idx; if (rate->flags & RATE_INFO_FLAGS_MCS) { group = minstrel_ht_ri_get_group_idx(rate); idx = rate->mcs % 8; goto out; } if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) { group = minstrel_vht_ri_get_group_idx(rate); idx = rate->mcs; goto out; } group = MINSTREL_CCK_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->cck_rates); idx++) { if (rate->legacy != minstrel_cck_bitrates[ mp->cck_rates[idx] ]) continue; /* short preamble */ if ((mi->supported[group] & BIT(idx + 4)) && mi->use_short_preamble) idx += 4; goto out; } group = MINSTREL_OFDM_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->ofdm_rates[0]); idx++) if (rate->legacy == minstrel_ofdm_bitrates[ mp->ofdm_rates[mi->band][idx] ]) goto out; idx = 0; out: return &mi->groups[group].rates[idx]; } static inline struct minstrel_rate_stats * minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index) { return &mi->groups[MI_RATE_GROUP(index)].rates[MI_RATE_IDX(index)]; } static inline int minstrel_get_duration(int index) { const struct mcs_group *group = &minstrel_mcs_groups[MI_RATE_GROUP(index)]; unsigned int duration = group->duration[MI_RATE_IDX(index)]; return duration << group->shift; } static unsigned int minstrel_ht_avg_ampdu_len(struct minstrel_ht_sta *mi) { int duration; if (mi->avg_ampdu_len) return MINSTREL_TRUNC(mi->avg_ampdu_len); if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(mi->max_tp_rate[0]))) return 1; duration = minstrel_get_duration(mi->max_tp_rate[0]); if (duration > 400 * 1000) return 2; if (duration > 250 * 1000) return 4; if (duration > 150 * 1000) return 8; return 16; } /* * Return current throughput based on the average A-MPDU length, taking into * account the expected number of retransmissions and their expected length */ int minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, int prob_avg) { unsigned int nsecs = 0, overhead = mi->overhead; unsigned int ampdu_len = 1; /* do not account throughput if success prob is below 10% */ if (prob_avg < MINSTREL_FRAC(10, 100)) return 0; if (minstrel_ht_is_legacy_group(group)) overhead = mi->overhead_legacy; else ampdu_len = minstrel_ht_avg_ampdu_len(mi); nsecs = 1000 * overhead / ampdu_len; nsecs += minstrel_mcs_groups[group].duration[rate] << minstrel_mcs_groups[group].shift; /* * For the throughput calculation, limit the probability value to 90% to * account for collision related packet error rate fluctuation * (prob is scaled - see MINSTREL_FRAC above) */ if (prob_avg > MINSTREL_FRAC(90, 100)) prob_avg = MINSTREL_FRAC(90, 100); return MINSTREL_TRUNC(100 * ((prob_avg * 1000000) / nsecs)); } /* * Find & sort topmost throughput rates * * If multiple rates provide equal throughput the sorting is based on their * current success probability. Higher success probability is preferred among * MCS groups, CCK rates do not provide aggregation and are therefore at last. */ static void minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u16 index, u16 *tp_list) { int cur_group, cur_idx, cur_tp_avg, cur_prob; int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; int j = MAX_THR_RATES; cur_group = MI_RATE_GROUP(index); cur_idx = MI_RATE_IDX(index); cur_prob = mi->groups[cur_group].rates[cur_idx].prob_avg; cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, cur_prob); do { tmp_group = MI_RATE_GROUP(tp_list[j - 1]); tmp_idx = MI_RATE_IDX(tp_list[j - 1]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); if (cur_tp_avg < tmp_tp_avg || (cur_tp_avg == tmp_tp_avg && cur_prob <= tmp_prob)) break; j--; } while (j > 0); if (j < MAX_THR_RATES - 1) { memmove(&tp_list[j + 1], &tp_list[j], (sizeof(*tp_list) * (MAX_THR_RATES - (j + 1)))); } if (j < MAX_THR_RATES) tp_list[j] = index; } /* * Find and set the topmost probability rate per sta and per group */ static void minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 *dest, u16 index) { struct minstrel_mcs_group_data *mg; struct minstrel_rate_stats *mrs; int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; int max_tp_group, max_tp_idx, max_tp_prob; int cur_tp_avg, cur_group, cur_idx; int max_gpr_group, max_gpr_idx; int max_gpr_tp_avg, max_gpr_prob; cur_group = MI_RATE_GROUP(index); cur_idx = MI_RATE_IDX(index); mg = &mi->groups[cur_group]; mrs = &mg->rates[cur_idx]; tmp_group = MI_RATE_GROUP(*dest); tmp_idx = MI_RATE_IDX(*dest); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); /* if max_tp_rate[0] is from MCS_GROUP max_prob_rate get selected from * MCS_GROUP as well as CCK_GROUP rates do not allow aggregation */ max_tp_group = MI_RATE_GROUP(mi->max_tp_rate[0]); max_tp_idx = MI_RATE_IDX(mi->max_tp_rate[0]); max_tp_prob = mi->groups[max_tp_group].rates[max_tp_idx].prob_avg; if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(index)) && !minstrel_ht_is_legacy_group(max_tp_group)) return; /* skip rates faster than max tp rate with lower prob */ if (minstrel_get_duration(mi->max_tp_rate[0]) > minstrel_get_duration(index) && mrs->prob_avg < max_tp_prob) return; max_gpr_group = MI_RATE_GROUP(mg->max_group_prob_rate); max_gpr_idx = MI_RATE_IDX(mg->max_group_prob_rate); max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_avg; if (mrs->prob_avg > MINSTREL_FRAC(75, 100)) { cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, mrs->prob_avg); if (cur_tp_avg > tmp_tp_avg) *dest = index; max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, max_gpr_idx, max_gpr_prob); if (cur_tp_avg > max_gpr_tp_avg) mg->max_group_prob_rate = index; } else { if (mrs->prob_avg > tmp_prob) *dest = index; if (mrs->prob_avg > max_gpr_prob) mg->max_group_prob_rate = index; } } /* * Assign new rate set per sta and use CCK rates only if the fastest * rate (max_tp_rate[0]) is from CCK group. This prohibits such sorted * rate sets where MCS and CCK rates are mixed, because CCK rates can * not use aggregation. */ static void minstrel_ht_assign_best_tp_rates(struct minstrel_ht_sta *mi, u16 tmp_mcs_tp_rate[MAX_THR_RATES], u16 tmp_legacy_tp_rate[MAX_THR_RATES]) { unsigned int tmp_group, tmp_idx, tmp_cck_tp, tmp_mcs_tp, tmp_prob; int i; tmp_group = MI_RATE_GROUP(tmp_legacy_tp_rate[0]); tmp_idx = MI_RATE_IDX(tmp_legacy_tp_rate[0]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_cck_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); tmp_group = MI_RATE_GROUP(tmp_mcs_tp_rate[0]); tmp_idx = MI_RATE_IDX(tmp_mcs_tp_rate[0]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_mcs_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); if (tmp_cck_tp > tmp_mcs_tp) { for(i = 0; i < MAX_THR_RATES; i++) { minstrel_ht_sort_best_tp_rates(mi, tmp_legacy_tp_rate[i], tmp_mcs_tp_rate); } } } /* * Try to increase robustness of max_prob rate by decrease number of * streams if possible. */ static inline void minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; int tmp_max_streams, group, tmp_idx, tmp_prob; int tmp_tp = 0; if (!mi->sta->deflink.ht_cap.ht_supported) return; group = MI_RATE_GROUP(mi->max_tp_rate[0]); tmp_max_streams = minstrel_mcs_groups[group].streams; for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { mg = &mi->groups[group]; if (!mi->supported[group] || group == MINSTREL_CCK_GROUP) continue; tmp_idx = MI_RATE_IDX(mg->max_group_prob_rate); tmp_prob = mi->groups[group].rates[tmp_idx].prob_avg; if (tmp_tp < minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob) && (minstrel_mcs_groups[group].streams < tmp_max_streams)) { mi->max_prob_rate = mg->max_group_prob_rate; tmp_tp = minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob); } } } static u16 __minstrel_ht_get_sample_rate(struct minstrel_ht_sta *mi, enum minstrel_sample_type type) { u16 *rates = mi->sample[type].sample_rates; u16 cur; int i; for (i = 0; i < MINSTREL_SAMPLE_RATES; i++) { if (!rates[i]) continue; cur = rates[i]; rates[i] = 0; return cur; } return 0; } static inline int minstrel_ewma(int old, int new, int weight) { int diff, incr; diff = new - old; incr = (EWMA_DIV - weight) * diff / EWMA_DIV; return old + incr; } static inline int minstrel_filter_avg_add(u16 *prev_1, u16 *prev_2, s32 in) { s32 out_1 = *prev_1; s32 out_2 = *prev_2; s32 val; if (!in) in += 1; if (!out_1) { val = out_1 = in; goto out; } val = MINSTREL_AVG_COEFF1 * in; val += MINSTREL_AVG_COEFF2 * out_1; val += MINSTREL_AVG_COEFF3 * out_2; val >>= MINSTREL_SCALE; if (val > 1 << MINSTREL_SCALE) val = 1 << MINSTREL_SCALE; if (val < 0) val = 1; out: *prev_2 = out_1; *prev_1 = val; return val; } /* * Recalculate statistics and counters of a given rate */ static void minstrel_ht_calc_rate_stats(struct minstrel_priv *mp, struct minstrel_rate_stats *mrs) { unsigned int cur_prob; if (unlikely(mrs->attempts > 0)) { cur_prob = MINSTREL_FRAC(mrs->success, mrs->attempts); minstrel_filter_avg_add(&mrs->prob_avg, &mrs->prob_avg_1, cur_prob); mrs->att_hist += mrs->attempts; mrs->succ_hist += mrs->success; } mrs->last_success = mrs->success; mrs->last_attempts = mrs->attempts; mrs->success = 0; mrs->attempts = 0; } static bool minstrel_ht_find_sample_rate(struct minstrel_ht_sta *mi, int type, int idx) { int i; for (i = 0; i < MINSTREL_SAMPLE_RATES; i++) { u16 cur = mi->sample[type].sample_rates[i]; if (cur == idx) return true; if (!cur) break; } return false; } static int minstrel_ht_move_sample_rates(struct minstrel_ht_sta *mi, int type, u32 fast_rate_dur, u32 slow_rate_dur) { u16 *rates = mi->sample[type].sample_rates; int i, j; for (i = 0, j = 0; i < MINSTREL_SAMPLE_RATES; i++) { u32 duration; bool valid = false; u16 cur; cur = rates[i]; if (!cur) continue; duration = minstrel_get_duration(cur); switch (type) { case MINSTREL_SAMPLE_TYPE_SLOW: valid = duration > fast_rate_dur && duration < slow_rate_dur; break; case MINSTREL_SAMPLE_TYPE_INC: case MINSTREL_SAMPLE_TYPE_JUMP: valid = duration < fast_rate_dur; break; default: valid = false; break; } if (!valid) { rates[i] = 0; continue; } if (i == j) continue; rates[j++] = cur; rates[i] = 0; } return j; } static int minstrel_ht_group_min_rate_offset(struct minstrel_ht_sta *mi, int group, u32 max_duration) { u16 supported = mi->supported[group]; int i; for (i = 0; i < MCS_GROUP_RATES && supported; i++, supported >>= 1) { if (!(supported & BIT(0))) continue; if (minstrel_get_duration(MI_RATE(group, i)) >= max_duration) continue; return i; } return -1; } /* * Incremental update rates: * Flip through groups and pick the first group rate that is faster than the * highest currently selected rate */ static u16 minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur) { u8 type = MINSTREL_SAMPLE_TYPE_INC; int i, index = 0; u8 group; group = mi->sample[type].sample_group; for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) { group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups); index = minstrel_ht_group_min_rate_offset(mi, group, fast_rate_dur); if (index < 0) continue; index = MI_RATE(group, index & 0xf); if (!minstrel_ht_find_sample_rate(mi, type, index)) goto out; } index = 0; out: mi->sample[type].sample_group = group; return index; } static int minstrel_ht_next_group_sample_rate(struct minstrel_ht_sta *mi, int group, u16 supported, int offset) { struct minstrel_mcs_group_data *mg = &mi->groups[group]; u16 idx; int i; for (i = 0; i < MCS_GROUP_RATES; i++) { idx = sample_table[mg->column][mg->index]; if (++mg->index >= MCS_GROUP_RATES) { mg->index = 0; if (++mg->column >= ARRAY_SIZE(sample_table)) mg->column = 0; } if (idx < offset) continue; if (!(supported & BIT(idx))) continue; return MI_RATE(group, idx); } return -1; } /* * Jump rates: * Sample random rates, use those that are faster than the highest * currently selected rate. Rates between the fastest and the slowest * get sorted into the slow sample bucket, but only if it has room */ static u16 minstrel_ht_next_jump_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur, u32 slow_rate_dur, int *slow_rate_ofs) { struct minstrel_rate_stats *mrs; u32 max_duration = slow_rate_dur; int i, index, offset; u16 *slow_rates; u16 supported; u32 duration; u8 group; if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) max_duration = fast_rate_dur; slow_rates = mi->sample[MINSTREL_SAMPLE_TYPE_SLOW].sample_rates; group = mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_group; for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) { u8 type; group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups); supported = mi->supported[group]; if (!supported) continue; offset = minstrel_ht_group_min_rate_offset(mi, group, max_duration); if (offset < 0) continue; index = minstrel_ht_next_group_sample_rate(mi, group, supported, offset); if (index < 0) continue; duration = minstrel_get_duration(index); if (duration < fast_rate_dur) type = MINSTREL_SAMPLE_TYPE_JUMP; else type = MINSTREL_SAMPLE_TYPE_SLOW; if (minstrel_ht_find_sample_rate(mi, type, index)) continue; if (type == MINSTREL_SAMPLE_TYPE_JUMP) goto found; if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) continue; if (duration >= slow_rate_dur) continue; /* skip slow rates with high success probability */ mrs = minstrel_get_ratestats(mi, index); if (mrs->prob_avg > MINSTREL_FRAC(95, 100)) continue; slow_rates[(*slow_rate_ofs)++] = index; if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) max_duration = fast_rate_dur; } index = 0; found: mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_group = group; return index; } static void minstrel_ht_refill_sample_rates(struct minstrel_ht_sta *mi) { u32 prob_dur = minstrel_get_duration(mi->max_prob_rate); u32 tp_dur = minstrel_get_duration(mi->max_tp_rate[0]); u32 tp2_dur = minstrel_get_duration(mi->max_tp_rate[1]); u32 fast_rate_dur = min(min(tp_dur, tp2_dur), prob_dur); u32 slow_rate_dur = max(max(tp_dur, tp2_dur), prob_dur); u16 *rates; int i, j; rates = mi->sample[MINSTREL_SAMPLE_TYPE_INC].sample_rates; i = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_INC, fast_rate_dur, slow_rate_dur); while (i < MINSTREL_SAMPLE_RATES) { rates[i] = minstrel_ht_next_inc_rate(mi, tp_dur); if (!rates[i]) break; i++; } rates = mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_rates; i = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_JUMP, fast_rate_dur, slow_rate_dur); j = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_SLOW, fast_rate_dur, slow_rate_dur); while (i < MINSTREL_SAMPLE_RATES) { rates[i] = minstrel_ht_next_jump_rate(mi, fast_rate_dur, slow_rate_dur, &j); if (!rates[i]) break; i++; } for (i = 0; i < ARRAY_SIZE(mi->sample); i++) memcpy(mi->sample[i].cur_sample_rates, mi->sample[i].sample_rates, sizeof(mi->sample[i].cur_sample_rates)); } /* * Update rate statistics and select new primary rates * * Rules for rate selection: * - max_prob_rate must use only one stream, as a tradeoff between delivery * probability and throughput during strong fluctuations * - as long as the max prob rate has a probability of more than 75%, pick * higher throughput rates, even if the probability is a bit lower */ static void minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; struct minstrel_rate_stats *mrs; int group, i, j, cur_prob; u16 tmp_mcs_tp_rate[MAX_THR_RATES], tmp_group_tp_rate[MAX_THR_RATES]; u16 tmp_legacy_tp_rate[MAX_THR_RATES], tmp_max_prob_rate; u16 index; bool ht_supported = mi->sta->deflink.ht_cap.ht_supported; if (mi->ampdu_packets > 0) { if (!ieee80211_hw_check(mp->hw, TX_STATUS_NO_AMPDU_LEN)) mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), EWMA_LEVEL); else mi->avg_ampdu_len = 0; mi->ampdu_len = 0; mi->ampdu_packets = 0; } if (mi->supported[MINSTREL_CCK_GROUP]) group = MINSTREL_CCK_GROUP; else if (mi->supported[MINSTREL_OFDM_GROUP]) group = MINSTREL_OFDM_GROUP; else group = 0; index = MI_RATE(group, 0); for (j = 0; j < ARRAY_SIZE(tmp_legacy_tp_rate); j++) tmp_legacy_tp_rate[j] = index; if (mi->supported[MINSTREL_VHT_GROUP_0]) group = MINSTREL_VHT_GROUP_0; else if (ht_supported) group = MINSTREL_HT_GROUP_0; else if (mi->supported[MINSTREL_CCK_GROUP]) group = MINSTREL_CCK_GROUP; else group = MINSTREL_OFDM_GROUP; index = MI_RATE(group, 0); tmp_max_prob_rate = index; for (j = 0; j < ARRAY_SIZE(tmp_mcs_tp_rate); j++) tmp_mcs_tp_rate[j] = index; /* Find best rate sets within all MCS groups*/ for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { u16 *tp_rate = tmp_mcs_tp_rate; u16 last_prob = 0; mg = &mi->groups[group]; if (!mi->supported[group]) continue; /* (re)Initialize group rate indexes */ for(j = 0; j < MAX_THR_RATES; j++) tmp_group_tp_rate[j] = MI_RATE(group, 0); if (group == MINSTREL_CCK_GROUP && ht_supported) tp_rate = tmp_legacy_tp_rate; for (i = MCS_GROUP_RATES - 1; i >= 0; i--) { if (!(mi->supported[group] & BIT(i))) continue; index = MI_RATE(group, i); mrs = &mg->rates[i]; mrs->retry_updated = false; minstrel_ht_calc_rate_stats(mp, mrs); if (mrs->att_hist) last_prob = max(last_prob, mrs->prob_avg); else mrs->prob_avg = max(last_prob, mrs->prob_avg); cur_prob = mrs->prob_avg; if (minstrel_ht_get_tp_avg(mi, group, i, cur_prob) == 0) continue; /* Find max throughput rate set */ minstrel_ht_sort_best_tp_rates(mi, index, tp_rate); /* Find max throughput rate set within a group */ minstrel_ht_sort_best_tp_rates(mi, index, tmp_group_tp_rate); } memcpy(mg->max_group_tp_rate, tmp_group_tp_rate, sizeof(mg->max_group_tp_rate)); } /* Assign new rate set per sta */ minstrel_ht_assign_best_tp_rates(mi, tmp_mcs_tp_rate, tmp_legacy_tp_rate); memcpy(mi->max_tp_rate, tmp_mcs_tp_rate, sizeof(mi->max_tp_rate)); for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { if (!mi->supported[group]) continue; mg = &mi->groups[group]; mg->max_group_prob_rate = MI_RATE(group, 0); for (i = 0; i < MCS_GROUP_RATES; i++) { if (!(mi->supported[group] & BIT(i))) continue; index = MI_RATE(group, i); /* Find max probability rate per group and global */ minstrel_ht_set_best_prob_rate(mi, &tmp_max_prob_rate, index); } } mi->max_prob_rate = tmp_max_prob_rate; /* Try to increase robustness of max_prob_rate*/ minstrel_ht_prob_rate_reduce_streams(mi); minstrel_ht_refill_sample_rates(mi); #ifdef CONFIG_MAC80211_DEBUGFS /* use fixed index if set */ if (mp->fixed_rate_idx != -1) { for (i = 0; i < 4; i++) mi->max_tp_rate[i] = mp->fixed_rate_idx; mi->max_prob_rate = mp->fixed_rate_idx; } #endif /* Reset update timer */ mi->last_stats_update = jiffies; mi->sample_time = jiffies; } static bool minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_tx_rate *rate) { int i; if (rate->idx < 0) return false; if (!rate->count) return false; if (rate->flags & IEEE80211_TX_RC_MCS || rate->flags & IEEE80211_TX_RC_VHT_MCS) return true; for (i = 0; i < ARRAY_SIZE(mp->cck_rates); i++) if (rate->idx == mp->cck_rates[i]) return true; for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates[0]); i++) if (rate->idx == mp->ofdm_rates[mi->band][i]) return true; return false; } /* * Check whether rate_status contains valid information. */ static bool minstrel_ht_ri_txstat_valid(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_rate_status *rate_status) { int i; if (!rate_status) return false; if (!rate_status->try_count) return false; if (rate_status->rate_idx.flags & RATE_INFO_FLAGS_MCS || rate_status->rate_idx.flags & RATE_INFO_FLAGS_VHT_MCS) return true; for (i = 0; i < ARRAY_SIZE(mp->cck_rates); i++) { if (rate_status->rate_idx.legacy == minstrel_cck_bitrates[ mp->cck_rates[i] ]) return true; } for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates); i++) { if (rate_status->rate_idx.legacy == minstrel_ofdm_bitrates[ mp->ofdm_rates[mi->band][i] ]) return true; } return false; } static void minstrel_downgrade_rate(struct minstrel_ht_sta *mi, u16 *idx, bool primary) { int group, orig_group; orig_group = group = MI_RATE_GROUP(*idx); while (group > 0) { group--; if (!mi->supported[group]) continue; if (minstrel_mcs_groups[group].streams > minstrel_mcs_groups[orig_group].streams) continue; if (primary) *idx = mi->groups[group].max_group_tp_rate[0]; else *idx = mi->groups[group].max_group_tp_rate[1]; break; } } static void minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, void *priv_sta, struct ieee80211_tx_status *st) { struct ieee80211_tx_info *info = st->info; struct minstrel_ht_sta *mi = priv_sta; struct ieee80211_tx_rate *ar = info->status.rates; struct minstrel_rate_stats *rate, *rate2; struct minstrel_priv *mp = priv; u32 update_interval = mp->update_interval; bool last, update = false; int i; /* Ignore packet that was sent with noAck flag */ if (info->flags & IEEE80211_TX_CTL_NO_ACK) return; /* This packet was aggregated but doesn't carry status info */ if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) return; if (!(info->flags & IEEE80211_TX_STAT_AMPDU)) { info->status.ampdu_ack_len = (info->flags & IEEE80211_TX_STAT_ACK ? 1 : 0); info->status.ampdu_len = 1; } /* wraparound */ if (mi->total_packets >= ~0 - info->status.ampdu_len) { mi->total_packets = 0; mi->sample_packets = 0; } mi->total_packets += info->status.ampdu_len; if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) mi->sample_packets += info->status.ampdu_len; mi->ampdu_packets++; mi->ampdu_len += info->status.ampdu_len; if (st->rates && st->n_rates) { last = !minstrel_ht_ri_txstat_valid(mp, mi, &(st->rates[0])); for (i = 0; !last; i++) { last = (i == st->n_rates - 1) || !minstrel_ht_ri_txstat_valid(mp, mi, &(st->rates[i + 1])); rate = minstrel_ht_ri_get_stats(mp, mi, &(st->rates[i])); if (last) rate->success += info->status.ampdu_ack_len; rate->attempts += st->rates[i].try_count * info->status.ampdu_len; } } else { last = !minstrel_ht_txstat_valid(mp, mi, &ar[0]); for (i = 0; !last; i++) { last = (i == IEEE80211_TX_MAX_RATES - 1) || !minstrel_ht_txstat_valid(mp, mi, &ar[i + 1]); rate = minstrel_ht_get_stats(mp, mi, &ar[i]); if (last) rate->success += info->status.ampdu_ack_len; rate->attempts += ar[i].count * info->status.ampdu_len; } } if (mp->hw->max_rates > 1) { /* * check for sudden death of spatial multiplexing, * downgrade to a lower number of streams if necessary. */ rate = minstrel_get_ratestats(mi, mi->max_tp_rate[0]); if (rate->attempts > 30 && rate->success < rate->attempts / 4) { minstrel_downgrade_rate(mi, &mi->max_tp_rate[0], true); update = true; } rate2 = minstrel_get_ratestats(mi, mi->max_tp_rate[1]); if (rate2->attempts > 30 && rate2->success < rate2->attempts / 4) { minstrel_downgrade_rate(mi, &mi->max_tp_rate[1], false); update = true; } } if (time_after(jiffies, mi->last_stats_update + update_interval)) { update = true; minstrel_ht_update_stats(mp, mi); } if (update) minstrel_ht_update_rates(mp, mi); } static void minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, int index) { struct minstrel_rate_stats *mrs; unsigned int tx_time, tx_time_rtscts, tx_time_data; unsigned int cw = mp->cw_min; unsigned int ctime = 0; unsigned int t_slot = 9; /* FIXME */ unsigned int ampdu_len = minstrel_ht_avg_ampdu_len(mi); unsigned int overhead = 0, overhead_rtscts = 0; mrs = minstrel_get_ratestats(mi, index); if (mrs->prob_avg < MINSTREL_FRAC(1, 10)) { mrs->retry_count = 1; mrs->retry_count_rtscts = 1; return; } mrs->retry_count = 2; mrs->retry_count_rtscts = 2; mrs->retry_updated = true; tx_time_data = minstrel_get_duration(index) * ampdu_len / 1000; /* Contention time for first 2 tries */ ctime = (t_slot * cw) >> 1; cw = min((cw << 1) | 1, mp->cw_max); ctime += (t_slot * cw) >> 1; cw = min((cw << 1) | 1, mp->cw_max); if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(index))) { overhead = mi->overhead_legacy; overhead_rtscts = mi->overhead_legacy_rtscts; } else { overhead = mi->overhead; overhead_rtscts = mi->overhead_rtscts; } /* Total TX time for data and Contention after first 2 tries */ tx_time = ctime + 2 * (overhead + tx_time_data); tx_time_rtscts = ctime + 2 * (overhead_rtscts + tx_time_data); /* See how many more tries we can fit inside segment size */ do { /* Contention time for this try */ ctime = (t_slot * cw) >> 1; cw = min((cw << 1) | 1, mp->cw_max); /* Total TX time after this try */ tx_time += ctime + overhead + tx_time_data; tx_time_rtscts += ctime + overhead_rtscts + tx_time_data; if (tx_time_rtscts < mp->segment_size) mrs->retry_count_rtscts++; } while ((tx_time < mp->segment_size) && (++mrs->retry_count < mp->max_retry)); } static void minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_sta_rates *ratetbl, int offset, int index) { int group_idx = MI_RATE_GROUP(index); const struct mcs_group *group = &minstrel_mcs_groups[group_idx]; struct minstrel_rate_stats *mrs; u8 idx; u16 flags = group->flags; mrs = minstrel_get_ratestats(mi, index); if (!mrs->retry_updated) minstrel_calc_retransmit(mp, mi, index); if (mrs->prob_avg < MINSTREL_FRAC(20, 100) || !mrs->retry_count) { ratetbl->rate[offset].count = 2; ratetbl->rate[offset].count_rts = 2; ratetbl->rate[offset].count_cts = 2; } else { ratetbl->rate[offset].count = mrs->retry_count; ratetbl->rate[offset].count_cts = mrs->retry_count; ratetbl->rate[offset].count_rts = mrs->retry_count_rtscts; } index = MI_RATE_IDX(index); if (group_idx == MINSTREL_CCK_GROUP) idx = mp->cck_rates[index % ARRAY_SIZE(mp->cck_rates)]; else if (group_idx == MINSTREL_OFDM_GROUP) idx = mp->ofdm_rates[mi->band][index % ARRAY_SIZE(mp->ofdm_rates[0])]; else if (flags & IEEE80211_TX_RC_VHT_MCS) idx = ((group->streams - 1) << 4) | (index & 0xF); else idx = index + (group->streams - 1) * 8; /* enable RTS/CTS if needed: * - if station is in dynamic SMPS (and streams > 1) * - for fallback rates, to increase chances of getting through */ if (offset > 0 || (mi->sta->deflink.smps_mode == IEEE80211_SMPS_DYNAMIC && group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; flags |= IEEE80211_TX_RC_USE_RTS_CTS; } ratetbl->rate[offset].idx = idx; ratetbl->rate[offset].flags = flags; } static inline int minstrel_ht_get_prob_avg(struct minstrel_ht_sta *mi, int rate) { int group = MI_RATE_GROUP(rate); rate = MI_RATE_IDX(rate); return mi->groups[group].rates[rate].prob_avg; } static int minstrel_ht_get_max_amsdu_len(struct minstrel_ht_sta *mi) { int group = MI_RATE_GROUP(mi->max_prob_rate); const struct mcs_group *g = &minstrel_mcs_groups[group]; int rate = MI_RATE_IDX(mi->max_prob_rate); unsigned int duration; /* Disable A-MSDU if max_prob_rate is bad */ if (mi->groups[group].rates[rate].prob_avg < MINSTREL_FRAC(50, 100)) return 1; duration = g->duration[rate]; duration <<= g->shift; /* If the rate is slower than single-stream MCS1, make A-MSDU limit small */ if (duration > MCS_DURATION(1, 0, 52)) return 500; /* * If the rate is slower than single-stream MCS4, limit A-MSDU to usual * data packet size */ if (duration > MCS_DURATION(1, 0, 104)) return 1600; /* * If the rate is slower than single-stream MCS7, or if the max throughput * rate success probability is less than 75%, limit A-MSDU to twice the usual * data packet size */ if (duration > MCS_DURATION(1, 0, 260) || (minstrel_ht_get_prob_avg(mi, mi->max_tp_rate[0]) < MINSTREL_FRAC(75, 100))) return 3200; /* * HT A-MPDU limits maximum MPDU size under BA agreement to 4095 bytes. * Since aggregation sessions are started/stopped without txq flush, use * the limit here to avoid the complexity of having to de-aggregate * packets in the queue. */ if (!mi->sta->deflink.vht_cap.vht_supported) return IEEE80211_MAX_MPDU_LEN_HT_BA; /* unlimited */ return 0; } static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct ieee80211_sta_rates *rates; int i = 0; int max_rates = min_t(int, mp->hw->max_rates, IEEE80211_TX_RATE_TABLE_SIZE); rates = kzalloc(sizeof(*rates), GFP_ATOMIC); if (!rates) return; /* Start with max_tp_rate[0] */ minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_tp_rate[0]); /* Fill up remaining, keep one entry for max_probe_rate */ for (; i < (max_rates - 1); i++) minstrel_ht_set_rate(mp, mi, rates, i, mi->max_tp_rate[i]); if (i < max_rates) minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_prob_rate); if (i < IEEE80211_TX_RATE_TABLE_SIZE) rates->rate[i].idx = -1; mi->sta->deflink.agg.max_rc_amsdu_len = minstrel_ht_get_max_amsdu_len(mi); ieee80211_sta_recalc_aggregates(mi->sta); rate_control_set_rates(mp->hw, mi->sta, rates); } static u16 minstrel_ht_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { u8 seq; if (mp->hw->max_rates > 1) { seq = mi->sample_seq; mi->sample_seq = (seq + 1) % ARRAY_SIZE(minstrel_sample_seq); seq = minstrel_sample_seq[seq]; } else { seq = MINSTREL_SAMPLE_TYPE_INC; } return __minstrel_ht_get_sample_rate(mi, seq); } static void minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, struct ieee80211_tx_rate_control *txrc) { const struct mcs_group *sample_group; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txrc->skb); struct ieee80211_tx_rate *rate = &info->status.rates[0]; struct minstrel_ht_sta *mi = priv_sta; struct minstrel_priv *mp = priv; u16 sample_idx; info->flags |= mi->tx_flags; #ifdef CONFIG_MAC80211_DEBUGFS if (mp->fixed_rate_idx != -1) return; #endif /* Don't use EAPOL frames for sampling on non-mrr hw */ if (mp->hw->max_rates == 1 && (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) return; if (time_is_after_jiffies(mi->sample_time)) return; mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL; sample_idx = minstrel_ht_get_sample_rate(mp, mi); if (!sample_idx) return; sample_group = &minstrel_mcs_groups[MI_RATE_GROUP(sample_idx)]; sample_idx = MI_RATE_IDX(sample_idx); if (sample_group == &minstrel_mcs_groups[MINSTREL_CCK_GROUP] && (sample_idx >= 4) != txrc->short_preamble) return; info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; rate->count = 1; if (sample_group == &minstrel_mcs_groups[MINSTREL_CCK_GROUP]) { int idx = sample_idx % ARRAY_SIZE(mp->cck_rates); rate->idx = mp->cck_rates[idx]; } else if (sample_group == &minstrel_mcs_groups[MINSTREL_OFDM_GROUP]) { int idx = sample_idx % ARRAY_SIZE(mp->ofdm_rates[0]); rate->idx = mp->ofdm_rates[mi->band][idx]; } else if (sample_group->flags & IEEE80211_TX_RC_VHT_MCS) { ieee80211_rate_set_vht(rate, MI_RATE_IDX(sample_idx), sample_group->streams); } else { rate->idx = sample_idx + (sample_group->streams - 1) * 8; } rate->flags = sample_group->flags; } static void minstrel_ht_update_cck(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) { int i; if (sband->band != NL80211_BAND_2GHZ) return; if (sta->deflink.ht_cap.ht_supported && !ieee80211_hw_check(mp->hw, SUPPORTS_HT_CCK_RATES)) return; for (i = 0; i < 4; i++) { if (mp->cck_rates[i] == 0xff || !rate_supported(sta, sband->band, mp->cck_rates[i])) continue; mi->supported[MINSTREL_CCK_GROUP] |= BIT(i); if (sband->bitrates[i].flags & IEEE80211_RATE_SHORT_PREAMBLE) mi->supported[MINSTREL_CCK_GROUP] |= BIT(i + 4); } } static void minstrel_ht_update_ofdm(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) { const u8 *rates; int i; if (sta->deflink.ht_cap.ht_supported) return; rates = mp->ofdm_rates[sband->band]; for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates[0]); i++) { if (rates[i] == 0xff || !rate_supported(sta, sband->band, rates[i])) continue; mi->supported[MINSTREL_OFDM_GROUP] |= BIT(i); } } static void minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta) { struct minstrel_priv *mp = priv; struct minstrel_ht_sta *mi = priv_sta; struct ieee80211_mcs_info *mcs = &sta->deflink.ht_cap.mcs; u16 ht_cap = sta->deflink.ht_cap.cap; struct ieee80211_sta_vht_cap *vht_cap = &sta->deflink.vht_cap; const struct ieee80211_rate *ctl_rate; struct sta_info *sta_info; bool ldpc, erp; int use_vht; int ack_dur; int stbc; int i; BUILD_BUG_ON(ARRAY_SIZE(minstrel_mcs_groups) != MINSTREL_GROUPS_NB); if (vht_cap->vht_supported) use_vht = vht_cap->vht_mcs.tx_mcs_map != cpu_to_le16(~0); else use_vht = 0; memset(mi, 0, sizeof(*mi)); mi->sta = sta; mi->band = sband->band; mi->last_stats_update = jiffies; ack_dur = ieee80211_frame_duration(sband->band, 10, 60, 1, 1); mi->overhead = ieee80211_frame_duration(sband->band, 0, 60, 1, 1); mi->overhead += ack_dur; mi->overhead_rtscts = mi->overhead + 2 * ack_dur; ctl_rate = &sband->bitrates[rate_lowest_index(sband, sta)]; erp = ctl_rate->flags & IEEE80211_RATE_ERP_G; ack_dur = ieee80211_frame_duration(sband->band, 10, ctl_rate->bitrate, erp, 1); mi->overhead_legacy = ack_dur; mi->overhead_legacy_rtscts = mi->overhead_legacy + 2 * ack_dur; mi->avg_ampdu_len = MINSTREL_FRAC(1, 1); if (!use_vht) { stbc = (ht_cap & IEEE80211_HT_CAP_RX_STBC) >> IEEE80211_HT_CAP_RX_STBC_SHIFT; ldpc = ht_cap & IEEE80211_HT_CAP_LDPC_CODING; } else { stbc = (vht_cap->cap & IEEE80211_VHT_CAP_RXSTBC_MASK) >> IEEE80211_VHT_CAP_RXSTBC_SHIFT; ldpc = vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC; } mi->tx_flags |= stbc << IEEE80211_TX_CTL_STBC_SHIFT; if (ldpc) mi->tx_flags |= IEEE80211_TX_CTL_LDPC; for (i = 0; i < ARRAY_SIZE(mi->groups); i++) { u32 gflags = minstrel_mcs_groups[i].flags; int bw, nss; mi->supported[i] = 0; if (minstrel_ht_is_legacy_group(i)) continue; if (gflags & IEEE80211_TX_RC_SHORT_GI) { if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) { if (!(ht_cap & IEEE80211_HT_CAP_SGI_40)) continue; } else { if (!(ht_cap & IEEE80211_HT_CAP_SGI_20)) continue; } } if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH && sta->deflink.bandwidth < IEEE80211_STA_RX_BW_40) continue; nss = minstrel_mcs_groups[i].streams; /* Mark MCS > 7 as unsupported if STA is in static SMPS mode */ if (sta->deflink.smps_mode == IEEE80211_SMPS_STATIC && nss > 1) continue; /* HT rate */ if (gflags & IEEE80211_TX_RC_MCS) { if (use_vht && minstrel_vht_only) continue; mi->supported[i] = mcs->rx_mask[nss - 1]; continue; } /* VHT rate */ if (!vht_cap->vht_supported || WARN_ON(!(gflags & IEEE80211_TX_RC_VHT_MCS)) || WARN_ON(gflags & IEEE80211_TX_RC_160_MHZ_WIDTH)) continue; if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH) { if (sta->deflink.bandwidth < IEEE80211_STA_RX_BW_80 || ((gflags & IEEE80211_TX_RC_SHORT_GI) && !(vht_cap->cap & IEEE80211_VHT_CAP_SHORT_GI_80))) { continue; } } if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) bw = BW_40; else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH) bw = BW_80; else bw = BW_20; mi->supported[i] = minstrel_get_valid_vht_rates(bw, nss, vht_cap->vht_mcs.tx_mcs_map); } sta_info = container_of(sta, struct sta_info, sta); mi->use_short_preamble = test_sta_flag(sta_info, WLAN_STA_SHORT_PREAMBLE) && sta_info->sdata->vif.bss_conf.use_short_preamble; minstrel_ht_update_cck(mp, mi, sband, sta); minstrel_ht_update_ofdm(mp, mi, sband, sta); /* create an initial rate table with the lowest supported rates */ minstrel_ht_update_stats(mp, mi); minstrel_ht_update_rates(mp, mi); } static void minstrel_ht_rate_init(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta) { minstrel_ht_update_caps(priv, sband, chandef, sta, priv_sta); } static void minstrel_ht_rate_update(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta, u32 changed) { minstrel_ht_update_caps(priv, sband, chandef, sta, priv_sta); } static void * minstrel_ht_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) { struct ieee80211_supported_band *sband; struct minstrel_ht_sta *mi; struct minstrel_priv *mp = priv; struct ieee80211_hw *hw = mp->hw; int max_rates = 0; int i; for (i = 0; i < NUM_NL80211_BANDS; i++) { sband = hw->wiphy->bands[i]; if (sband && sband->n_bitrates > max_rates) max_rates = sband->n_bitrates; } return kzalloc(sizeof(*mi), gfp); } static void minstrel_ht_free_sta(void *priv, struct ieee80211_sta *sta, void *priv_sta) { kfree(priv_sta); } static void minstrel_ht_fill_rate_array(u8 *dest, struct ieee80211_supported_band *sband, const s16 *bitrates, int n_rates, u32 rate_flags) { int i, j; for (i = 0; i < sband->n_bitrates; i++) { struct ieee80211_rate *rate = &sband->bitrates[i]; if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; for (j = 0; j < n_rates; j++) { if (rate->bitrate != bitrates[j]) continue; dest[j] = i; break; } } } static void minstrel_ht_init_cck_rates(struct minstrel_priv *mp) { static const s16 bitrates[4] = { 10, 20, 55, 110 }; struct ieee80211_supported_band *sband; u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); memset(mp->cck_rates, 0xff, sizeof(mp->cck_rates)); sband = mp->hw->wiphy->bands[NL80211_BAND_2GHZ]; if (!sband) return; BUILD_BUG_ON(ARRAY_SIZE(mp->cck_rates) != ARRAY_SIZE(bitrates)); minstrel_ht_fill_rate_array(mp->cck_rates, sband, minstrel_cck_bitrates, ARRAY_SIZE(minstrel_cck_bitrates), rate_flags); } static void minstrel_ht_init_ofdm_rates(struct minstrel_priv *mp, enum nl80211_band band) { static const s16 bitrates[8] = { 60, 90, 120, 180, 240, 360, 480, 540 }; struct ieee80211_supported_band *sband; u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); memset(mp->ofdm_rates[band], 0xff, sizeof(mp->ofdm_rates[band])); sband = mp->hw->wiphy->bands[band]; if (!sband) return; BUILD_BUG_ON(ARRAY_SIZE(mp->ofdm_rates[band]) != ARRAY_SIZE(bitrates)); minstrel_ht_fill_rate_array(mp->ofdm_rates[band], sband, minstrel_ofdm_bitrates, ARRAY_SIZE(minstrel_ofdm_bitrates), rate_flags); } static void * minstrel_ht_alloc(struct ieee80211_hw *hw) { struct minstrel_priv *mp; int i; mp = kzalloc(sizeof(struct minstrel_priv), GFP_ATOMIC); if (!mp) return NULL; /* contention window settings * Just an approximation. Using the per-queue values would complicate * the calculations and is probably unnecessary */ mp->cw_min = 15; mp->cw_max = 1023; /* maximum time that the hw is allowed to stay in one MRR segment */ mp->segment_size = 6000; if (hw->max_rate_tries > 0) mp->max_retry = hw->max_rate_tries; else /* safe default, does not necessarily have to match hw properties */ mp->max_retry = 7; mp->hw = hw; mp->update_interval = HZ / 20; minstrel_ht_init_cck_rates(mp); for (i = 0; i < ARRAY_SIZE(mp->hw->wiphy->bands); i++) minstrel_ht_init_ofdm_rates(mp, i); return mp; } #ifdef CONFIG_MAC80211_DEBUGFS static void minstrel_ht_add_debugfs(struct ieee80211_hw *hw, void *priv, struct dentry *debugfsdir) { struct minstrel_priv *mp = priv; mp->fixed_rate_idx = (u32) -1; debugfs_create_u32("fixed_rate_idx", S_IRUGO | S_IWUGO, debugfsdir, &mp->fixed_rate_idx); } #endif static void minstrel_ht_free(void *priv) { kfree(priv); } static u32 minstrel_ht_get_expected_throughput(void *priv_sta) { struct minstrel_ht_sta *mi = priv_sta; int i, j, prob, tp_avg; i = MI_RATE_GROUP(mi->max_tp_rate[0]); j = MI_RATE_IDX(mi->max_tp_rate[0]); prob = mi->groups[i].rates[j].prob_avg; /* convert tp_avg from pkt per second in kbps */ tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } static const struct rate_control_ops mac80211_minstrel_ht = { .name = "minstrel_ht", .capa = RATE_CTRL_CAPA_AMPDU_TRIGGER, .tx_status_ext = minstrel_ht_tx_status, .get_rate = minstrel_ht_get_rate, .rate_init = minstrel_ht_rate_init, .rate_update = minstrel_ht_rate_update, .alloc_sta = minstrel_ht_alloc_sta, .free_sta = minstrel_ht_free_sta, .alloc = minstrel_ht_alloc, .free = minstrel_ht_free, #ifdef CONFIG_MAC80211_DEBUGFS .add_debugfs = minstrel_ht_add_debugfs, .add_sta_debugfs = minstrel_ht_add_sta_debugfs, #endif .get_expected_throughput = minstrel_ht_get_expected_throughput, }; static void __init init_sample_table(void) { int col, i, new_idx; u8 rnd[MCS_GROUP_RATES]; memset(sample_table, 0xff, sizeof(sample_table)); for (col = 0; col < SAMPLE_COLUMNS; col++) { get_random_bytes(rnd, sizeof(rnd)); for (i = 0; i < MCS_GROUP_RATES; i++) { new_idx = (i + rnd[i]) % MCS_GROUP_RATES; while (sample_table[col][new_idx] != 0xff) new_idx = (new_idx + 1) % MCS_GROUP_RATES; sample_table[col][new_idx] = i; } } } int __init rc80211_minstrel_init(void) { init_sample_table(); return ieee80211_rate_control_register(&mac80211_minstrel_ht); } void rc80211_minstrel_exit(void) { ieee80211_rate_control_unregister(&mac80211_minstrel_ht); } |
| 140 135 140 139 137 137 67 137 137 136 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | // SPDX-License-Identifier: GPL-2.0 #include <linux/proc_fs.h> #include <linux/nsproxy.h> #include <linux/ptrace.h> #include <linux/namei.h> #include <linux/file.h> #include <linux/utsname.h> #include <net/net_namespace.h> #include <linux/ipc_namespace.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include "internal.h" static const struct proc_ns_operations *ns_entries[] = { #ifdef CONFIG_NET_NS &netns_operations, #endif #ifdef CONFIG_UTS_NS &utsns_operations, #endif #ifdef CONFIG_IPC_NS &ipcns_operations, #endif #ifdef CONFIG_PID_NS &pidns_operations, &pidns_for_children_operations, #endif #ifdef CONFIG_USER_NS &userns_operations, #endif &mntns_operations, #ifdef CONFIG_CGROUPS &cgroupns_operations, #endif #ifdef CONFIG_TIME_NS &timens_operations, &timens_for_children_operations, #endif }; static const char *proc_ns_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; struct path ns_path; int error = -EACCES; if (!dentry) return ERR_PTR(-ECHILD); task = get_proc_task(inode); if (!task) return ERR_PTR(-EACCES); if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out; error = ns_get_path(&ns_path, task, ns_ops); if (error) goto out; error = nd_jump_link(&ns_path); out: put_task_struct(task); return ERR_PTR(error); } static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; char name[50]; int res = -EACCES; task = get_proc_task(inode); if (!task) return res; if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) res = readlink_copy(buffer, buflen, name, strlen(name)); } put_task_struct(task); return res; } static const struct inode_operations proc_ns_link_inode_operations = { .readlink = proc_ns_readlink, .get_link = proc_ns_get_link, .setattr = proc_setattr, }; static struct dentry *proc_ns_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { const struct proc_ns_operations *ns_ops = ptr; struct inode *inode; struct proc_inode *ei; inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); inode->i_op = &proc_ns_link_inode_operations; ei->ns_ops = ns_ops; pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); return d_splice_alias(inode, dentry); } static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx) { struct task_struct *task = get_proc_task(file_inode(file)); const struct proc_ns_operations **entry, **last; if (!task) return -ENOENT; if (!dir_emit_dots(file, ctx)) goto out; if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries)) goto out; entry = ns_entries + (ctx->pos - 2); last = &ns_entries[ARRAY_SIZE(ns_entries) - 1]; while (entry <= last) { const struct proc_ns_operations *ops = *entry; if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name), proc_ns_instantiate, task, ops)) break; ctx->pos++; entry++; } out: put_task_struct(task); return 0; } const struct file_operations proc_ns_dir_operations = { .read = generic_read_dir, .iterate_shared = proc_ns_dir_readdir, .llseek = generic_file_llseek, }; static struct dentry *proc_ns_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct task_struct *task = get_proc_task(dir); const struct proc_ns_operations **entry, **last; unsigned int len = dentry->d_name.len; struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; last = &ns_entries[ARRAY_SIZE(ns_entries)]; for (entry = ns_entries; entry < last; entry++) { if (strlen((*entry)->name) != len) continue; if (!memcmp(dentry->d_name.name, (*entry)->name, len)) break; } if (entry == last) goto out; res = proc_ns_instantiate(dentry, task, *entry); out: put_task_struct(task); out_no_task: return res; } const struct inode_operations proc_ns_dir_inode_operations = { .lookup = proc_ns_dir_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; |
| 5026 1906 3362 33 33 33 33 11 33 243 245 244 245 244 245 56 73 765 3695 213 213 213 213 327 46 361 154 154 154 70 70 392 393 393 391 284 284 21 267 285 17 17 17 17 16 92 1 3890 3410 3423 3658 3653 570 3177 3670 3654 1160 4461 47 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <linux/pidfs.h> #include <linux/seqlock.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; static int pid_max_min = RESERVED_PIDS + 1; static int pid_max_max = PID_MAX_LIMIT; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .ns.count = REFCOUNT_INIT(2), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .ns.inum = PROC_PID_INIT_INO, #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif .pid_max = PID_MAX_DEFAULT, #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); seqcount_spinlock_t pidmap_lock_seq = SEQCNT_SPINLOCK_ZERO(pidmap_lock_seq, &pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { int i; lockdep_assert_not_held(&tasklist_lock); spin_lock(&pidmap_lock); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; break; } idr_remove(&ns->idr, upid->nr); } pidfs_remove_pid(pid); spin_unlock(&pidmap_lock); call_rcu(&pid->rcu, delayed_put_pid); } void free_pids(struct pid **pids) { int tmp; /* * This can batch pidmap_lock. */ for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pids[tmp]) free_pid(pids[tmp]); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; /* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int tid = 0; int pid_max = READ_ONCE(tmp->pid_max); if (set_tid_size) { tid = set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; } idr_preload(GFP_KERNEL); spin_lock(&pidmap_lock); if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); } spin_unlock(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. */ retval = -ENOMEM; get_pid_ns(ns); refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; idr_preload(GFP_KERNEL); spin_lock(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; pidfs_add_pid(pid); for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock(&pidmap_lock); idr_preload_end(); return pid; out_unlock: spin_unlock(&pidmap_lock); idr_preload_end(); put_pid_ns(ns); out_free: spin_lock(&pidmap_lock); while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; lockdep_assert_held_write(&tasklist_lock); pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct pid **pids, struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr, *pid; int tmp; lockdep_assert_held_write(&tasklist_lock); pid_ptr = task_pid_ptr(task, type); pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; if (type == PIDTYPE_PID) { WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID)); wake_up_all(&pid->wait_pidfd); } for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; WARN_ON(pids[type]); pids[type] = pid; } void detach_pid(struct pid **pids, struct task_struct *task, enum pid_type type) { __change_pid(pids, task, type, NULL); } void change_pid(struct pid **pids, struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(pids, task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; lockdep_assert_held_write(&tasklist_lock); /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { WARN_ON_ONCE(type == PIDTYPE_PID); lockdep_assert_held_write(&tasklist_lock); hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } EXPORT_SYMBOL_GPL(find_ge_pid); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { CLASS(fd, f)(fd); struct pid *pid; if (fd_empty(f)) return ERR_PTR(-EBADF); pid = pidfd_pid(fd_file(f)); if (!IS_ERR(pid)) { get_pid(pid); *flags = fd_file(f)->f_flags; } return pid; } /** * pidfd_get_task() - Get the task associated with a pidfd * * @pidfd: pidfd for which to get the task * @flags: flags associated with this pidfd * * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) { unsigned int f_flags = 0; struct pid *pid; struct task_struct *task; enum pid_type type; switch (pidfd) { case PIDFD_SELF_THREAD: type = PIDTYPE_PID; pid = get_task_pid(current, type); break; case PIDFD_SELF_THREAD_GROUP: type = PIDTYPE_TGID; pid = get_task_pid(current, type); break; default: pid = pidfd_get_pid(pidfd, &f_flags); if (IS_ERR(pid)) return ERR_CAST(pid); type = PIDTYPE_TGID; break; } task = get_pid_task(pid, type); put_pid(pid); if (!task) return ERR_PTR(-ESRCH); *flags = f_flags; return task; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ static int pidfd_create(struct pid *pid, unsigned int flags) { int pidfd; struct file *pidfd_file; pidfd = pidfd_prepare(pid, flags, &pidfd_file); if (pidfd < 0) return pidfd; fd_install(pidfd, pidfd_file); return pidfd; } /** * sys_pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the task identified by @pid. Without PIDFD_THREAD flag the target task * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } #ifdef CONFIG_SYSCTL static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root) { return &task_active_pid_ns(current)->set; } static int set_is_seen(struct ctl_table_set *set) { return &task_active_pid_ns(current)->set == set; } static int pid_table_root_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct pid_namespace *pidns = container_of(head->set, struct pid_namespace, set); int mode = table->mode; if (ns_capable(pidns->user_ns, CAP_SYS_ADMIN) || uid_eq(current_euid(), make_kuid(pidns->user_ns, 0))) mode = (mode & S_IRWXU) >> 6; else if (in_egroup_p(make_kgid(pidns->user_ns, 0))) mode = (mode & S_IRWXG) >> 3; else mode = mode & S_IROTH; return (mode << 6) | (mode << 3) | mode; } static void pid_table_root_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct pid_namespace *pidns = container_of(head->set, struct pid_namespace, set); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(pidns->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(pidns->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root pid_table_root = { .lookup = pid_table_root_lookup, .permissions = pid_table_root_permissions, .set_ownership = pid_table_root_set_ownership, }; static const struct ctl_table pid_table[] = { { .procname = "pid_max", .data = &init_pid_ns.pid_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &pid_max_min, .extra2 = &pid_max_max, }, }; #endif int register_pidns_sysctls(struct pid_namespace *pidns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen); tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL); if (!tbl) return -ENOMEM; tbl->data = &pidns->pid_max; pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl, ARRAY_SIZE(pid_table)); if (!pidns->sysctls) { kfree(tbl); retire_sysctl_set(&pidns->set); return -ENOMEM; } #endif return 0; } void unregister_pidns_sysctls(struct pid_namespace *pidns) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; tbl = pidns->sysctls->ctl_table_arg; unregister_sysctl_table(pidns->sysctls); retire_sysctl_set(&pidns->set); kfree(tbl); #endif } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = kmem_cache_create("pid", struct_size_t(struct pid, numbers, 1), __alignof__(struct pid), SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); } static __init int pid_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL /* "kernel" directory will have already been initialized. */ BUG_ON(register_pidns_sysctls(&init_pid_ns)); #endif return 0; } subsys_initcall(pid_namespace_sysctl_init); static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); if (!file) { /* * It is possible that the target thread is exiting; it can be * either: * 1. before exit_signals(), which gives a real fd * 2. before exit_files() takes the task_lock() gives a real fd * 3. after exit_files() releases task_lock(), ->files is NULL; * this has PF_EXITING, since it was set in exit_signals(), * __pidfd_fget() returns EBADF. * In case 3 we get EBADF, but that really means ESRCH, since * the task is currently exiting and has freed its files * struct, so we fix it up. */ if (task->flags & PF_EXITING) file = ERR_PTR(-ESRCH); else file = ERR_PTR(-EBADF); } return file; } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, NULL, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; CLASS(fd, f)(pidfd); if (fd_empty(f)) return -EBADF; pid = pidfd_pid(fd_file(f)); if (IS_ERR(pid)) return PTR_ERR(pid); return pidfd_getfd(pid, fd); } |
| 157 325 91 76 464 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ #include <linux/netlink.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> struct sk_buff; struct nlmsghdr; struct sock; struct sock_diag_handler { struct module *owner; __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh); }; int sock_diag_register(const struct sock_diag_handler *h); void sock_diag_unregister(const struct sock_diag_handler *h); struct sock_diag_inet_compat { struct module *owner; int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh); }; void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr); void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr); u64 __sock_gen_cookie(struct sock *sk); static inline u64 sock_gen_cookie(struct sock *sk) { u64 cookie; preempt_disable(); cookie = __sock_gen_cookie(sk); preempt_enable(); return cookie; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); static inline enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) { switch (sk->sk_family) { case AF_INET: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET_UDP_DESTROY; default: return SKNLGRP_NONE; } case AF_INET6: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET6_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET6_UDP_DESTROY; default: return SKNLGRP_NONE; } default: return SKNLGRP_NONE; } } static inline bool sock_diag_has_destroy_listeners(const struct sock *sk) { const struct net *n = sock_net(sk); const enum sknetlink_groups group = sock_diag_destroy_group(sk); return group != SKNLGRP_NONE && n->diag_nlsk && netlink_has_listeners(n->diag_nlsk, group); } void sock_diag_broadcast_destroy(struct sock *sk); int sock_diag_destroy(struct sock *sk, int err); #endif |
| 55 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 * x86-64 work by Andi Kleen 2002 */ #ifndef _ASM_X86_FPU_API_H #define _ASM_X86_FPU_API_H #include <linux/bottom_half.h> #include <asm/fpu/types.h> /* * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption and softirq processing, so be careful if you intend to * use it for long periods of time. Kernel-mode FPU cannot be used in all * contexts -- see irq_fpu_usable() for details. */ /* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ #define KFPU_387 _BITUL(0) /* 387 state will be initialized */ #define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); /* Code that is unaware of kernel_fpu_begin_mask() can use this */ static inline void kernel_fpu_begin(void) { #ifdef CONFIG_X86_64 /* * Any 64-bit code that uses 387 instructions must explicitly request * KFPU_387. */ kernel_fpu_begin_mask(KFPU_MXCSR); #else /* * 32-bit kernel code may use 387 operations as well as SSE2, etc, * as long as it checks that the CPU has the required capability. */ kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); #endif } /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate, or while * using the FPU in kernel mode. A context switch will (and softirq might) save * CPU's FPU registers to fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving * CPU's FPU registers in a random state. * * local_bh_disable() protects against both preemption and soft interrupts * on !RT kernels. * * On RT kernels local_bh_disable() is not sufficient because it only * serializes soft interrupt related sections via a local lock, but stays * preemptible. Disabling preemption is the right choice here as bottom * half processing is always in thread context on RT kernels so it * implicitly prevents bottom half processing as well. */ static inline void fpregs_lock(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_disable(); else preempt_disable(); } static inline void fpregs_unlock(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_enable(); else preempt_enable(); } /* * FPU state gets lazily restored before returning to userspace. So when in the * kernel, the valid FPU state may be kept in the buffer. This function will force * restore all the fpu state to the registers early if needed, and lock them from * being automatically saved/restored. Then FPU state can be modified safely in the * registers, before unlocking with fpregs_unlock(). */ void fpregs_lock_and_load(void); #ifdef CONFIG_X86_DEBUG_FPU extern void fpregs_assert_state_consistent(void); #else static inline void fpregs_assert_state_consistent(void) { } #endif /* * Load the task FPU state before returning to userspace. */ extern void switch_fpu_return(void); /* * Query the presence of one or more xfeatures. Works on any legacy CPU as well. * * If 'feature_name' is set then put a human-readable description of * the feature there as well - this can be used to print error (or success) * messages. */ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); /* Trap handling */ extern int fpu__exception_code(struct fpu *fpu, int trap_nr); extern void fpu_sync_fpstate(struct fpu *fpu); extern void fpu_reset_from_exception_fixup(void); /* Boot, hotplug and resume */ extern void fpu__init_cpu(void); extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); #ifdef CONFIG_MATH_EMULATION extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif /* State tracking */ DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* Process cleanup */ #ifdef CONFIG_X86_64 extern void fpstate_free(struct fpu *fpu); #else static inline void fpstate_free(struct fpu *fpu) { } #endif /* fpstate-related functions which are exported to KVM */ extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature); extern u64 xstate_get_guest_group_perm(void); extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); /* KVM specific functions */ extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest); extern int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures); #ifdef CONFIG_X86_64 extern void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd); extern void fpu_sync_guest_vmexit_xfd_state(void); #else static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { } static inline void fpu_sync_guest_vmexit_xfd_state(void) { } #endif extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u64 xfeatures, u32 pkru); extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); static inline void fpstate_set_confidential(struct fpu_guest *gfpu) { gfpu->fpstate->is_confidential = true; } static inline bool fpstate_is_confidential(struct fpu_guest *gfpu) { return gfpu->fpstate->is_confidential; } /* prctl */ extern long fpu_xstate_prctl(int option, unsigned long arg2); extern void fpu_idle_fpregs(void); #endif /* _ASM_X86_FPU_API_H */ |
| 8 436 435 436 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"}, \ {I_LINKABLE, "I_LINKABLE"}, \ {I_WB_SWITCH, "I_WB_SWITCH"}, \ {I_OVL_INUSE, "I_OVL_INUSE"}, \ {I_CREATING, "I_CREATING"}, \ {I_DONTCACHE, "I_DONTCACHE"}, \ {I_SYNC_QUEUED, "I_SYNC_QUEUED"}, \ {I_PINNING_NETFS_WB, "I_PINNING_NETFS_WB"}, \ {I_LRU_ISOLATING, "I_LRU_ISOLATING"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EM( WB_REASON_FORKER_THREAD, "forker_thread") \ EMe(WB_REASON_FOREIGN_FLUSH, "foreign_flush") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_folio_template, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, (unsigned long)__entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DEFINE_EVENT(writeback_folio_template, folio_wait_writeback, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return 1; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return 1; } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return 1; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, old_cgroup_ino) __field(ino_t, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->old_cgroup_ino, (unsigned long)__entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct folio *folio, struct bdi_writeback *wb), TP_ARGS(folio, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(ino_t, ino) __field(unsigned int, memcg_id) __field(ino_t, cgroup_ino) __field(ino_t, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = folio_mapping(folio); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", __entry->name, __entry->bdi_id, (unsigned long)__entry->ino, __entry->memcg_id, (unsigned long)__entry->cgroup_ino, (unsigned long)__entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u", __entry->name, (unsigned long)__entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(int, sync_mode) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, __entry->sync_mode, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", __entry->name, (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%lu", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, (unsigned long)__entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%lu", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, struct dirty_throttle_control *dtc, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, dtc, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, wb_setpoint) __field(unsigned long, wb_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(ino_t, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (dtc->thresh + dtc->bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = dtc->limit; __entry->setpoint = (dtc->limit + freerun) / 2; __entry->dirty = dtc->dirty; __entry->wb_setpoint = __entry->setpoint * dtc->wb_thresh / (dtc->thresh + 1); __entry->wb_dirty = dtc->wb_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "wb_setpoint=%lu wb_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->wb_setpoint, __entry->wb_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, (unsigned long)__entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_COUNTER_H #define _LINUX_PAGE_COUNTER_H #include <linux/atomic.h> #include <linux/cache.h> #include <linux/limits.h> #include <asm/page.h> struct page_counter { /* * Make sure 'usage' does not share cacheline with any other field in * v2. The memcg->memory.usage is a hot member of struct mem_cgroup. */ atomic_long_t usage; unsigned long failcnt; /* v1-only field */ CACHELINE_PADDING(_pad1_); /* effective memory.min and memory.min usage tracking */ unsigned long emin; atomic_long_t min_usage; atomic_long_t children_min_usage; /* effective memory.low and memory.low usage tracking */ unsigned long elow; atomic_long_t low_usage; atomic_long_t children_low_usage; unsigned long watermark; /* Latest cg2 reset watermark */ unsigned long local_watermark; /* Keep all the read most fields in a separete cacheline. */ CACHELINE_PADDING(_pad2_); bool protection_support; bool track_failcnt; unsigned long min; unsigned long low; unsigned long high; unsigned long max; struct page_counter *parent; } ____cacheline_internodealigned_in_smp; #if BITS_PER_LONG == 32 #define PAGE_COUNTER_MAX LONG_MAX #else #define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE) #endif /* * Protection is supported only for the first counter (with id 0). */ static inline void page_counter_init(struct page_counter *counter, struct page_counter *parent, bool protection_support) { counter->usage = (atomic_long_t)ATOMIC_LONG_INIT(0); counter->max = PAGE_COUNTER_MAX; counter->parent = parent; counter->protection_support = protection_support; counter->track_failcnt = false; } static inline unsigned long page_counter_read(struct page_counter *counter) { return atomic_long_read(&counter->usage); } void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); void page_counter_charge(struct page_counter *counter, unsigned long nr_pages); bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages); static inline void page_counter_set_high(struct page_counter *counter, unsigned long nr_pages) { WRITE_ONCE(counter->high, nr_pages); } int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); static inline void page_counter_reset_watermark(struct page_counter *counter) { unsigned long usage = page_counter_read(counter); /* * Update local_watermark first, so it's always <= watermark * (modulo CPU/compiler re-ordering) */ counter->local_watermark = usage; counter->watermark = usage; } #if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM) void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection); #else static inline void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection) {} #endif #endif /* _LINUX_PAGE_COUNTER_H */ |
| 11 11 1 9 1 1 2 1 4 4 4 3 1 11 11 11 11 2 1 1 46 2 32 13 8 2 11 8 18 24 2 18 18 25 2 10 9 18 5 8 7 47 47 24 25 13 11 11 11 11 11 15 1 1 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 | // SPDX-License-Identifier: GPL-2.0 /* * Management Component Transport Protocol (MCTP) * * Copyright (c) 2021 Code Construct * Copyright (c) 2021 Google */ #include <linux/compat.h> #include <linux/if_arp.h> #include <linux/net.h> #include <linux/mctp.h> #include <linux/module.h> #include <linux/socket.h> #include <net/mctp.h> #include <net/mctpdevice.h> #include <net/sock.h> #define CREATE_TRACE_POINTS #include <trace/events/mctp.h> /* socket implementation */ static void mctp_sk_expire_keys(struct timer_list *timer); static int mctp_release(struct socket *sock) { struct sock *sk = sock->sk; if (sk) { sock->sk = NULL; sk->sk_prot->close(sk, 0); } return 0; } /* Generic sockaddr checks, padding checks only so far */ static bool mctp_sockaddr_is_ok(const struct sockaddr_mctp *addr) { return !addr->__smctp_pad0 && !addr->__smctp_pad1; } static bool mctp_sockaddr_ext_is_ok(const struct sockaddr_mctp_ext *addr) { return !addr->__smctp_pad0[0] && !addr->__smctp_pad0[1] && !addr->__smctp_pad0[2]; } static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct sockaddr_mctp *smctp; int rc; if (addrlen < sizeof(*smctp)) return -EINVAL; if (addr->sa_family != AF_MCTP) return -EAFNOSUPPORT; if (!capable(CAP_NET_BIND_SERVICE)) return -EACCES; /* it's a valid sockaddr for MCTP, cast and do protocol checks */ smctp = (struct sockaddr_mctp *)addr; if (!mctp_sockaddr_is_ok(smctp)) return -EINVAL; lock_sock(sk); /* TODO: allow rebind */ if (sk_hashed(sk)) { rc = -EADDRINUSE; goto out_release; } msk->bind_net = smctp->smctp_network; msk->bind_addr = smctp->smctp_addr.s_addr; msk->bind_type = smctp->smctp_type & 0x7f; /* ignore the IC bit */ rc = sk->sk_prot->hash(sk); out_release: release_sock(sk); return rc; } static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; struct sk_buff *skb = NULL; int hlen; if (addr) { const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC; if (addrlen < sizeof(struct sockaddr_mctp)) return -EINVAL; if (addr->smctp_family != AF_MCTP) return -EINVAL; if (!mctp_sockaddr_is_ok(addr)) return -EINVAL; if (addr->smctp_tag & ~tagbits) return -EINVAL; /* can't preallocate a non-owned tag */ if (addr->smctp_tag & MCTP_TAG_PREALLOC && !(addr->smctp_tag & MCTP_TAG_OWNER)) return -EINVAL; } else { /* TODO: connect()ed sockets */ return -EDESTADDRREQ; } if (!capable(CAP_NET_RAW)) return -EACCES; if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); /* direct addressing */ if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, extaddr, msg->msg_name); struct net_device *dev; rc = -EINVAL; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex); /* check for correct halen */ if (dev && extaddr->smctp_halen == dev->addr_len) { hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr); rc = 0; } rcu_read_unlock(); if (rc) goto err_free; rt = NULL; } else { rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, addr->smctp_addr.s_addr); if (!rt) { rc = -EHOSTUNREACH; goto err_free; } hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr); } skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) return rc; skb_reserve(skb, hlen); /* set type as fist byte in payload */ *(u8 *)skb_put(skb, 1) = addr->smctp_type; rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len); if (rc < 0) goto err_free; /* set up cb */ cb = __mctp_cb(skb); cb->net = addr->smctp_network; if (!rt) { /* fill extended address in cb */ DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, extaddr, msg->msg_name); if (!mctp_sockaddr_ext_is_ok(extaddr) || extaddr->smctp_halen > sizeof(cb->haddr)) { rc = -EINVAL; goto err_free; } cb->ifindex = extaddr->smctp_ifindex; /* smctp_halen is checked above */ cb->halen = extaddr->smctp_halen; memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); } rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, addr->smctp_tag); return rc ? : len; err_free: kfree_skb(skb); return rc; } static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct sk_buff *skb; size_t msglen; u8 type; int rc; if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK)) return -EOPNOTSUPP; skb = skb_recv_datagram(sk, flags, &rc); if (!skb) return rc; if (!skb->len) { rc = 0; goto out_free; } /* extract message type, remove from data */ type = *((u8 *)skb->data); msglen = skb->len - 1; if (len < msglen) msg->msg_flags |= MSG_TRUNC; else len = msglen; rc = skb_copy_datagram_msg(skb, 1, msg, len); if (rc < 0) goto out_free; sock_recv_cmsgs(msg, sk, skb); if (addr) { struct mctp_skb_cb *cb = mctp_cb(skb); /* TODO: expand mctp_skb_cb for header fields? */ struct mctp_hdr *hdr = mctp_hdr(skb); addr = msg->msg_name; addr->smctp_family = AF_MCTP; addr->__smctp_pad0 = 0; addr->smctp_network = cb->net; addr->smctp_addr.s_addr = hdr->src; addr->smctp_type = type; addr->smctp_tag = hdr->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); addr->__smctp_pad1 = 0; msg->msg_namelen = sizeof(*addr); if (msk->addr_ext) { DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, ae, msg->msg_name); msg->msg_namelen = sizeof(*ae); ae->smctp_ifindex = cb->ifindex; ae->smctp_halen = cb->halen; memset(ae->__smctp_pad0, 0x0, sizeof(ae->__smctp_pad0)); memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr)); memcpy(ae->smctp_haddr, cb->haddr, cb->halen); } } rc = len; if (flags & MSG_TRUNC) rc = msglen; out_free: skb_free_datagram(sk, skb); return rc; } /* We're done with the key; invalidate, stop reassembly, and remove from lists. */ static void __mctp_key_remove(struct mctp_sk_key *key, struct net *net, unsigned long flags, unsigned long reason) __releases(&key->lock) __must_hold(&net->mctp.keys_lock) { struct sk_buff *skb; trace_mctp_key_release(key, reason); skb = key->reasm_head; key->reasm_head = NULL; key->reasm_dead = true; key->valid = false; mctp_dev_release_key(key->dev, key); spin_unlock_irqrestore(&key->lock, flags); if (!hlist_unhashed(&key->hlist)) { hlist_del_init(&key->hlist); hlist_del_init(&key->sklist); /* unref for the lists */ mctp_key_unref(key); } kfree_skb(skb); } static int mctp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); int val; if (level != SOL_MCTP) return -EINVAL; if (optname == MCTP_OPT_ADDR_EXT) { if (optlen != sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; msk->addr_ext = val; return 0; } return -ENOPROTOOPT; } static int mctp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); int len, val; if (level != SOL_MCTP) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (optname == MCTP_OPT_ADDR_EXT) { if (len != sizeof(int)) return -EINVAL; val = !!msk->addr_ext; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } return -EINVAL; } /* helpers for reading/writing the tag ioc, handling compatibility across the * two versions, and some basic API error checking */ static int mctp_ioctl_tag_copy_from_user(unsigned long arg, struct mctp_ioc_tag_ctl2 *ctl, bool tagv2) { struct mctp_ioc_tag_ctl ctl_compat; unsigned long size; void *ptr; int rc; if (tagv2) { size = sizeof(*ctl); ptr = ctl; } else { size = sizeof(ctl_compat); ptr = &ctl_compat; } rc = copy_from_user(ptr, (void __user *)arg, size); if (rc) return -EFAULT; if (!tagv2) { /* compat, using defaults for new fields */ ctl->net = MCTP_INITIAL_DEFAULT_NET; ctl->peer_addr = ctl_compat.peer_addr; ctl->local_addr = MCTP_ADDR_ANY; ctl->flags = ctl_compat.flags; ctl->tag = ctl_compat.tag; } if (ctl->flags) return -EINVAL; if (ctl->local_addr != MCTP_ADDR_ANY && ctl->local_addr != MCTP_ADDR_NULL) return -EINVAL; return 0; } static int mctp_ioctl_tag_copy_to_user(unsigned long arg, struct mctp_ioc_tag_ctl2 *ctl, bool tagv2) { struct mctp_ioc_tag_ctl ctl_compat; unsigned long size; void *ptr; int rc; if (tagv2) { ptr = ctl; size = sizeof(*ctl); } else { ctl_compat.peer_addr = ctl->peer_addr; ctl_compat.tag = ctl->tag; ctl_compat.flags = ctl->flags; ptr = &ctl_compat; size = sizeof(ctl_compat); } rc = copy_to_user((void __user *)arg, ptr, size); if (rc) return -EFAULT; return 0; } static int mctp_ioctl_alloctag(struct mctp_sock *msk, bool tagv2, unsigned long arg) { struct net *net = sock_net(&msk->sk); struct mctp_sk_key *key = NULL; struct mctp_ioc_tag_ctl2 ctl; unsigned long flags; u8 tag; int rc; rc = mctp_ioctl_tag_copy_from_user(arg, &ctl, tagv2); if (rc) return rc; if (ctl.tag) return -EINVAL; key = mctp_alloc_local_tag(msk, ctl.net, MCTP_ADDR_ANY, ctl.peer_addr, true, &tag); if (IS_ERR(key)) return PTR_ERR(key); ctl.tag = tag | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC; rc = mctp_ioctl_tag_copy_to_user(arg, &ctl, tagv2); if (rc) { unsigned long fl2; /* Unwind our key allocation: the keys list lock needs to be * taken before the individual key locks, and we need a valid * flags value (fl2) to pass to __mctp_key_remove, hence the * second spin_lock_irqsave() rather than a plain spin_lock(). */ spin_lock_irqsave(&net->mctp.keys_lock, flags); spin_lock_irqsave(&key->lock, fl2); __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_DROPPED); mctp_key_unref(key); spin_unlock_irqrestore(&net->mctp.keys_lock, flags); return rc; } mctp_key_unref(key); return 0; } static int mctp_ioctl_droptag(struct mctp_sock *msk, bool tagv2, unsigned long arg) { struct net *net = sock_net(&msk->sk); struct mctp_ioc_tag_ctl2 ctl; unsigned long flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; int rc; u8 tag; rc = mctp_ioctl_tag_copy_from_user(arg, &ctl, tagv2); if (rc) return rc; /* Must be a local tag, TO set, preallocated */ if ((ctl.tag & ~MCTP_TAG_MASK) != (MCTP_TAG_OWNER | MCTP_TAG_PREALLOC)) return -EINVAL; tag = ctl.tag & MCTP_TAG_MASK; rc = -EINVAL; if (ctl.peer_addr == MCTP_ADDR_NULL) ctl.peer_addr = MCTP_ADDR_ANY; spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { /* we do an irqsave here, even though we know the irq state, * so we have the flags to pass to __mctp_key_remove */ spin_lock_irqsave(&key->lock, fl2); if (key->manual_alloc && ctl.net == key->net && ctl.peer_addr == key->peer_addr && tag == key->tag) { __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_DROPPED); rc = 0; } else { spin_unlock_irqrestore(&key->lock, fl2); } } spin_unlock_irqrestore(&net->mctp.keys_lock, flags); return rc; } static int mctp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); bool tagv2 = false; switch (cmd) { case SIOCMCTPALLOCTAG2: case SIOCMCTPALLOCTAG: tagv2 = cmd == SIOCMCTPALLOCTAG2; return mctp_ioctl_alloctag(msk, tagv2, arg); case SIOCMCTPDROPTAG: case SIOCMCTPDROPTAG2: tagv2 = cmd == SIOCMCTPDROPTAG2; return mctp_ioctl_droptag(msk, tagv2, arg); } return -EINVAL; } #ifdef CONFIG_COMPAT static int mctp_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); switch (cmd) { /* These have compatible ptr layouts */ case SIOCMCTPALLOCTAG: case SIOCMCTPDROPTAG: return mctp_ioctl(sock, cmd, (unsigned long)argp); } return -ENOIOCTLCMD; } #endif static const struct proto_ops mctp_dgram_ops = { .family = PF_MCTP, .release = mctp_release, .bind = mctp_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = mctp_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = mctp_setsockopt, .getsockopt = mctp_getsockopt, .sendmsg = mctp_sendmsg, .recvmsg = mctp_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = mctp_compat_ioctl, #endif }; static void mctp_sk_expire_keys(struct timer_list *timer) { struct mctp_sock *msk = container_of(timer, struct mctp_sock, key_expiry); struct net *net = sock_net(&msk->sk); unsigned long next_expiry, flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; bool next_expiry_valid = false; spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { /* don't expire. manual_alloc is immutable, no locking * required. */ if (key->manual_alloc) continue; spin_lock_irqsave(&key->lock, fl2); if (!time_after_eq(key->expiry, jiffies)) { __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_TIMEOUT); continue; } if (next_expiry_valid) { if (time_before(key->expiry, next_expiry)) next_expiry = key->expiry; } else { next_expiry = key->expiry; next_expiry_valid = true; } spin_unlock_irqrestore(&key->lock, fl2); } spin_unlock_irqrestore(&net->mctp.keys_lock, flags); if (next_expiry_valid) mod_timer(timer, next_expiry); } static int mctp_sk_init(struct sock *sk) { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); INIT_HLIST_HEAD(&msk->keys); timer_setup(&msk->key_expiry, mctp_sk_expire_keys, 0); return 0; } static void mctp_sk_close(struct sock *sk, long timeout) { sk_common_release(sk); } static int mctp_sk_hash(struct sock *sk) { struct net *net = sock_net(sk); /* Bind lookup runs under RCU, remain live during that. */ sock_set_flag(sk, SOCK_RCU_FREE); mutex_lock(&net->mctp.bind_lock); sk_add_node_rcu(sk, &net->mctp.binds); mutex_unlock(&net->mctp.bind_lock); return 0; } static void mctp_sk_unhash(struct sock *sk) { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct net *net = sock_net(sk); unsigned long flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; /* remove from any type-based binds */ mutex_lock(&net->mctp.bind_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->mctp.bind_lock); /* remove tag allocations */ spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { spin_lock_irqsave(&key->lock, fl2); __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED); } sock_set_flag(sk, SOCK_DEAD); spin_unlock_irqrestore(&net->mctp.keys_lock, flags); /* Since there are no more tag allocations (we have removed all of the * keys), stop any pending expiry events. the timer cannot be re-queued * as the sk is no longer observable */ timer_delete_sync(&msk->key_expiry); } static void mctp_sk_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); } static struct proto mctp_proto = { .name = "MCTP", .owner = THIS_MODULE, .obj_size = sizeof(struct mctp_sock), .init = mctp_sk_init, .close = mctp_sk_close, .hash = mctp_sk_hash, .unhash = mctp_sk_unhash, }; static int mctp_pf_create(struct net *net, struct socket *sock, int protocol, int kern) { const struct proto_ops *ops; struct proto *proto; struct sock *sk; int rc; if (protocol) return -EPROTONOSUPPORT; /* only datagram sockets are supported */ if (sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; proto = &mctp_proto; ops = &mctp_dgram_ops; sock->state = SS_UNCONNECTED; sock->ops = ops; sk = sk_alloc(net, PF_MCTP, GFP_KERNEL, proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); sk->sk_destruct = mctp_sk_destruct; rc = 0; if (sk->sk_prot->init) rc = sk->sk_prot->init(sk); if (rc) goto err_sk_put; return 0; err_sk_put: sock_orphan(sk); sock_put(sk); return rc; } static struct net_proto_family mctp_pf = { .family = PF_MCTP, .create = mctp_pf_create, .owner = THIS_MODULE, }; static __init int mctp_init(void) { int rc; /* ensure our uapi tag definitions match the header format */ BUILD_BUG_ON(MCTP_TAG_OWNER != MCTP_HDR_FLAG_TO); BUILD_BUG_ON(MCTP_TAG_MASK != MCTP_HDR_TAG_MASK); pr_info("mctp: management component transport protocol core\n"); rc = sock_register(&mctp_pf); if (rc) return rc; rc = proto_register(&mctp_proto, 0); if (rc) goto err_unreg_sock; rc = mctp_routes_init(); if (rc) goto err_unreg_proto; rc = mctp_neigh_init(); if (rc) goto err_unreg_routes; rc = mctp_device_init(); if (rc) goto err_unreg_neigh; return 0; err_unreg_neigh: mctp_neigh_exit(); err_unreg_routes: mctp_routes_exit(); err_unreg_proto: proto_unregister(&mctp_proto); err_unreg_sock: sock_unregister(PF_MCTP); return rc; } static __exit void mctp_exit(void) { mctp_device_exit(); mctp_neigh_exit(); mctp_routes_exit(); proto_unregister(&mctp_proto); sock_unregister(PF_MCTP); } subsys_initcall(mctp_init); module_exit(mctp_exit); MODULE_DESCRIPTION("MCTP core"); MODULE_AUTHOR("Jeremy Kerr <jk@codeconstruct.com.au>"); MODULE_ALIAS_NETPROTO(PF_MCTP); |
| 518 418 418 139 140 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Software nodes for the firmware node framework. * * Copyright (C) 2018, Intel Corporation * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com> */ #include <linux/container_of.h> #include <linux/device.h> #include <linux/err.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kobject.h> #include <linux/kstrtox.h> #include <linux/list.h> #include <linux/property.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/sysfs.h> #include <linux/types.h> #include "base.h" struct swnode { struct kobject kobj; struct fwnode_handle fwnode; const struct software_node *node; int id; /* hierarchy */ struct ida child_ids; struct list_head entry; struct list_head children; struct swnode *parent; unsigned int allocated:1; unsigned int managed:1; }; static DEFINE_IDA(swnode_root_ids); static struct kset *swnode_kset; #define kobj_to_swnode(_kobj_) container_of(_kobj_, struct swnode, kobj) static const struct fwnode_operations software_node_ops; bool is_software_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &software_node_ops; } EXPORT_SYMBOL_GPL(is_software_node); #define to_swnode(__fwnode) \ ({ \ typeof(__fwnode) __to_swnode_fwnode = __fwnode; \ \ is_software_node(__to_swnode_fwnode) ? \ container_of(__to_swnode_fwnode, \ struct swnode, fwnode) : NULL; \ }) static inline struct swnode *dev_to_swnode(struct device *dev) { struct fwnode_handle *fwnode = dev_fwnode(dev); if (!fwnode) return NULL; if (!is_software_node(fwnode)) fwnode = fwnode->secondary; return to_swnode(fwnode); } static struct swnode * software_node_to_swnode(const struct software_node *node) { struct swnode *swnode = NULL; struct kobject *k; if (!node) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (swnode->node == node) break; swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode; } const struct software_node *to_software_node(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(to_software_node); struct fwnode_handle *software_node_fwnode(const struct software_node *node) { struct swnode *swnode = software_node_to_swnode(node); return swnode ? &swnode->fwnode : NULL; } EXPORT_SYMBOL_GPL(software_node_fwnode); /* -------------------------------------------------------------------------- */ /* property_entry processing */ static const struct property_entry * property_entry_get(const struct property_entry *prop, const char *name) { if (!prop) return NULL; for (; prop->name; prop++) if (!strcmp(name, prop->name)) return prop; return NULL; } static const void *property_get_pointer(const struct property_entry *prop) { if (!prop->length) return NULL; return prop->is_inline ? &prop->value : prop->pointer; } static const void *property_entry_find(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; const void *pointer; prop = property_entry_get(props, propname); if (!prop) return ERR_PTR(-EINVAL); pointer = property_get_pointer(prop); if (!pointer) return ERR_PTR(-ENODATA); if (length > prop->length) return ERR_PTR(-EOVERFLOW); return pointer; } static int property_entry_count_elems_of_size(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; prop = property_entry_get(props, propname); if (!prop) return -EINVAL; return prop->length / length; } static int property_entry_read_int_array(const struct property_entry *props, const char *name, unsigned int elem_size, void *val, size_t nval) { const void *pointer; size_t length; if (!val) return property_entry_count_elems_of_size(props, name, elem_size); if (!is_power_of_2(elem_size) || elem_size > sizeof(u64)) return -ENXIO; length = nval * elem_size; pointer = property_entry_find(props, name, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(val, pointer, length); return 0; } static int property_entry_read_string_array(const struct property_entry *props, const char *propname, const char **strings, size_t nval) { const void *pointer; size_t length; int array_len; /* Find out the array length. */ array_len = property_entry_count_elems_of_size(props, propname, sizeof(const char *)); if (array_len < 0) return array_len; /* Return how many there are if strings is NULL. */ if (!strings) return array_len; array_len = min_t(size_t, nval, array_len); length = array_len * sizeof(*strings); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(strings, pointer, length); return array_len; } static void property_entry_free_data(const struct property_entry *p) { const char * const *src_str; size_t i, nval; if (p->type == DEV_PROP_STRING) { src_str = property_get_pointer(p); nval = p->length / sizeof(*src_str); for (i = 0; i < nval; i++) kfree(src_str[i]); } if (!p->is_inline) kfree(p->pointer); kfree(p->name); } static bool property_copy_string_array(const char **dst_ptr, const char * const *src_ptr, size_t nval) { int i; for (i = 0; i < nval; i++) { dst_ptr[i] = kstrdup(src_ptr[i], GFP_KERNEL); if (!dst_ptr[i] && src_ptr[i]) { while (--i >= 0) kfree(dst_ptr[i]); return false; } } return true; } static int property_entry_copy_data(struct property_entry *dst, const struct property_entry *src) { const void *pointer = property_get_pointer(src); void *dst_ptr; size_t nval; /* * Properties with no data should not be marked as stored * out of line. */ if (!src->is_inline && !src->length) return -ENODATA; /* * Reference properties are never stored inline as * they are too big. */ if (src->type == DEV_PROP_REF && src->is_inline) return -EINVAL; if (src->length <= sizeof(dst->value)) { dst_ptr = &dst->value; dst->is_inline = true; } else { dst_ptr = kmalloc(src->length, GFP_KERNEL); if (!dst_ptr) return -ENOMEM; dst->pointer = dst_ptr; } if (src->type == DEV_PROP_STRING) { nval = src->length / sizeof(const char *); if (!property_copy_string_array(dst_ptr, pointer, nval)) { if (!dst->is_inline) kfree(dst->pointer); return -ENOMEM; } } else { memcpy(dst_ptr, pointer, src->length); } dst->length = src->length; dst->type = src->type; dst->name = kstrdup(src->name, GFP_KERNEL); if (!dst->name) { property_entry_free_data(dst); return -ENOMEM; } return 0; } /** * property_entries_dup - duplicate array of properties * @properties: array of properties to copy * * This function creates a deep copy of the given NULL-terminated array * of property entries. */ struct property_entry * property_entries_dup(const struct property_entry *properties) { struct property_entry *p; int i, n = 0; int ret; if (!properties) return NULL; while (properties[n].name) n++; p = kcalloc(n + 1, sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); for (i = 0; i < n; i++) { ret = property_entry_copy_data(&p[i], &properties[i]); if (ret) { while (--i >= 0) property_entry_free_data(&p[i]); kfree(p); return ERR_PTR(ret); } } return p; } EXPORT_SYMBOL_GPL(property_entries_dup); /** * property_entries_free - free previously allocated array of properties * @properties: array of properties to destroy * * This function frees given NULL-terminated array of property entries, * along with their data. */ void property_entries_free(const struct property_entry *properties) { const struct property_entry *p; if (!properties) return; for (p = properties; p->name; p++) property_entry_free_data(p); kfree(properties); } EXPORT_SYMBOL_GPL(property_entries_free); /* -------------------------------------------------------------------------- */ /* fwnode operations */ static struct fwnode_handle *software_node_get(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_get(&swnode->kobj); return &swnode->fwnode; } static void software_node_put(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_put(&swnode->kobj); } static bool software_node_property_present(const struct fwnode_handle *fwnode, const char *propname) { struct swnode *swnode = to_swnode(fwnode); return !!property_entry_get(swnode->node->properties, propname); } static int software_node_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_int_array(swnode->node->properties, propname, elem_size, val, nval); } static int software_node_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_string_array(swnode->node->properties, propname, val, nval); } static const char * software_node_get_name(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); return kobject_name(&swnode->kobj); } static const char * software_node_get_name_prefix(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; const char *prefix; parent = fwnode_get_parent(fwnode); if (!parent) return ""; /* Figure out the prefix from the parents. */ while (is_software_node(parent)) parent = fwnode_get_next_parent(parent); prefix = fwnode_get_name_prefix(parent); fwnode_handle_put(parent); /* Guess something if prefix was NULL. */ return prefix ?: "/"; } static struct fwnode_handle * software_node_get_parent(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode || !swnode->parent) return NULL; return fwnode_handle_get(&swnode->parent->fwnode); } static struct fwnode_handle * software_node_get_next_child(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct swnode *p = to_swnode(fwnode); struct swnode *c = to_swnode(child); if (!p || list_empty(&p->children) || (c && list_is_last(&c->entry, &p->children))) { fwnode_handle_put(child); return NULL; } if (c) c = list_next_entry(c, entry); else c = list_first_entry(&p->children, struct swnode, entry); fwnode_handle_put(child); return fwnode_handle_get(&c->fwnode); } static struct fwnode_handle * software_node_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct swnode *swnode = to_swnode(fwnode); struct swnode *child; if (!swnode || list_empty(&swnode->children)) return NULL; list_for_each_entry(child, &swnode->children, entry) { if (!strcmp(childname, kobject_name(&child->kobj))) { kobject_get(&child->kobj); return &child->fwnode; } } return NULL; } static int software_node_get_reference_args(const struct fwnode_handle *fwnode, const char *propname, const char *nargs_prop, unsigned int nargs, unsigned int index, struct fwnode_reference_args *args) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_ref_args *ref_array; const struct software_node_ref_args *ref; const struct property_entry *prop; struct fwnode_handle *refnode; u32 nargs_prop_val; int error; int i; prop = property_entry_get(swnode->node->properties, propname); if (!prop) return -ENOENT; if (prop->type != DEV_PROP_REF) return -EINVAL; /* * We expect that references are never stored inline, even * single ones, as they are too big. */ if (prop->is_inline) return -EINVAL; if (index * sizeof(*ref) >= prop->length) return -ENOENT; ref_array = prop->pointer; ref = &ref_array[index]; refnode = software_node_fwnode(ref->node); if (!refnode) return -ENOENT; if (nargs_prop) { error = property_entry_read_int_array(ref->node->properties, nargs_prop, sizeof(u32), &nargs_prop_val, 1); if (error) return error; nargs = nargs_prop_val; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (!args) return 0; args->fwnode = software_node_get(refnode); args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = ref->args[i]; return 0; } static struct fwnode_handle * swnode_graph_find_next_port(const struct fwnode_handle *parent, struct fwnode_handle *port) { struct fwnode_handle *old = port; while ((port = software_node_get_next_child(parent, old))) { /* * fwnode ports have naming style "port@", so we search for any * children that follow that convention. */ if (!strncmp(to_swnode(port)->node->name, "port@", strlen("port@"))) return port; old = port; } return NULL; } static struct fwnode_handle * software_node_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *endpoint) { struct swnode *swnode = to_swnode(fwnode); struct fwnode_handle *parent; struct fwnode_handle *port; if (!swnode) return NULL; if (endpoint) { port = software_node_get_parent(endpoint); parent = software_node_get_parent(port); } else { parent = software_node_get_named_child_node(fwnode, "ports"); if (!parent) parent = software_node_get(&swnode->fwnode); port = swnode_graph_find_next_port(parent, NULL); } for (; port; port = swnode_graph_find_next_port(parent, port)) { endpoint = software_node_get_next_child(port, endpoint); if (endpoint) { fwnode_handle_put(port); break; } } fwnode_handle_put(parent); return endpoint; } static struct fwnode_handle * software_node_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_ref_args *ref; const struct property_entry *prop; if (!swnode) return NULL; prop = property_entry_get(swnode->node->properties, "remote-endpoint"); if (!prop || prop->type != DEV_PROP_REF || prop->is_inline) return NULL; ref = prop->pointer; return software_node_get(software_node_fwnode(ref[0].node)); } static struct fwnode_handle * software_node_graph_get_port_parent(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); swnode = swnode->parent; if (swnode && !strcmp(swnode->node->name, "ports")) swnode = swnode->parent; return swnode ? software_node_get(&swnode->fwnode) : NULL; } static int software_node_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { struct swnode *swnode = to_swnode(fwnode); const char *parent_name = swnode->parent->node->name; int ret; if (strlen("port@") >= strlen(parent_name) || strncmp(parent_name, "port@", strlen("port@"))) return -EINVAL; /* Ports have naming style "port@n", we need to select the n */ ret = kstrtou32(parent_name + strlen("port@"), 10, &endpoint->port); if (ret) return ret; endpoint->id = swnode->id; endpoint->local_fwnode = fwnode; return 0; } static const struct fwnode_operations software_node_ops = { .get = software_node_get, .put = software_node_put, .property_present = software_node_property_present, .property_read_bool = software_node_property_present, .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, .get_name = software_node_get_name, .get_name_prefix = software_node_get_name_prefix, .get_parent = software_node_get_parent, .get_next_child_node = software_node_get_next_child, .get_named_child_node = software_node_get_named_child_node, .get_reference_args = software_node_get_reference_args, .graph_get_next_endpoint = software_node_graph_get_next_endpoint, .graph_get_remote_endpoint = software_node_graph_get_remote_endpoint, .graph_get_port_parent = software_node_graph_get_port_parent, .graph_parse_endpoint = software_node_graph_parse_endpoint, }; /* -------------------------------------------------------------------------- */ /** * software_node_find_by_name - Find software node by name * @parent: Parent of the software node * @name: Name of the software node * * The function will find a node that is child of @parent and that is named * @name. If no node is found, the function returns NULL. * * NOTE: you will need to drop the reference with fwnode_handle_put() after use. */ const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name) { struct swnode *swnode = NULL; struct kobject *k; if (!name) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (parent == swnode->node->parent && swnode->node->name && !strcmp(name, swnode->node->name)) { kobject_get(&swnode->kobj); break; } swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(software_node_find_by_name); static struct software_node *software_node_alloc(const struct property_entry *properties) { struct property_entry *props; struct software_node *node; props = property_entries_dup(properties); if (IS_ERR(props)) return ERR_CAST(props); node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) { property_entries_free(props); return ERR_PTR(-ENOMEM); } node->properties = props; return node; } static void software_node_free(const struct software_node *node) { property_entries_free(node->properties); kfree(node); } static void software_node_release(struct kobject *kobj) { struct swnode *swnode = kobj_to_swnode(kobj); if (swnode->parent) { ida_free(&swnode->parent->child_ids, swnode->id); list_del(&swnode->entry); } else { ida_free(&swnode_root_ids, swnode->id); } if (swnode->allocated) software_node_free(swnode->node); ida_destroy(&swnode->child_ids); kfree(swnode); } static const struct kobj_type software_node_type = { .release = software_node_release, .sysfs_ops = &kobj_sysfs_ops, }; static struct fwnode_handle * swnode_register(const struct software_node *node, struct swnode *parent, unsigned int allocated) { struct swnode *swnode; int ret; swnode = kzalloc(sizeof(*swnode), GFP_KERNEL); if (!swnode) return ERR_PTR(-ENOMEM); ret = ida_alloc(parent ? &parent->child_ids : &swnode_root_ids, GFP_KERNEL); if (ret < 0) { kfree(swnode); return ERR_PTR(ret); } swnode->id = ret; swnode->node = node; swnode->parent = parent; swnode->kobj.kset = swnode_kset; fwnode_init(&swnode->fwnode, &software_node_ops); ida_init(&swnode->child_ids); INIT_LIST_HEAD(&swnode->entry); INIT_LIST_HEAD(&swnode->children); if (node->name) ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "%s", node->name); else ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "node%d", swnode->id); if (ret) { kobject_put(&swnode->kobj); return ERR_PTR(ret); } /* * Assign the flag only in the successful case, so * the above kobject_put() won't mess up with properties. */ swnode->allocated = allocated; if (parent) list_add_tail(&swnode->entry, &parent->children); kobject_uevent(&swnode->kobj, KOBJ_ADD); return &swnode->fwnode; } /** * software_node_register_node_group - Register a group of software nodes * @node_group: NULL terminated array of software node pointers to be registered * * Register multiple software nodes at once. If any node in the array * has its .parent pointer set (which can only be to another software_node), * then its parent **must** have been registered before it is; either outside * of this function or by ordering the array such that parent comes before * child. */ int software_node_register_node_group(const struct software_node **node_group) { unsigned int i; int ret; if (!node_group) return 0; for (i = 0; node_group[i]; i++) { ret = software_node_register(node_group[i]); if (ret) { software_node_unregister_node_group(node_group); return ret; } } return 0; } EXPORT_SYMBOL_GPL(software_node_register_node_group); /** * software_node_unregister_node_group - Unregister a group of software nodes * @node_group: NULL terminated array of software node pointers to be unregistered * * Unregister multiple software nodes at once. If parent pointers are set up * in any of the software nodes then the array **must** be ordered such that * parents come before their children. * * NOTE: If you are uncertain whether the array is ordered such that * parents will be unregistered before their children, it is wiser to * remove the nodes individually, in the correct order (child before * parent). */ void software_node_unregister_node_group( const struct software_node **node_group) { unsigned int i = 0; if (!node_group) return; while (node_group[i]) i++; while (i--) software_node_unregister(node_group[i]); } EXPORT_SYMBOL_GPL(software_node_unregister_node_group); /** * software_node_register - Register static software node * @node: The software node to be registered */ int software_node_register(const struct software_node *node) { struct swnode *parent = software_node_to_swnode(node->parent); if (software_node_to_swnode(node)) return -EEXIST; if (node->parent && !parent) return -EINVAL; return PTR_ERR_OR_ZERO(swnode_register(node, parent, 0)); } EXPORT_SYMBOL_GPL(software_node_register); /** * software_node_unregister - Unregister static software node * @node: The software node to be unregistered */ void software_node_unregister(const struct software_node *node) { struct swnode *swnode; swnode = software_node_to_swnode(node); if (swnode) fwnode_remove_software_node(&swnode->fwnode); } EXPORT_SYMBOL_GPL(software_node_unregister); struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent) { struct fwnode_handle *fwnode; struct software_node *node; struct swnode *p; if (IS_ERR(parent)) return ERR_CAST(parent); p = to_swnode(parent); if (parent && !p) return ERR_PTR(-EINVAL); node = software_node_alloc(properties); if (IS_ERR(node)) return ERR_CAST(node); node->parent = p ? p->node : NULL; fwnode = swnode_register(node, p, 1); if (IS_ERR(fwnode)) software_node_free(node); return fwnode; } EXPORT_SYMBOL_GPL(fwnode_create_software_node); void fwnode_remove_software_node(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode) return; kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(fwnode_remove_software_node); /** * device_add_software_node - Assign software node to a device * @dev: The device the software node is meant for. * @node: The software node. * * This function will make @node the secondary firmware node pointer of @dev. If * @dev has no primary node, then @node will become the primary node. The * function will register @node automatically if it wasn't already registered. */ int device_add_software_node(struct device *dev, const struct software_node *node) { struct swnode *swnode; int ret; /* Only one software node per device. */ if (dev_to_swnode(dev)) return -EBUSY; swnode = software_node_to_swnode(node); if (swnode) { kobject_get(&swnode->kobj); } else { ret = software_node_register(node); if (ret) return ret; swnode = software_node_to_swnode(node); } set_secondary_fwnode(dev, &swnode->fwnode); /* * If the device has been fully registered by the time this function is * called, software_node_notify() must be called separately so that the * symlinks get created and the reference count of the node is kept in * balance. */ if (device_is_registered(dev)) software_node_notify(dev); return 0; } EXPORT_SYMBOL_GPL(device_add_software_node); /** * device_remove_software_node - Remove device's software node * @dev: The device with the software node. * * This function will unregister the software node of @dev. */ void device_remove_software_node(struct device *dev) { struct swnode *swnode; swnode = dev_to_swnode(dev); if (!swnode) return; if (device_is_registered(dev)) software_node_notify_remove(dev); set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(device_remove_software_node); /** * device_create_managed_software_node - Create a software node for a device * @dev: The device the software node is assigned to. * @properties: Device properties for the software node. * @parent: Parent of the software node. * * Creates a software node as a managed resource for @dev, which means the * lifetime of the newly created software node is tied to the lifetime of @dev. * Software nodes created with this function should not be reused or shared * because of that. The function takes a deep copy of @properties for the * software node. * * Since the new software node is assigned directly to @dev, and since it should * not be shared, it is not returned to the caller. The function returns 0 on * success, and errno in case of an error. */ int device_create_managed_software_node(struct device *dev, const struct property_entry *properties, const struct software_node *parent) { struct fwnode_handle *p = software_node_fwnode(parent); struct fwnode_handle *fwnode; if (parent && !p) return -EINVAL; fwnode = fwnode_create_software_node(properties, p); if (IS_ERR(fwnode)) return PTR_ERR(fwnode); to_swnode(fwnode)->managed = true; set_secondary_fwnode(dev, fwnode); if (device_is_registered(dev)) software_node_notify(dev); return 0; } EXPORT_SYMBOL_GPL(device_create_managed_software_node); void software_node_notify(struct device *dev) { struct swnode *swnode; int ret; swnode = dev_to_swnode(dev); if (!swnode) return; kobject_get(&swnode->kobj); ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node"); if (ret) return; ret = sysfs_create_link(&swnode->kobj, &dev->kobj, dev_name(dev)); if (ret) { sysfs_remove_link(&dev->kobj, "software_node"); return; } } void software_node_notify_remove(struct device *dev) { struct swnode *swnode; swnode = dev_to_swnode(dev); if (!swnode) return; sysfs_remove_link(&swnode->kobj, dev_name(dev)); sysfs_remove_link(&dev->kobj, "software_node"); kobject_put(&swnode->kobj); if (swnode->managed) { set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } } static int __init software_node_init(void) { swnode_kset = kset_create_and_add("software_nodes", NULL, kernel_kobj); if (!swnode_kset) return -ENOMEM; return 0; } postcore_initcall(software_node_init); static void __exit software_node_exit(void) { ida_destroy(&swnode_root_ids); kset_unregister(swnode_kset); } __exitcall(software_node_exit); |
| 2168 2174 2165 2174 2172 2175 2178 2173 2170 2172 2177 2170 2170 2178 2172 2166 2178 2173 2170 2174 2176 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Base port operations for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * Split from 8250_core.c, Copyright (C) 2001 Russell King. * * A note about mapbase / membase * * mapbase is the physical address of the IO port. * membase is an 'ioremapped' cookie. */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/console.h> #include <linux/gpio/consumer.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include <linux/ktime.h> #include <asm/io.h> #include <asm/irq.h> #include "8250.h" /* * Debugging. */ #if 0 #define DEBUG_AUTOCONF(fmt...) printk(fmt) #else #define DEBUG_AUTOCONF(fmt...) do { } while (0) #endif /* * Here we define the default xmit fifo size used for each type of UART. */ static const struct serial8250_config uart_config[] = { [PORT_UNKNOWN] = { .name = "unknown", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_8250] = { .name = "8250", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16450] = { .name = "16450", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550] = { .name = "16550", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550A] = { .name = "16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_CIRRUS] = { .name = "Cirrus", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16650] = { .name = "ST16650", .fifo_size = 1, .tx_loadsz = 1, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16650V2] = { .name = "ST16650V2", .fifo_size = 32, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_00, .rxtrig_bytes = {8, 16, 24, 28}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16750] = { .name = "TI16750", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .rxtrig_bytes = {1, 16, 32, 56}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP | UART_CAP_AFE, }, [PORT_STARTECH] = { .name = "Startech", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16C950] = { .name = "16C950/954", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {16, 32, 112, 120}, /* UART_CAP_EFR breaks billionon CF bluetooth card. */ .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_16654] = { .name = "ST16654", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_10, .rxtrig_bytes = {8, 16, 56, 60}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16850] = { .name = "XR16850", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_RSA] = { .name = "RSA", .fifo_size = 2048, .tx_loadsz = 2048, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11, .flags = UART_CAP_FIFO, }, [PORT_NS16550A] = { .name = "NS16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_NATSEMI, }, [PORT_XSCALE] = { .name = "XScale", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_UUE | UART_CAP_RTOIE, }, [PORT_OCTEON] = { .name = "OCTEON", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO, }, [PORT_U6_16550A] = { .name = "U6_16550A", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_TEGRA] = { .name = "Tegra", .fifo_size = 32, .tx_loadsz = 8, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_01, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_RTOIE, }, [PORT_XR17D15X] = { .name = "XR17D15X", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_XR17V35X] = { .name = "XR17V35X", .fifo_size = 256, .tx_loadsz = 256, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11 | UART_FCR_T_TRIG_11, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_LPC3220] = { .name = "LPC3220", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00 | UART_FCR_T_TRIG_00, .flags = UART_CAP_FIFO, }, [PORT_BRCM_TRUMANAGE] = { .name = "TruManage", .fifo_size = 1, .tx_loadsz = 1024, .flags = UART_CAP_HFIFO, }, [PORT_8250_CIR] = { .name = "CIR port" }, [PORT_ALTR_16550_F32] = { .name = "Altera 16550 FIFO32", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 8, 16, 30}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F64] = { .name = "Altera 16550 FIFO64", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 16, 32, 62}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F128] = { .name = "Altera 16550 FIFO128", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 126}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, /* * tx_loadsz is set to 63-bytes instead of 64-bytes to implement * workaround of errata A-008006 which states that tx_loadsz should * be configured less than Maximum supported fifo bytes. */ [PORT_16550A_FSL64] = { .name = "16550A_FSL64", .fifo_size = 64, .tx_loadsz = 63, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .flags = UART_CAP_FIFO | UART_CAP_NOTEMT, }, [PORT_RT2880] = { .name = "Palmchip BK-3103", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_DA830] = { .name = "TI DA8xx/66AK2x", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_MTK_BTIF] = { .name = "MediaTek BTIF", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .flags = UART_CAP_FIFO, }, [PORT_NPCM] = { .name = "Nuvoton 16550", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_SUNIX] = { .name = "Sunix", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 112}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_ASPEED_VUART] = { .name = "ASPEED VUART", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_MCHP16550A] = { .name = "MCHP16550A", .fifo_size = 256, .tx_loadsz = 256, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {2, 66, 130, 194}, .flags = UART_CAP_FIFO, }, [PORT_BCM7271] = { .name = "Broadcom BCM7271 UART", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {1, 8, 16, 30}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, }; /* Uart divisor latch read */ static u32 default_serial_dl_read(struct uart_8250_port *up) { /* Assign these in pieces to truncate any bits above 7. */ unsigned char dll = serial_in(up, UART_DLL); unsigned char dlm = serial_in(up, UART_DLM); return dll | dlm << 8; } /* Uart divisor latch write */ static void default_serial_dl_write(struct uart_8250_port *up, u32 value) { serial_out(up, UART_DLL, value & 0xff); serial_out(up, UART_DLM, value >> 8 & 0xff); } #ifdef CONFIG_HAS_IOPORT static unsigned int hub6_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); return inb(p->iobase + 1); } static void hub6_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); outb(value, p->iobase + 1); } #endif /* CONFIG_HAS_IOPORT */ static unsigned int mem_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readb(p->membase + offset); } static void mem_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writeb(value, p->membase + offset); } static void mem16_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writew(value, p->membase + offset); } static unsigned int mem16_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readw(p->membase + offset); } static void mem32_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writel(value, p->membase + offset); } static unsigned int mem32_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readl(p->membase + offset); } static void mem32be_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; iowrite32be(value, p->membase + offset); } static unsigned int mem32be_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return ioread32be(p->membase + offset); } #ifdef CONFIG_HAS_IOPORT static unsigned int io_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return inb(p->iobase + offset); } static void io_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; outb(value, p->iobase + offset); } #endif static unsigned int no_serial_in(struct uart_port *p, int offset) { return (unsigned int)-1; } static void no_serial_out(struct uart_port *p, int offset, int value) { } static int serial8250_default_handle_irq(struct uart_port *port); static void set_io_from_upio(struct uart_port *p) { struct uart_8250_port *up = up_to_u8250p(p); up->dl_read = default_serial_dl_read; up->dl_write = default_serial_dl_write; switch (p->iotype) { #ifdef CONFIG_HAS_IOPORT case UPIO_HUB6: p->serial_in = hub6_serial_in; p->serial_out = hub6_serial_out; break; #endif case UPIO_MEM: p->serial_in = mem_serial_in; p->serial_out = mem_serial_out; break; case UPIO_MEM16: p->serial_in = mem16_serial_in; p->serial_out = mem16_serial_out; break; case UPIO_MEM32: p->serial_in = mem32_serial_in; p->serial_out = mem32_serial_out; break; case UPIO_MEM32BE: p->serial_in = mem32be_serial_in; p->serial_out = mem32be_serial_out; break; #ifdef CONFIG_HAS_IOPORT case UPIO_PORT: p->serial_in = io_serial_in; p->serial_out = io_serial_out; break; #endif default: WARN(p->iotype != UPIO_PORT || p->iobase, "Unsupported UART type %x\n", p->iotype); p->serial_in = no_serial_in; p->serial_out = no_serial_out; } /* Remember loaded iotype */ up->cur_iotype = p->iotype; p->handle_irq = serial8250_default_handle_irq; } static void serial_port_out_sync(struct uart_port *p, int offset, int value) { switch (p->iotype) { case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: p->serial_out(p, offset, value); p->serial_in(p, UART_LCR); /* safe, no side-effects */ break; default: p->serial_out(p, offset, value); } } /* * FIFO support. */ static void serial8250_clear_fifos(struct uart_8250_port *p) { if (p->capabilities & UART_CAP_FIFO) { serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial_out(p, UART_FCR, 0); } } static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t); static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t); void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p) { serial8250_clear_fifos(p); serial_out(p, UART_FCR, p->fcr); } EXPORT_SYMBOL_GPL(serial8250_clear_and_reinit_fifos); void serial8250_rpm_get(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_get_sync(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_get); void serial8250_rpm_put(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_put); /** * serial8250_em485_init() - put uart_8250_port into rs485 emulating * @p: uart_8250_port port instance * * The function is used to start rs485 software emulating on the * &struct uart_8250_port* @p. Namely, RTS is switched before/after * transmission. The function is idempotent, so it is safe to call it * multiple times. * * The caller MUST enable interrupt on empty shift register before * calling serial8250_em485_init(). This interrupt is not a part of * 8250 standard, but implementation defined. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_destroy() * * Return 0 - success, -errno - otherwise */ static int serial8250_em485_init(struct uart_8250_port *p) { /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&p->port.lock); if (p->em485) goto deassert_rts; p->em485 = kmalloc(sizeof(struct uart_8250_em485), GFP_ATOMIC); if (!p->em485) return -ENOMEM; hrtimer_setup(&p->em485->stop_tx_timer, &serial8250_em485_handle_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer_setup(&p->em485->start_tx_timer, &serial8250_em485_handle_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); p->em485->port = p; p->em485->active_timer = NULL; p->em485->tx_stopped = true; deassert_rts: if (p->em485->tx_stopped) p->rs485_stop_tx(p, true); return 0; } /** * serial8250_em485_destroy() - put uart_8250_port into normal state * @p: uart_8250_port port instance * * The function is used to stop rs485 software emulating on the * &struct uart_8250_port* @p. The function is idempotent, so it is safe to * call it multiple times. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_init() */ void serial8250_em485_destroy(struct uart_8250_port *p) { if (!p->em485) return; hrtimer_cancel(&p->em485->start_tx_timer); hrtimer_cancel(&p->em485->stop_tx_timer); kfree(p->em485); p->em485 = NULL; } EXPORT_SYMBOL_GPL(serial8250_em485_destroy); struct serial_rs485 serial8250_em485_supported = { .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND | SER_RS485_TERMINATE_BUS | SER_RS485_RX_DURING_TX, .delay_rts_before_send = 1, .delay_rts_after_send = 1, }; EXPORT_SYMBOL_GPL(serial8250_em485_supported); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port * @termios: termios structure * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings * if the uart is incapable of driving RTS as a Transmit Enable signal in * hardware, relying on software emulation instead. */ int serial8250_em485_config(struct uart_port *port, struct ktermios *termios, struct serial_rs485 *rs485) { struct uart_8250_port *up = up_to_u8250p(port); /* * Both serial8250_em485_init() and serial8250_em485_destroy() * are idempotent. */ if (rs485->flags & SER_RS485_ENABLED) return serial8250_em485_init(up); serial8250_em485_destroy(up); return 0; } EXPORT_SYMBOL_GPL(serial8250_em485_config); /* * These two wrappers ensure that enable_runtime_pm_tx() can be called more than * once and disable_runtime_pm_tx() will still disable RPM because the fifo is * empty and the HW can idle again. */ void serial8250_rpm_get_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 1); if (rpm_active) return; pm_runtime_get_sync(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_get_tx); void serial8250_rpm_put_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 0); if (!rpm_active) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_put_tx); /* * IER sleep support. UARTs which have EFRs need the "extended * capability" bit enabled. Note that on XR16C850s, we need to * reset LCR to write to IER. */ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) { unsigned char lcr = 0, efr = 0; serial8250_rpm_get(p); if (p->capabilities & UART_CAP_SLEEP) { /* Synchronize UART_IER access against the console. */ uart_port_lock_irq(&p->port); if (p->capabilities & UART_CAP_EFR) { lcr = serial_in(p, UART_LCR); efr = serial_in(p, UART_EFR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, UART_EFR_ECB); serial_out(p, UART_LCR, 0); } serial_out(p, UART_IER, sleep ? UART_IERX_SLEEP : 0); if (p->capabilities & UART_CAP_EFR) { serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, efr); serial_out(p, UART_LCR, lcr); } uart_port_unlock_irq(&p->port); } serial8250_rpm_put(p); } static void serial8250_clear_IER(struct uart_8250_port *up) { if (up->capabilities & UART_CAP_UUE) serial_out(up, UART_IER, UART_IER_UUE); else serial_out(up, UART_IER, 0); } #ifdef CONFIG_SERIAL_8250_RSA /* * Attempts to turn on the RSA FIFO. Returns zero on failure. * We set the port uart clock rate if we succeed. */ static int __enable_rsa(struct uart_8250_port *up) { unsigned char mode; int result; mode = serial_in(up, UART_RSA_MSR); result = mode & UART_RSA_MSR_FIFO; if (!result) { serial_out(up, UART_RSA_MSR, mode | UART_RSA_MSR_FIFO); mode = serial_in(up, UART_RSA_MSR); result = mode & UART_RSA_MSR_FIFO; } if (result) up->port.uartclk = SERIAL_RSA_BAUD_BASE * 16; return result; } static void enable_rsa(struct uart_8250_port *up) { if (up->port.type == PORT_RSA) { if (up->port.uartclk != SERIAL_RSA_BAUD_BASE * 16) { uart_port_lock_irq(&up->port); __enable_rsa(up); uart_port_unlock_irq(&up->port); } if (up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) serial_out(up, UART_RSA_FRR, 0); } } /* * Attempts to turn off the RSA FIFO. Returns zero on failure. * It is unknown why interrupts were disabled in here. However, * the caller is expected to preserve this behaviour by grabbing * the spinlock before calling this function. */ static void disable_rsa(struct uart_8250_port *up) { unsigned char mode; int result; if (up->port.type == PORT_RSA && up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) { uart_port_lock_irq(&up->port); mode = serial_in(up, UART_RSA_MSR); result = !(mode & UART_RSA_MSR_FIFO); if (!result) { serial_out(up, UART_RSA_MSR, mode & ~UART_RSA_MSR_FIFO); mode = serial_in(up, UART_RSA_MSR); result = !(mode & UART_RSA_MSR_FIFO); } if (result) up->port.uartclk = SERIAL_RSA_BAUD_BASE_LO * 16; uart_port_unlock_irq(&up->port); } } #endif /* CONFIG_SERIAL_8250_RSA */ /* * This is a quickie test to see how big the FIFO is. * It doesn't work at all the time, more's the pity. */ static int size_fifo(struct uart_8250_port *up) { unsigned char old_fcr, old_mcr, old_lcr; u32 old_dl; int count; old_lcr = serial_in(up, UART_LCR); serial_out(up, UART_LCR, 0); old_fcr = serial_in(up, UART_FCR); old_mcr = serial8250_in_MCR(up); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial8250_out_MCR(up, UART_MCR_LOOP); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(up); serial_dl_write(up, 0x0001); serial_out(up, UART_LCR, UART_LCR_WLEN8); for (count = 0; count < 256; count++) serial_out(up, UART_TX, count); mdelay(20);/* FIXME - schedule_timeout */ for (count = 0; (serial_in(up, UART_LSR) & UART_LSR_DR) && (count < 256); count++) serial_in(up, UART_RX); serial_out(up, UART_FCR, old_fcr); serial8250_out_MCR(up, old_mcr); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_dl_write(up, old_dl); serial_out(up, UART_LCR, old_lcr); return count; } /* * Read UART ID using the divisor method - set DLL and DLM to zero * and the revision will be in DLL and device type in DLM. We * preserve the device state across this. */ static unsigned int autoconfig_read_divisor_id(struct uart_8250_port *p) { unsigned char old_lcr; unsigned int id, old_dl; old_lcr = serial_in(p, UART_LCR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(p); serial_dl_write(p, 0); id = serial_dl_read(p); serial_dl_write(p, old_dl); serial_out(p, UART_LCR, old_lcr); return id; } /* * This is a helper routine to autodetect StarTech/Exar/Oxsemi UART's. * When this function is called we know it is at least a StarTech * 16650 V2, but it might be one of several StarTech UARTs, or one of * its clones. (We treat the broken original StarTech 16650 V1 as a * 16550, and why not? Startech doesn't seem to even acknowledge its * existence.) * * What evil have men's minds wrought... */ static void autoconfig_has_efr(struct uart_8250_port *up) { unsigned int id1, id2, id3, rev; /* * Everything with an EFR has SLEEP */ up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; /* * First we check to see if it's an Oxford Semiconductor UART. * * If we have to do this here because some non-National * Semiconductor clone chips lock up if you try writing to the * LSR register (which serial_icr_read does) */ /* * Check for Oxford Semiconductor 16C950. * * EFR [4] must be set else this test fails. * * This shouldn't be necessary, but Mike Hudson (Exoray@isys.ca) * claims that it's needed for 952 dual UART's (which are not * recommended for new designs). */ up->acr = 0; serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, 0x00); id1 = serial_icr_read(up, UART_ID1); id2 = serial_icr_read(up, UART_ID2); id3 = serial_icr_read(up, UART_ID3); rev = serial_icr_read(up, UART_REV); DEBUG_AUTOCONF("950id=%02x:%02x:%02x:%02x ", id1, id2, id3, rev); if (id1 == 0x16 && id2 == 0xC9 && (id3 == 0x50 || id3 == 0x52 || id3 == 0x54)) { up->port.type = PORT_16C950; /* * Enable work around for the Oxford Semiconductor 952 rev B * chip which causes it to seriously miscalculate baud rates * when DLL is 0. */ if (id3 == 0x52 && rev == 0x01) up->bugs |= UART_BUG_QUOT; return; } /* * We check for a XR16C850 by setting DLL and DLM to 0, and then * reading back DLL and DLM. The chip type depends on the DLM * value read back: * 0x10 - XR16C850 and the DLL contains the chip revision. * 0x12 - XR16C2850. * 0x14 - XR16C854. */ id1 = autoconfig_read_divisor_id(up); DEBUG_AUTOCONF("850id=%04x ", id1); id2 = id1 >> 8; if (id2 == 0x10 || id2 == 0x12 || id2 == 0x14) { up->port.type = PORT_16850; return; } /* * It wasn't an XR16C850. * * We distinguish between the '654 and the '650 by counting * how many bytes are in the FIFO. I'm using this for now, * since that's the technique that was sent to me in the * serial driver update, but I'm not convinced this works. * I've had problems doing this in the past. -TYT */ if (size_fifo(up) == 64) up->port.type = PORT_16654; else up->port.type = PORT_16650V2; } /* * We detected a chip without a FIFO. Only two fall into * this category - the original 8250 and the 16450. The * 16450 has a scratch register (accessible with LCR=0) */ static void autoconfig_8250(struct uart_8250_port *up) { unsigned char scratch, status1, status2; up->port.type = PORT_8250; scratch = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0xa5); status1 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0x5a); status2 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, scratch); if (status1 == 0xa5 && status2 == 0x5a) up->port.type = PORT_16450; } static int broken_efr(struct uart_8250_port *up) { /* * Exar ST16C2550 "A2" devices incorrectly detect as * having an EFR, and report an ID of 0x0201. See * http://linux.derkeiler.com/Mailing-Lists/Kernel/2004-11/4812.html */ if (autoconfig_read_divisor_id(up) == 0x0201 && size_fifo(up) == 16) return 1; return 0; } /* * We know that the chip has FIFOs. Does it have an EFR? The * EFR is located in the same register position as the IIR and * we know the top two bits of the IIR are currently set. The * EFR should contain zero. Try to read the EFR. */ static void autoconfig_16550a(struct uart_8250_port *up) { unsigned char status1, status2; unsigned int iersave; /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&up->port.lock); up->port.type = PORT_16550A; up->capabilities |= UART_CAP_FIFO; if (!IS_ENABLED(CONFIG_SERIAL_8250_16550A_VARIANTS) && !(up->port.flags & UPF_FULL_PROBE)) return; /* * Check for presence of the EFR when DLAB is set. * Only ST16C650V1 UARTs pass this test. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); if (serial_in(up, UART_EFR) == 0) { serial_out(up, UART_EFR, 0xA8); if (serial_in(up, UART_EFR) != 0) { DEBUG_AUTOCONF("EFRv1 "); up->port.type = PORT_16650; up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; } else { serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, 0); serial_out(up, UART_LCR, 0); if (status1 == UART_IIR_FIFO_ENABLED_16750) up->port.type = PORT_16550A_FSL64; else DEBUG_AUTOCONF("Motorola 8xxx DUART "); } serial_out(up, UART_EFR, 0); return; } /* * Maybe it requires 0xbf to be written to the LCR. * (other ST16C650V2 UARTs, TI16C752A, etc) */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); if (serial_in(up, UART_EFR) == 0 && !broken_efr(up)) { DEBUG_AUTOCONF("EFRv2 "); autoconfig_has_efr(up); return; } /* * Check for a National Semiconductor SuperIO chip. * Attempt to switch to bank 2, read the value of the LOOP bit * from EXCR1. Switch back to bank 0, change it in MCR. Then * switch back to bank 2, read it from EXCR1 again and check * it's changed. If so, set baud_base in EXCR2 to 921600. -- dwmw2 */ serial_out(up, UART_LCR, 0); status1 = serial8250_in_MCR(up); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ if (!((status2 ^ status1) & UART_MCR_LOOP)) { serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1 ^ UART_MCR_LOOP); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1); if ((status2 ^ status1) & UART_MCR_LOOP) { unsigned short quot; serial_out(up, UART_LCR, 0xE0); quot = serial_dl_read(up); quot <<= 3; if (ns16550a_goto_highspeed(up)) serial_dl_write(up, quot); serial_out(up, UART_LCR, 0); up->port.uartclk = 921600*16; up->port.type = PORT_NS16550A; up->capabilities |= UART_NATSEMI; return; } } /* * No EFR. Try to detect a TI16750, which only sets bit 5 of * the IIR when 64 byte FIFO mode is enabled when DLAB is set. * Try setting it with and without DLAB set. Cheap clones * set bit 5 without DLAB set. */ serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status2 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, 0); DEBUG_AUTOCONF("iir1=%d iir2=%d ", status1, status2); if (status1 == UART_IIR_FIFO_ENABLED_16550A && status2 == UART_IIR_FIFO_ENABLED_16750) { up->port.type = PORT_16750; up->capabilities |= UART_CAP_AFE | UART_CAP_SLEEP; return; } /* * Try writing and reading the UART_IER_UUE bit (b6). * If it works, this is probably one of the Xscale platform's * internal UARTs. * We're going to explicitly set the UUE bit to 0 before * trying to write and read a 1 just to make sure it's not * already a 1 and maybe locked there before we even start. */ iersave = serial_in(up, UART_IER); serial_out(up, UART_IER, iersave & ~UART_IER_UUE); if (!(serial_in(up, UART_IER) & UART_IER_UUE)) { /* * OK it's in a known zero state, try writing and reading * without disturbing the current state of the other bits. */ serial_out(up, UART_IER, iersave | UART_IER_UUE); if (serial_in(up, UART_IER) & UART_IER_UUE) { /* * It's an Xscale. * We'll leave the UART_IER_UUE bit set to 1 (enabled). */ DEBUG_AUTOCONF("Xscale "); up->port.type = PORT_XSCALE; up->capabilities |= UART_CAP_UUE | UART_CAP_RTOIE; return; } } else { /* * If we got here we couldn't force the IER_UUE bit to 0. * Log it and continue. */ DEBUG_AUTOCONF("Couldn't force IER_UUE to 0 "); } serial_out(up, UART_IER, iersave); /* * We distinguish between 16550A and U6 16550A by counting * how many bytes are in the FIFO. */ if (up->port.type == PORT_16550A && size_fifo(up) == 64) { up->port.type = PORT_U6_16550A; up->capabilities |= UART_CAP_AFE; } } /* * This routine is called by rs_init() to initialize a specific serial * port. It determines what type of UART chip this serial port is * using: 8250, 16450, 16550, 16550A. The important question is * whether or not this UART is a 16550A or not, since this will * determine whether or not we can use its FIFO features or not. */ static void autoconfig(struct uart_8250_port *up) { unsigned char status1, scratch, scratch2, scratch3; unsigned char save_lcr, save_mcr; struct uart_port *port = &up->port; unsigned long flags; unsigned int old_capabilities; if (!port->iobase && !port->mapbase && !port->membase) return; DEBUG_AUTOCONF("%s: autoconf (0x%04lx, 0x%p): ", port->name, port->iobase, port->membase); /* * We really do need global IRQs disabled here - we're going to * be frobbing the chips IRQ enable register to see if it exists. * * Synchronize UART_IER access against the console. */ uart_port_lock_irqsave(port, &flags); up->capabilities = 0; up->bugs = 0; if (!(port->flags & UPF_BUGGY_UART)) { /* * Do a simple existence test first; if we fail this, * there's no point trying anything else. * * 0x80 is used as a nonsense port to prevent against * false positives due to ISA bus float. The * assumption is that 0x80 is a non-existent port; * which should be safe since include/asm/io.h also * makes this assumption. * * Note: this is safe as long as MCR bit 4 is clear * and the device is in "PC" mode. */ scratch = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); #if defined(__i386__) && defined(CONFIG_HAS_IOPORT) outb(0xff, 0x080); #endif /* * Mask out IER[7:4] bits for test as some UARTs (e.g. TL * 16C754B) allow only to modify them if an EFR bit is set. */ scratch2 = serial_in(up, UART_IER) & UART_IER_ALL_INTR; serial_out(up, UART_IER, UART_IER_ALL_INTR); #if defined(__i386__) && defined(CONFIG_HAS_IOPORT) outb(0, 0x080); #endif scratch3 = serial_in(up, UART_IER) & UART_IER_ALL_INTR; serial_out(up, UART_IER, scratch); if (scratch2 != 0 || scratch3 != UART_IER_ALL_INTR) { /* * We failed; there's nothing here */ uart_port_unlock_irqrestore(port, flags); DEBUG_AUTOCONF("IER test failed (%02x, %02x) ", scratch2, scratch3); goto out; } } save_mcr = serial8250_in_MCR(up); save_lcr = serial_in(up, UART_LCR); /* * Check to see if a UART is really there. Certain broken * internal modems based on the Rockwell chipset fail this * test, because they apparently don't implement the loopback * test mode. So this test is skipped on the COM 1 through * COM 4 ports. This *should* be safe, since no board * manufacturer would be stupid enough to design a board * that conflicts with COM 1-4 --- we hope! */ if (!(port->flags & UPF_SKIP_TEST)) { serial8250_out_MCR(up, UART_MCR_LOOP | UART_MCR_OUT2 | UART_MCR_RTS); status1 = serial_in(up, UART_MSR) & UART_MSR_STATUS_BITS; serial8250_out_MCR(up, save_mcr); if (status1 != (UART_MSR_DCD | UART_MSR_CTS)) { uart_port_unlock_irqrestore(port, flags); DEBUG_AUTOCONF("LOOP test failed (%02x) ", status1); goto out; } } /* * We're pretty sure there's a port here. Lets find out what * type of port it is. The IIR top two bits allows us to find * out if it's 8250 or 16450, 16550, 16550A or later. This * determines what we test for next. * * We also initialise the EFR (if any) to zero for later. The * EFR occupies the same register location as the FCR and IIR. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, 0); serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); switch (serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED) { case UART_IIR_FIFO_ENABLED_8250: autoconfig_8250(up); break; case UART_IIR_FIFO_ENABLED_16550: port->type = PORT_16550; break; case UART_IIR_FIFO_ENABLED_16550A: autoconfig_16550a(up); break; default: port->type = PORT_UNKNOWN; break; } #ifdef CONFIG_SERIAL_8250_RSA /* * Only probe for RSA ports if we got the region. */ if (port->type == PORT_16550A && up->probe & UART_PROBE_RSA && __enable_rsa(up)) port->type = PORT_RSA; #endif serial_out(up, UART_LCR, save_lcr); port->fifosize = uart_config[up->port.type].fifo_size; old_capabilities = up->capabilities; up->capabilities = uart_config[port->type].flags; up->tx_loadsz = uart_config[port->type].tx_loadsz; if (port->type == PORT_UNKNOWN) goto out_unlock; /* * Reset the UART. */ #ifdef CONFIG_SERIAL_8250_RSA if (port->type == PORT_RSA) serial_out(up, UART_RSA_FRR, 0); #endif serial8250_out_MCR(up, save_mcr); serial8250_clear_fifos(up); serial_in(up, UART_RX); serial8250_clear_IER(up); out_unlock: uart_port_unlock_irqrestore(port, flags); /* * Check if the device is a Fintek F81216A */ if (port->type == PORT_16550A && port->iotype == UPIO_PORT) fintek_8250_probe(up); if (up->capabilities != old_capabilities) { dev_warn(port->dev, "detected caps %08x should be %08x\n", old_capabilities, up->capabilities); } out: DEBUG_AUTOCONF("iir=%d ", scratch); DEBUG_AUTOCONF("type=%s\n", uart_config[port->type].name); } static void autoconfig_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; unsigned char save_mcr, save_ier; unsigned char save_ICP = 0; unsigned int ICP = 0; unsigned long irqs; int irq; if (port->flags & UPF_FOURPORT) { ICP = (port->iobase & 0xfe0) | 0x1f; save_ICP = inb_p(ICP); outb_p(0x80, ICP); inb_p(ICP); } /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); /* Synchronize UART_IER access against the console. */ uart_port_lock_irq(port); save_ier = serial_in(up, UART_IER); uart_port_unlock_irq(port); serial8250_out_MCR(up, UART_MCR_OUT1 | UART_MCR_OUT2); irqs = probe_irq_on(); serial8250_out_MCR(up, 0); udelay(10); if (port->flags & UPF_FOURPORT) { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); } else { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2); } /* Synchronize UART_IER access against the console. */ uart_port_lock_irq(port); serial_out(up, UART_IER, UART_IER_ALL_INTR); uart_port_unlock_irq(port); serial_in(up, UART_LSR); serial_in(up, UART_RX); serial_in(up, UART_IIR); serial_in(up, UART_MSR); serial_out(up, UART_TX, 0xFF); udelay(20); irq = probe_irq_off(irqs); serial8250_out_MCR(up, save_mcr); /* Synchronize UART_IER access against the console. */ uart_port_lock_irq(port); serial_out(up, UART_IER, save_ier); uart_port_unlock_irq(port); if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); port->irq = (irq > 0) ? irq : 0; } static void serial8250_stop_rx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); serial8250_rpm_get(up); up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); serial_port_out(port, UART_IER, up->ier); serial8250_rpm_put(up); } /** * serial8250_em485_stop_tx() - generic ->rs485_stop_tx() callback * @p: uart 8250 port * @toggle_ier: true to allow enabling receive interrupts * * Generic callback usable by 8250 uart drivers to stop rs485 transmission. */ void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier) { unsigned char mcr = serial8250_in_MCR(p); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&p->port.lock); if (p->port.rs485.flags & SER_RS485_RTS_AFTER_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(p, mcr); /* * Empty the RX FIFO, we are not interested in anything * received during the half-duplex transmission. * Enable previously disabled RX interrupts. */ if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) { serial8250_clear_and_reinit_fifos(p); if (toggle_ier) { p->ier |= UART_IER_RLSI | UART_IER_RDI; serial_port_out(&p->port, UART_IER, p->ier); } } } EXPORT_SYMBOL_GPL(serial8250_em485_stop_tx); static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t) { struct uart_8250_em485 *em485 = container_of(t, struct uart_8250_em485, stop_tx_timer); struct uart_8250_port *p = em485->port; unsigned long flags; serial8250_rpm_get(p); uart_port_lock_irqsave(&p->port, &flags); if (em485->active_timer == &em485->stop_tx_timer) { p->rs485_stop_tx(p, true); em485->active_timer = NULL; em485->tx_stopped = true; } uart_port_unlock_irqrestore(&p->port, flags); serial8250_rpm_put(p); return HRTIMER_NORESTART; } static void start_hrtimer_ms(struct hrtimer *hrt, unsigned long msec) { hrtimer_start(hrt, ms_to_ktime(msec), HRTIMER_MODE_REL); } static void __stop_tx_rs485(struct uart_8250_port *p, u64 stop_delay) { struct uart_8250_em485 *em485 = p->em485; /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&p->port.lock); stop_delay += (u64)p->port.rs485.delay_rts_after_send * NSEC_PER_MSEC; /* * rs485_stop_tx() is going to set RTS according to config * AND flush RX FIFO if required. */ if (stop_delay > 0) { em485->active_timer = &em485->stop_tx_timer; hrtimer_start(&em485->stop_tx_timer, ns_to_ktime(stop_delay), HRTIMER_MODE_REL); } else { p->rs485_stop_tx(p, true); em485->active_timer = NULL; em485->tx_stopped = true; } } static inline void __stop_tx(struct uart_8250_port *p) { struct uart_8250_em485 *em485 = p->em485; if (em485) { u16 lsr = serial_lsr_in(p); u64 stop_delay = 0; if (!(lsr & UART_LSR_THRE)) return; /* * To provide required timing and allow FIFO transfer, * __stop_tx_rs485() must be called only when both FIFO and * shift register are empty. The device driver should either * enable interrupt on TEMT or set UART_CAP_NOTEMT that will * enlarge stop_tx_timer by the tx time of one frame to cover * for emptying of the shift register. */ if (!(lsr & UART_LSR_TEMT)) { if (!(p->capabilities & UART_CAP_NOTEMT)) return; /* * RTS might get deasserted too early with the normal * frame timing formula. It seems to suggest THRE might * get asserted already during tx of the stop bit * rather than after it is fully sent. * Roughly estimate 1 extra bit here with / 7. */ stop_delay = p->port.frame_time + DIV_ROUND_UP(p->port.frame_time, 7); } __stop_tx_rs485(p, stop_delay); } if (serial8250_clear_THRI(p)) serial8250_rpm_put_tx(p); } static void serial8250_stop_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); __stop_tx(up); /* * We really want to stop the transmitter from sending. */ if (port->type == PORT_16C950) { up->acr |= UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } serial8250_rpm_put(up); } static inline void __start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (up->dma && !up->dma->tx_dma(up)) return; if (serial8250_set_THRI(up)) { if (up->bugs & UART_BUG_TXEN) { u16 lsr = serial_lsr_in(up); if (lsr & UART_LSR_THRE) serial8250_tx_chars(up); } } /* * Re-enable the transmitter if we disabled it. */ if (port->type == PORT_16C950 && up->acr & UART_ACR_TXDIS) { up->acr &= ~UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } } /** * serial8250_em485_start_tx() - generic ->rs485_start_tx() callback * @up: uart 8250 port * @toggle_ier: true to allow disabling receive interrupts * * Generic callback usable by 8250 uart drivers to start rs485 transmission. * Assumes that setting the RTS bit in the MCR register means RTS is high. * (Some chips use inverse semantics.) Further assumes that reception is * stoppable by disabling the UART_IER_RDI interrupt. (Some chips set the * UART_LSR_DR bit even when UART_IER_RDI is disabled, foiling this approach.) */ void serial8250_em485_start_tx(struct uart_8250_port *up, bool toggle_ier) { unsigned char mcr = serial8250_in_MCR(up); if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX) && toggle_ier) serial8250_stop_rx(&up->port); if (up->port.rs485.flags & SER_RS485_RTS_ON_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(up, mcr); } EXPORT_SYMBOL_GPL(serial8250_em485_start_tx); /* Returns false, if start_tx_timer was setup to defer TX start */ static bool start_tx_rs485(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; /* * While serial8250_em485_handle_stop_tx() is a noop if * em485->active_timer != &em485->stop_tx_timer, it might happen that * the timer is still armed and triggers only after the current bunch of * chars is send and em485->active_timer == &em485->stop_tx_timer again. * So cancel the timer. There is still a theoretical race condition if * the timer is already running and only comes around to check for * em485->active_timer when &em485->stop_tx_timer is armed again. */ if (em485->active_timer == &em485->stop_tx_timer) hrtimer_try_to_cancel(&em485->stop_tx_timer); em485->active_timer = NULL; if (em485->tx_stopped) { em485->tx_stopped = false; up->rs485_start_tx(up, true); if (up->port.rs485.delay_rts_before_send > 0) { em485->active_timer = &em485->start_tx_timer; start_hrtimer_ms(&em485->start_tx_timer, up->port.rs485.delay_rts_before_send); return false; } } return true; } static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t) { struct uart_8250_em485 *em485 = container_of(t, struct uart_8250_em485, start_tx_timer); struct uart_8250_port *p = em485->port; unsigned long flags; uart_port_lock_irqsave(&p->port, &flags); if (em485->active_timer == &em485->start_tx_timer) { __start_tx(&p->port); em485->active_timer = NULL; } uart_port_unlock_irqrestore(&p->port, flags); return HRTIMER_NORESTART; } static void serial8250_start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); if (!port->x_char && kfifo_is_empty(&port->state->port.xmit_fifo)) return; serial8250_rpm_get_tx(up); if (em485) { if ((em485->active_timer == &em485->start_tx_timer) || !start_tx_rs485(port)) return; } __start_tx(port); } static void serial8250_throttle(struct uart_port *port) { port->throttle(port); } static void serial8250_unthrottle(struct uart_port *port) { port->unthrottle(port); } static void serial8250_disable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_disable_ms_no_sync(up->gpios); up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } static void serial8250_enable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_enable_ms(up->gpios); up->ier |= UART_IER_MSI; serial8250_rpm_get(up); serial_port_out(port, UART_IER, up->ier); serial8250_rpm_put(up); } void serial8250_read_char(struct uart_8250_port *up, u16 lsr) { struct uart_port *port = &up->port; u8 ch, flag = TTY_NORMAL; if (likely(lsr & UART_LSR_DR)) ch = serial_in(up, UART_RX); else /* * Intel 82571 has a Serial Over Lan device that will * set UART_LSR_BI without setting UART_LSR_DR when * it receives a break. To avoid reading from the * receive buffer without UART_LSR_DR bit set, we * just force the read character to be 0 */ ch = 0; port->icount.rx++; lsr |= up->lsr_saved_flags; up->lsr_saved_flags = 0; if (unlikely(lsr & UART_LSR_BRK_ERROR_BITS)) { if (lsr & UART_LSR_BI) { lsr &= ~(UART_LSR_FE | UART_LSR_PE); port->icount.brk++; /* * We do the SysRQ and SAK checking * here because otherwise the break * may get masked by ignore_status_mask * or read_status_mask. */ if (uart_handle_break(port)) return; } else if (lsr & UART_LSR_PE) port->icount.parity++; else if (lsr & UART_LSR_FE) port->icount.frame++; if (lsr & UART_LSR_OE) port->icount.overrun++; /* * Mask off conditions which should be ignored. */ lsr &= port->read_status_mask; if (lsr & UART_LSR_BI) { dev_dbg(port->dev, "handling break\n"); flag = TTY_BREAK; } else if (lsr & UART_LSR_PE) flag = TTY_PARITY; else if (lsr & UART_LSR_FE) flag = TTY_FRAME; } if (uart_prepare_sysrq_char(port, ch)) return; uart_insert_char(port, lsr, UART_LSR_OE, ch, flag); } EXPORT_SYMBOL_GPL(serial8250_read_char); /* * serial8250_rx_chars - Read characters. The first LSR value must be passed in. * * Returns LSR bits. The caller should rely only on non-Rx related LSR bits * (such as THRE) because the LSR value might come from an already consumed * character. */ u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr) { struct uart_port *port = &up->port; int max_count = 256; do { serial8250_read_char(up, lsr); if (--max_count == 0) break; lsr = serial_in(up, UART_LSR); } while (lsr & (UART_LSR_DR | UART_LSR_BI)); tty_flip_buffer_push(&port->state->port); return lsr; } EXPORT_SYMBOL_GPL(serial8250_rx_chars); void serial8250_tx_chars(struct uart_8250_port *up) { struct uart_port *port = &up->port; struct tty_port *tport = &port->state->port; int count; if (port->x_char) { uart_xchar_out(port, UART_TX); return; } if (uart_tx_stopped(port)) { serial8250_stop_tx(port); return; } if (kfifo_is_empty(&tport->xmit_fifo)) { __stop_tx(up); return; } count = up->tx_loadsz; |