| 1307 1307 1296 1296 336 336 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * bus.c - bus driver management * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2007 Novell Inc. */ #include <linux/async.h> #include <linux/device.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/sysfs.h> #include "base.h" #include "power/power.h" /* /sys/devices/system */ static struct kset *system_kset; #define to_bus_attr(_attr) container_of(_attr, struct bus_attribute, attr) /* * sysfs bindings for drivers */ #define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr) #define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct driver_attribute driver_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) static int __must_check bus_rescan_devices_helper(struct device *dev, void *data); static struct bus_type *bus_get(struct bus_type *bus) { if (bus) { kset_get(&bus->p->subsys); return bus; } return NULL; } static void bus_put(struct bus_type *bus) { if (bus) kset_put(&bus->p->subsys); } static ssize_t drv_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct driver_attribute *drv_attr = to_drv_attr(attr); struct driver_private *drv_priv = to_driver(kobj); ssize_t ret = -EIO; if (drv_attr->show) ret = drv_attr->show(drv_priv->driver, buf); return ret; } static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct driver_attribute *drv_attr = to_drv_attr(attr); struct driver_private *drv_priv = to_driver(kobj); ssize_t ret = -EIO; if (drv_attr->store) ret = drv_attr->store(drv_priv->driver, buf, count); return ret; } static const struct sysfs_ops driver_sysfs_ops = { .show = drv_attr_show, .store = drv_attr_store, }; static void driver_release(struct kobject *kobj) { struct driver_private *drv_priv = to_driver(kobj); pr_debug("driver: '%s': %s\n", kobject_name(kobj), __func__); kfree(drv_priv); } static struct kobj_type driver_ktype = { .sysfs_ops = &driver_sysfs_ops, .release = driver_release, }; /* * sysfs bindings for buses */ static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); ssize_t ret = 0; if (bus_attr->show) ret = bus_attr->show(subsys_priv->bus, buf); return ret; } static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); ssize_t ret = 0; if (bus_attr->store) ret = bus_attr->store(subsys_priv->bus, buf, count); return ret; } static const struct sysfs_ops bus_sysfs_ops = { .show = bus_attr_show, .store = bus_attr_store, }; int bus_create_file(struct bus_type *bus, struct bus_attribute *attr) { int error; if (bus_get(bus)) { error = sysfs_create_file(&bus->p->subsys.kobj, &attr->attr); bus_put(bus); } else error = -EINVAL; return error; } EXPORT_SYMBOL_GPL(bus_create_file); void bus_remove_file(struct bus_type *bus, struct bus_attribute *attr) { if (bus_get(bus)) { sysfs_remove_file(&bus->p->subsys.kobj, &attr->attr); bus_put(bus); } } EXPORT_SYMBOL_GPL(bus_remove_file); static void bus_release(struct kobject *kobj) { struct subsys_private *priv = to_subsys_private(kobj); struct bus_type *bus = priv->bus; kfree(priv); bus->p = NULL; } static struct kobj_type bus_ktype = { .sysfs_ops = &bus_sysfs_ops, .release = bus_release, }; static int bus_uevent_filter(struct kset *kset, struct kobject *kobj) { struct kobj_type *ktype = get_ktype(kobj); if (ktype == &bus_ktype) return 1; return 0; } static const struct kset_uevent_ops bus_uevent_ops = { .filter = bus_uevent_filter, }; static struct kset *bus_kset; /* Manually detach a device from its associated driver. */ static ssize_t unbind_store(struct device_driver *drv, const char *buf, size_t count) { struct bus_type *bus = bus_get(drv->bus); struct device *dev; int err = -ENODEV; dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == drv) { device_driver_detach(dev); err = count; } put_device(dev); bus_put(bus); return err; } static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, S_IWUSR, NULL, unbind_store); /* * Manually attach a device to a driver. * Note: the driver must want to bind to the device, * it is not possible to override the driver's id table. */ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t count) { struct bus_type *bus = bus_get(drv->bus); struct device *dev; int err = -ENODEV; dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == NULL && driver_match_device(drv, dev)) { err = device_driver_attach(drv, dev); if (err > 0) { /* success */ err = count; } else if (err == 0) { /* driver didn't accept device */ err = -ENODEV; } } put_device(dev); bus_put(bus); return err; } static DRIVER_ATTR_IGNORE_LOCKDEP(bind, S_IWUSR, NULL, bind_store); static ssize_t drivers_autoprobe_show(struct bus_type *bus, char *buf) { return sprintf(buf, "%d\n", bus->p->drivers_autoprobe); } static ssize_t drivers_autoprobe_store(struct bus_type *bus, const char *buf, size_t count) { if (buf[0] == '0') bus->p->drivers_autoprobe = 0; else bus->p->drivers_autoprobe = 1; return count; } static ssize_t drivers_probe_store(struct bus_type *bus, const char *buf, size_t count) { struct device *dev; int err = -EINVAL; dev = bus_find_device_by_name(bus, NULL, buf); if (!dev) return -ENODEV; if (bus_rescan_devices_helper(dev, NULL) == 0) err = count; put_device(dev); return err; } static struct device *next_device(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct device *dev = NULL; struct device_private *dev_prv; if (n) { dev_prv = to_device_private_bus(n); dev = dev_prv->device; } return dev; } /** * bus_for_each_dev - device iterator. * @bus: bus type. * @start: device to start iterating from. * @data: data for the callback. * @fn: function to be called for each device. * * Iterate over @bus's list of devices, and call @fn for each, * passing it @data. If @start is not NULL, we use that device to * begin iterating from. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. * * NOTE: The device that returns a non-zero value is not retained * in any way, nor is its refcount incremented. If the caller needs * to retain this data, it should do so, and increment the reference * count in the supplied callback. */ int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *, void *)) { struct klist_iter i; struct device *dev; int error = 0; if (!bus || !bus->p) return -EINVAL; klist_iter_init_node(&bus->p->klist_devices, &i, (start ? &start->p->knode_bus : NULL)); while (!error && (dev = next_device(&i))) error = fn(dev, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(bus_for_each_dev); /** * bus_find_device - device iterator for locating a particular device. * @bus: bus type * @start: Device to begin with * @data: Data to pass to match function * @match: Callback function to check device * * This is similar to the bus_for_each_dev() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. */ struct device *bus_find_device(struct bus_type *bus, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)) { struct klist_iter i; struct device *dev; if (!bus || !bus->p) return NULL; klist_iter_init_node(&bus->p->klist_devices, &i, (start ? &start->p->knode_bus : NULL)); while ((dev = next_device(&i))) if (match(dev, data) && get_device(dev)) break; klist_iter_exit(&i); return dev; } EXPORT_SYMBOL_GPL(bus_find_device); /** * subsys_find_device_by_id - find a device with a specific enumeration number * @subsys: subsystem * @id: index 'id' in struct device * @hint: device to check first * * Check the hint's next object and if it is a match return it directly, * otherwise, fall back to a full list search. Either way a reference for * the returned object is taken. */ struct device *subsys_find_device_by_id(struct bus_type *subsys, unsigned int id, struct device *hint) { struct klist_iter i; struct device *dev; if (!subsys) return NULL; if (hint) { klist_iter_init_node(&subsys->p->klist_devices, &i, &hint->p->knode_bus); dev = next_device(&i); if (dev && dev->id == id && get_device(dev)) { klist_iter_exit(&i); return dev; } klist_iter_exit(&i); } klist_iter_init_node(&subsys->p->klist_devices, &i, NULL); while ((dev = next_device(&i))) { if (dev->id == id && get_device(dev)) { klist_iter_exit(&i); return dev; } } klist_iter_exit(&i); return NULL; } EXPORT_SYMBOL_GPL(subsys_find_device_by_id); static struct device_driver *next_driver(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct driver_private *drv_priv; if (n) { drv_priv = container_of(n, struct driver_private, knode_bus); return drv_priv->driver; } return NULL; } /** * bus_for_each_drv - driver iterator * @bus: bus we're dealing with. * @start: driver to start iterating on. * @data: data to pass to the callback. * @fn: function to call for each driver. * * This is nearly identical to the device iterator above. * We iterate over each driver that belongs to @bus, and call * @fn for each. If @fn returns anything but 0, we break out * and return it. If @start is not NULL, we use it as the head * of the list. * * NOTE: we don't return the driver that returns a non-zero * value, nor do we leave the reference count incremented for that * driver. If the caller needs to know that info, it must set it * in the callback. It must also be sure to increment the refcount * so it doesn't disappear before returning to the caller. */ int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, void *data, int (*fn)(struct device_driver *, void *)) { struct klist_iter i; struct device_driver *drv; int error = 0; if (!bus) return -EINVAL; klist_iter_init_node(&bus->p->klist_drivers, &i, start ? &start->p->knode_bus : NULL); while ((drv = next_driver(&i)) && !error) error = fn(drv, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(bus_for_each_drv); /** * bus_add_device - add device to bus * @dev: device being added * * - Add device's bus attributes. * - Create links to device's bus. * - Add the device to its bus's list of devices. */ int bus_add_device(struct device *dev) { struct bus_type *bus = bus_get(dev->bus); int error = 0; if (bus) { pr_debug("bus: '%s': add device %s\n", bus->name, dev_name(dev)); error = device_add_groups(dev, bus->dev_groups); if (error) goto out_put; error = sysfs_create_link(&bus->p->devices_kset->kobj, &dev->kobj, dev_name(dev)); if (error) goto out_groups; error = sysfs_create_link(&dev->kobj, &dev->bus->p->subsys.kobj, "subsystem"); if (error) goto out_subsys; klist_add_tail(&dev->p->knode_bus, &bus->p->klist_devices); } return 0; out_subsys: sysfs_remove_link(&bus->p->devices_kset->kobj, dev_name(dev)); out_groups: device_remove_groups(dev, bus->dev_groups); out_put: bus_put(dev->bus); return error; } /** * bus_probe_device - probe drivers for a new device * @dev: device to probe * * - Automatically probe for a driver if the bus allows it. */ void bus_probe_device(struct device *dev) { struct bus_type *bus = dev->bus; struct subsys_interface *sif; if (!bus) return; if (bus->p->drivers_autoprobe) device_initial_probe(dev); mutex_lock(&bus->p->mutex); list_for_each_entry(sif, &bus->p->interfaces, node) if (sif->add_dev) sif->add_dev(dev, sif); mutex_unlock(&bus->p->mutex); } /** * bus_remove_device - remove device from bus * @dev: device to be removed * * - Remove device from all interfaces. * - Remove symlink from bus' directory. * - Delete device from bus's list. * - Detach from its driver. * - Drop reference taken in bus_add_device(). */ void bus_remove_device(struct device *dev) { struct bus_type *bus = dev->bus; struct subsys_interface *sif; if (!bus) return; mutex_lock(&bus->p->mutex); list_for_each_entry(sif, &bus->p->interfaces, node) if (sif->remove_dev) sif->remove_dev(dev, sif); mutex_unlock(&bus->p->mutex); sysfs_remove_link(&dev->kobj, "subsystem"); sysfs_remove_link(&dev->bus->p->devices_kset->kobj, dev_name(dev)); device_remove_groups(dev, dev->bus->dev_groups); if (klist_node_attached(&dev->p->knode_bus)) klist_del(&dev->p->knode_bus); pr_debug("bus: '%s': remove device %s\n", dev->bus->name, dev_name(dev)); device_release_driver(dev); bus_put(dev->bus); } static int __must_check add_bind_files(struct device_driver *drv) { int ret; ret = driver_create_file(drv, &driver_attr_unbind); if (ret == 0) { ret = driver_create_file(drv, &driver_attr_bind); if (ret) driver_remove_file(drv, &driver_attr_unbind); } return ret; } static void remove_bind_files(struct device_driver *drv) { driver_remove_file(drv, &driver_attr_bind); driver_remove_file(drv, &driver_attr_unbind); } static BUS_ATTR_WO(drivers_probe); static BUS_ATTR_RW(drivers_autoprobe); static int add_probe_files(struct bus_type *bus) { int retval; retval = bus_create_file(bus, &bus_attr_drivers_probe); if (retval) goto out; retval = bus_create_file(bus, &bus_attr_drivers_autoprobe); if (retval) bus_remove_file(bus, &bus_attr_drivers_probe); out: return retval; } static void remove_probe_files(struct bus_type *bus) { bus_remove_file(bus, &bus_attr_drivers_autoprobe); bus_remove_file(bus, &bus_attr_drivers_probe); } static ssize_t uevent_store(struct device_driver *drv, const char *buf, size_t count) { int rc; rc = kobject_synth_uevent(&drv->p->kobj, buf, count); return rc ? rc : count; } static DRIVER_ATTR_WO(uevent); /** * bus_add_driver - Add a driver to the bus. * @drv: driver. */ int bus_add_driver(struct device_driver *drv) { struct bus_type *bus; struct driver_private *priv; int error = 0; bus = bus_get(drv->bus); if (!bus) return -EINVAL; pr_debug("bus: '%s': add driver %s\n", bus->name, drv->name); priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) { error = -ENOMEM; goto out_put_bus; } klist_init(&priv->klist_devices, NULL, NULL); priv->driver = drv; drv->p = priv; priv->kobj.kset = bus->p->drivers_kset; error = kobject_init_and_add(&priv->kobj, &driver_ktype, NULL, "%s", drv->name); if (error) goto out_unregister; klist_add_tail(&priv->knode_bus, &bus->p->klist_drivers); if (drv->bus->p->drivers_autoprobe) { error = driver_attach(drv); if (error) goto out_del_list; } module_add_driver(drv->owner, drv); error = driver_create_file(drv, &driver_attr_uevent); if (error) { printk(KERN_ERR "%s: uevent attr (%s) failed\n", __func__, drv->name); } error = driver_add_groups(drv, bus->drv_groups); if (error) { /* How the hell do we get out of this pickle? Give up */ printk(KERN_ERR "%s: driver_create_groups(%s) failed\n", __func__, drv->name); } if (!drv->suppress_bind_attrs) { error = add_bind_files(drv); if (error) { /* Ditto */ printk(KERN_ERR "%s: add_bind_files(%s) failed\n", __func__, drv->name); } } return 0; out_del_list: klist_del(&priv->knode_bus); out_unregister: kobject_put(&priv->kobj); /* drv->p is freed in driver_release() */ drv->p = NULL; out_put_bus: bus_put(bus); return error; } /** * bus_remove_driver - delete driver from bus's knowledge. * @drv: driver. * * Detach the driver from the devices it controls, and remove * it from its bus's list of drivers. Finally, we drop the reference * to the bus we took in bus_add_driver(). */ void bus_remove_driver(struct device_driver *drv) { if (!drv->bus) return; if (!drv->suppress_bind_attrs) remove_bind_files(drv); driver_remove_groups(drv, drv->bus->drv_groups); driver_remove_file(drv, &driver_attr_uevent); klist_remove(&drv->p->knode_bus); pr_debug("bus: '%s': remove driver %s\n", drv->bus->name, drv->name); driver_detach(drv); module_remove_driver(drv); kobject_put(&drv->p->kobj); bus_put(drv->bus); } /* Helper for bus_rescan_devices's iter */ static int __must_check bus_rescan_devices_helper(struct device *dev, void *data) { int ret = 0; if (!dev->driver) { if (dev->parent && dev->bus->need_parent_lock) device_lock(dev->parent); ret = device_attach(dev); if (dev->parent && dev->bus->need_parent_lock) device_unlock(dev->parent); } return ret < 0 ? ret : 0; } /** * bus_rescan_devices - rescan devices on the bus for possible drivers * @bus: the bus to scan. * * This function will look for devices on the bus with no driver * attached and rescan it against existing drivers to see if it matches * any by calling device_attach() for the unbound devices. */ int bus_rescan_devices(struct bus_type *bus) { return bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper); } EXPORT_SYMBOL_GPL(bus_rescan_devices); /** * device_reprobe - remove driver for a device and probe for a new driver * @dev: the device to reprobe * * This function detaches the attached driver (if any) for the given * device and restarts the driver probing process. It is intended * to use if probing criteria changed during a devices lifetime and * driver attachment should change accordingly. */ int device_reprobe(struct device *dev) { if (dev->driver) device_driver_detach(dev); return bus_rescan_devices_helper(dev, NULL); } EXPORT_SYMBOL_GPL(device_reprobe); /** * find_bus - locate bus by name. * @name: name of bus. * * Call kset_find_obj() to iterate over list of buses to * find a bus by name. Return bus if found. * * Note that kset_find_obj increments bus' reference count. */ #if 0 struct bus_type *find_bus(char *name) { struct kobject *k = kset_find_obj(bus_kset, name); return k ? to_bus(k) : NULL; } #endif /* 0 */ static int bus_add_groups(struct bus_type *bus, const struct attribute_group **groups) { return sysfs_create_groups(&bus->p->subsys.kobj, groups); } static void bus_remove_groups(struct bus_type *bus, const struct attribute_group **groups) { sysfs_remove_groups(&bus->p->subsys.kobj, groups); } static void klist_devices_get(struct klist_node *n) { struct device_private *dev_prv = to_device_private_bus(n); struct device *dev = dev_prv->device; get_device(dev); } static void klist_devices_put(struct klist_node *n) { struct device_private *dev_prv = to_device_private_bus(n); struct device *dev = dev_prv->device; put_device(dev); } static ssize_t bus_uevent_store(struct bus_type *bus, const char *buf, size_t count) { int rc; rc = kobject_synth_uevent(&bus->p->subsys.kobj, buf, count); return rc ? rc : count; } /* * "open code" the old BUS_ATTR() macro here. We want to use BUS_ATTR_WO() * here, but can not use it as earlier in the file we have * DEVICE_ATTR_WO(uevent), which would cause a clash with the with the store * function name. */ static struct bus_attribute bus_attr_uevent = __ATTR(uevent, S_IWUSR, NULL, bus_uevent_store); /** * bus_register - register a driver-core subsystem * @bus: bus to register * * Once we have that, we register the bus with the kobject * infrastructure, then register the children subsystems it has: * the devices and drivers that belong to the subsystem. */ int bus_register(struct bus_type *bus) { int retval; struct subsys_private *priv; struct lock_class_key *key = &bus->lock_key; priv = kzalloc(sizeof(struct subsys_private), GFP_KERNEL); if (!priv) return -ENOMEM; priv->bus = bus; bus->p = priv; BLOCKING_INIT_NOTIFIER_HEAD(&priv->bus_notifier); retval = kobject_set_name(&priv->subsys.kobj, "%s", bus->name); if (retval) goto out; priv->subsys.kobj.kset = bus_kset; priv->subsys.kobj.ktype = &bus_ktype; priv->drivers_autoprobe = 1; retval = kset_register(&priv->subsys); if (retval) goto out; retval = bus_create_file(bus, &bus_attr_uevent); if (retval) goto bus_uevent_fail; priv->devices_kset = kset_create_and_add("devices", NULL, &priv->subsys.kobj); if (!priv->devices_kset) { retval = -ENOMEM; goto bus_devices_fail; } priv->drivers_kset = kset_create_and_add("drivers", NULL, &priv->subsys.kobj); if (!priv->drivers_kset) { retval = -ENOMEM; goto bus_drivers_fail; } INIT_LIST_HEAD(&priv->interfaces); __mutex_init(&priv->mutex, "subsys mutex", key); klist_init(&priv->klist_devices, klist_devices_get, klist_devices_put); klist_init(&priv->klist_drivers, NULL, NULL); retval = add_probe_files(bus); if (retval) goto bus_probe_files_fail; retval = bus_add_groups(bus, bus->bus_groups); if (retval) goto bus_groups_fail; pr_debug("bus: '%s': registered\n", bus->name); return 0; bus_groups_fail: remove_probe_files(bus); bus_probe_files_fail: kset_unregister(bus->p->drivers_kset); bus_drivers_fail: kset_unregister(bus->p->devices_kset); bus_devices_fail: bus_remove_file(bus, &bus_attr_uevent); bus_uevent_fail: kset_unregister(&bus->p->subsys); out: kfree(bus->p); bus->p = NULL; return retval; } EXPORT_SYMBOL_GPL(bus_register); /** * bus_unregister - remove a bus from the system * @bus: bus. * * Unregister the child subsystems and the bus itself. * Finally, we call bus_put() to release the refcount */ void bus_unregister(struct bus_type *bus) { pr_debug("bus: '%s': unregistering\n", bus->name); if (bus->dev_root) device_unregister(bus->dev_root); bus_remove_groups(bus, bus->bus_groups); remove_probe_files(bus); kset_unregister(bus->p->drivers_kset); kset_unregister(bus->p->devices_kset); bus_remove_file(bus, &bus_attr_uevent); kset_unregister(&bus->p->subsys); } EXPORT_SYMBOL_GPL(bus_unregister); int bus_register_notifier(struct bus_type *bus, struct notifier_block *nb) { return blocking_notifier_chain_register(&bus->p->bus_notifier, nb); } EXPORT_SYMBOL_GPL(bus_register_notifier); int bus_unregister_notifier(struct bus_type *bus, struct notifier_block *nb) { return blocking_notifier_chain_unregister(&bus->p->bus_notifier, nb); } EXPORT_SYMBOL_GPL(bus_unregister_notifier); struct kset *bus_get_kset(struct bus_type *bus) { return &bus->p->subsys; } EXPORT_SYMBOL_GPL(bus_get_kset); struct klist *bus_get_device_klist(struct bus_type *bus) { return &bus->p->klist_devices; } EXPORT_SYMBOL_GPL(bus_get_device_klist); /* * Yes, this forcibly breaks the klist abstraction temporarily. It * just wants to sort the klist, not change reference counts and * take/drop locks rapidly in the process. It does all this while * holding the lock for the list, so objects can't otherwise be * added/removed while we're swizzling. */ static void device_insertion_sort_klist(struct device *a, struct list_head *list, int (*compare)(const struct device *a, const struct device *b)) { struct klist_node *n; struct device_private *dev_prv; struct device *b; list_for_each_entry(n, list, n_node) { dev_prv = to_device_private_bus(n); b = dev_prv->device; if (compare(a, b) <= 0) { list_move_tail(&a->p->knode_bus.n_node, &b->p->knode_bus.n_node); return; } } list_move_tail(&a->p->knode_bus.n_node, list); } void bus_sort_breadthfirst(struct bus_type *bus, int (*compare)(const struct device *a, const struct device *b)) { LIST_HEAD(sorted_devices); struct klist_node *n, *tmp; struct device_private *dev_prv; struct device *dev; struct klist *device_klist; device_klist = bus_get_device_klist(bus); spin_lock(&device_klist->k_lock); list_for_each_entry_safe(n, tmp, &device_klist->k_list, n_node) { dev_prv = to_device_private_bus(n); dev = dev_prv->device; device_insertion_sort_klist(dev, &sorted_devices, compare); } list_splice(&sorted_devices, &device_klist->k_list); spin_unlock(&device_klist->k_lock); } EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); /** * subsys_dev_iter_init - initialize subsys device iterator * @iter: subsys iterator to initialize * @subsys: the subsys we wanna iterate over * @start: the device to start iterating from, if any * @type: device_type of the devices to iterate over, NULL for all * * Initialize subsys iterator @iter such that it iterates over devices * of @subsys. If @start is set, the list iteration will start there, * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; if (start) start_knode = &start->p->knode_bus; klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, start_knode); iter->type = type; } EXPORT_SYMBOL_GPL(subsys_dev_iter_init); /** * subsys_dev_iter_next - iterate to the next device * @iter: subsys iterator to proceed * * Proceed @iter to the next device and return it. Returns NULL if * iteration is complete. * * The returned device is referenced and won't be released till * iterator is proceed to the next device or exited. The caller is * free to do whatever it wants to do with the device including * calling back into subsys code. */ struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter) { struct klist_node *knode; struct device *dev; for (;;) { knode = klist_next(&iter->ki); if (!knode) return NULL; dev = to_device_private_bus(knode)->device; if (!iter->type || iter->type == dev->type) return dev; } } EXPORT_SYMBOL_GPL(subsys_dev_iter_next); /** * subsys_dev_iter_exit - finish iteration * @iter: subsys iterator to finish * * Finish an iteration. Always call this function after iteration is * complete whether the iteration ran till the end or not. */ void subsys_dev_iter_exit(struct subsys_dev_iter *iter) { klist_iter_exit(&iter->ki); } EXPORT_SYMBOL_GPL(subsys_dev_iter_exit); int subsys_interface_register(struct subsys_interface *sif) { struct bus_type *subsys; struct subsys_dev_iter iter; struct device *dev; if (!sif || !sif->subsys) return -ENODEV; subsys = bus_get(sif->subsys); if (!subsys) return -EINVAL; mutex_lock(&subsys->p->mutex); list_add_tail(&sif->node, &subsys->p->interfaces); if (sif->add_dev) { subsys_dev_iter_init(&iter, subsys, NULL, NULL); while ((dev = subsys_dev_iter_next(&iter))) sif->add_dev(dev, sif); subsys_dev_iter_exit(&iter); } mutex_unlock(&subsys->p->mutex); return 0; } EXPORT_SYMBOL_GPL(subsys_interface_register); void subsys_interface_unregister(struct subsys_interface *sif) { struct bus_type *subsys; struct subsys_dev_iter iter; struct device *dev; if (!sif || !sif->subsys) return; subsys = sif->subsys; mutex_lock(&subsys->p->mutex); list_del_init(&sif->node); if (sif->remove_dev) { subsys_dev_iter_init(&iter, subsys, NULL, NULL); while ((dev = subsys_dev_iter_next(&iter))) sif->remove_dev(dev, sif); subsys_dev_iter_exit(&iter); } mutex_unlock(&subsys->p->mutex); bus_put(subsys); } EXPORT_SYMBOL_GPL(subsys_interface_unregister); static void system_root_device_release(struct device *dev) { kfree(dev); } static int subsys_register(struct bus_type *subsys, const struct attribute_group **groups, struct kobject *parent_of_root) { struct device *dev; int err; err = bus_register(subsys); if (err < 0) return err; dev = kzalloc(sizeof(struct device), GFP_KERNEL); if (!dev) { err = -ENOMEM; goto err_dev; } err = dev_set_name(dev, "%s", subsys->name); if (err < 0) goto err_name; dev->kobj.parent = parent_of_root; dev->groups = groups; dev->release = system_root_device_release; err = device_register(dev); if (err < 0) goto err_dev_reg; subsys->dev_root = dev; return 0; err_dev_reg: put_device(dev); dev = NULL; err_name: kfree(dev); err_dev: bus_unregister(subsys); return err; } /** * subsys_system_register - register a subsystem at /sys/devices/system/ * @subsys: system subsystem * @groups: default attributes for the root device * * All 'system' subsystems have a /sys/devices/system/<name> root device * with the name of the subsystem. The root device can carry subsystem- * wide attributes. All registered devices are below this single root * device and are named after the subsystem with a simple enumeration * number appended. The registered devices are not explicitly named; * only 'id' in the device needs to be set. * * Do not use this interface for anything new, it exists for compatibility * with bad ideas only. New subsystems should use plain subsystems; and * add the subsystem-wide attributes should be added to the subsystem * directory itself and not some create fake root-device placed in * /sys/devices/system/<name>. */ int subsys_system_register(struct bus_type *subsys, const struct attribute_group **groups) { return subsys_register(subsys, groups, &system_kset->kobj); } EXPORT_SYMBOL_GPL(subsys_system_register); /** * subsys_virtual_register - register a subsystem at /sys/devices/virtual/ * @subsys: virtual subsystem * @groups: default attributes for the root device * * All 'virtual' subsystems have a /sys/devices/system/<name> root device * with the name of the subystem. The root device can carry subsystem-wide * attributes. All registered devices are below this single root device. * There's no restriction on device naming. This is for kernel software * constructs which need sysfs interface. */ int subsys_virtual_register(struct bus_type *subsys, const struct attribute_group **groups) { struct kobject *virtual_dir; virtual_dir = virtual_device_parent(NULL); if (!virtual_dir) return -ENOMEM; return subsys_register(subsys, groups, virtual_dir); } EXPORT_SYMBOL_GPL(subsys_virtual_register); int __init buses_init(void) { bus_kset = kset_create_and_add("bus", &bus_uevent_ops, NULL); if (!bus_kset) return -ENOMEM; system_kset = kset_create_and_add("system", NULL, &devices_kset->kobj); if (!system_kset) return -ENOMEM; return 0; } |
| 890 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 | // 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> extern unsigned int nf_conntrack_net_id; static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL __printf(5, 6) void nf_l4proto_log_invalid(const struct sk_buff *skb, struct net *net, u16 pf, u8 protonum, const char *fmt, ...) { 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, pf, 0, skb, NULL, NULL, NULL, "nf_ct_proto_%d: %pV ", protonum, &vaf); va_end(args); } EXPORT_SYMBOL_GPL(nf_l4proto_log_invalid); __printf(3, 4) void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, 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, net, nf_ct_l3num(ct), 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); unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { const struct nf_conn_help *help; help = nfct_help(ct); if (help) { const struct nf_conntrack_helper *helper; int ret; /* rcu_read_lock()ed by nf_hook_thresh */ helper = rcu_dereference(help->helper); if (helper) { ret = helper->help(skb, protoff, ct, ctinfo); if (ret != NF_ACCEPT) return ret; } } if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb)) { if (!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_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) return nf_conntrack_confirm(skb); return nf_confirm(skb, skb_network_offset(skb) + ip_hdrlen(skb), ct, ctinfo); } 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 = ipv4_confirm, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, { .hook = ipv4_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) { pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n"); return -ENOPROTOOPT; } if ((unsigned int)*len < sizeof(struct sockaddr_in)) { pr_debug("SO_ORIGINAL_DST: len %d not %zu\n", *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)); pr_debug("SO_ORIGINAL_DST: %pI4 %u\n", &sin.sin_addr.s_addr, ntohs(sin.sin_port)); nf_ct_put(ct); if (copy_to_user(user, &sin, sizeof(sin)) != 0) return -EFAULT; else return 0; } pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n", &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port), &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port)); 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) { pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); 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_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned char pnum = ipv6_hdr(skb)->nexthdr; __be16 frag_off; int protoff; ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) return nf_conntrack_confirm(skb); protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("proto header not found\n"); return nf_conntrack_confirm(skb); } return nf_confirm(skb, protoff, ct, ctinfo); } 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 = ipv6_confirm, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, { .hook = ipv6_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 = net_generic(net, nf_conntrack_net_id); 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) nf_ct_iterate_cleanup_net(net, nf_ct_tcp_fixup, (void *)(unsigned long)nfproto, 0, 0); return err; } static void nf_ct_netns_do_put(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); 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)); 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)); 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); /* fall through */ 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 } void nf_conntrack_proto_pernet_fini(struct net *net) { #ifdef CONFIG_NF_CT_PROTO_GRE nf_ct_gre_keymap_flush(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"); |
| 1353 703 2034 4 1353 1354 6 6 1347 1348 703 1348 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BLK_CGROUP_H #define _BLK_CGROUP_H /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> */ #include <linux/cgroup.h> #include <linux/percpu_counter.h> #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> #include <linux/atomic.h> #include <linux/kthread.h> #include <linux/fs.h> #ifndef __GENKSYMS__ #include <linux/blkdev.h> #endif /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX #ifdef CONFIG_BLK_CGROUP enum blkg_rwstat_type { BLKG_RWSTAT_READ, BLKG_RWSTAT_WRITE, BLKG_RWSTAT_SYNC, BLKG_RWSTAT_ASYNC, BLKG_RWSTAT_DISCARD, BLKG_RWSTAT_NR, BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, }; struct blkcg_gq; struct blkcg { struct cgroup_subsys_state css; spinlock_t lock; struct radix_tree_root blkg_tree; struct blkcg_gq __rcu *blkg_hint; struct hlist_head blkg_list; struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; refcount_t cgwb_refcnt; #endif }; /* * blkg_[rw]stat->aux_cnt is excluded for local stats but included for * recursive. Used to carry stats of dead children. */ struct blkg_rwstat { struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; atomic64_t aux_cnt[BLKG_RWSTAT_NR]; }; struct blkg_rwstat_sample { u64 cnt[BLKG_RWSTAT_NR]; }; /* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q). This is used by blkcg policies which need to track * information per blkcg - q pair. * * There can be multiple active blkcg policies and each blkg:policy pair is * represented by a blkg_policy_data which is allocated and freed by each * policy's pd_alloc/free_fn() methods. A policy can allocate private data * area by allocating larger data structure which embeds blkg_policy_data * at the beginning. */ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; }; /* * Policies that need to keep per-blkcg data which is independent from any * request_queue associated to it should implement cpd_alloc/free_fn() * methods. A policy can allocate private data area by allocating larger * data structure which embeds blkcg_policy_data at the beginning. * cpd_init() is invoked to let each policy handle per-blkcg data. */ struct blkcg_policy_data { /* the blkcg and policy id this per-policy data belongs to */ struct blkcg *blkcg; int plid; }; /* association between a blk cgroup and a request queue */ struct blkcg_gq { /* Pointer to the associated request_queue */ struct request_queue *q; struct list_head q_node; struct hlist_node blkcg_node; struct blkcg *blkcg; /* * Each blkg gets congested separately and the congestion state is * propagated to the matching bdi_writeback_congested. */ struct bdi_writeback_congested *wb_congested; /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; /* reference count */ struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; struct blkg_rwstat stat_bytes; struct blkg_rwstat stat_ios; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; spinlock_t async_bio_lock; struct bio_list async_bios; struct work_struct async_bio_work; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; struct rcu_head rcu_head; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg); typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf, size_t size); struct blkcg_policy { int plid; /* cgroup files for the policy */ struct cftype *dfl_cftypes; struct cftype *legacy_cftypes; /* operations */ blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; blkcg_pol_init_cpd_fn *cpd_init_fn; blkcg_pol_free_cpd_fn *cpd_free_fn; blkcg_pol_bind_cpd_fn *cpd_bind_fn; blkcg_pol_alloc_pd_fn *pd_alloc_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; blkcg_pol_stat_pd_fn *pd_stat_fn; }; extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); void blkcg_drain_queue(struct request_queue *q); void blkcg_exit_queue(struct request_queue *q); /* Blkio controller policy registration */ int blkcg_policy_register(struct blkcg_policy *pol); void blkcg_policy_unregister(struct blkcg_policy *pol); int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol); void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol); static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, unsigned int idx) { return atomic64_read(&rwstat->aux_cnt[idx]) + percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); } const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, const struct blkg_rwstat_sample *rwstat); u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, int off); int blkg_print_stat_bytes(struct seq_file *sf, void *v); int blkg_print_stat_ios(struct seq_file *sf, void *v); int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v); int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v); void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, int off, struct blkg_rwstat_sample *sum); struct blkg_conf_ctx { struct gendisk *disk; struct blkcg_gq *blkg; char *body; }; struct gendisk *blkcg_conf_get_disk(char **inputp); int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static inline struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } /** * __bio_blkcg - internal, inconsistent version to get blkcg * * DO NOT USE. * This function is inconsistent and consequently is dangerous to use. The * first part of the function returns a blkcg where a reference is owned by the * bio. This means it does not need to be rcu protected as it cannot go away * with the bio owning a reference to it. However, the latter potentially gets * it from task_css(). This can race against task migration and the cgroup * dying. It is also semantically different as it must be called rcu protected * and is susceptible to failure when trying to get a reference to it. * Therefore, it is not ok to assume that *_get() will always succeed on the * blkcg returned here. */ static inline struct blkcg *__bio_blkcg(struct bio *bio) { if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return css_to_blkcg(blkcg_css()); } /** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio * * This returns the blkcg associated with a bio, %NULL if not associated. * Callers are expected to either handle %NULL or know association has been * done prior to calling this. */ static inline struct blkcg *bio_blkcg(struct bio *bio) { if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return NULL; } static inline bool blk_cgroup_congested(void) { struct cgroup_subsys_state *css; bool ret = false; rcu_read_lock(); css = kthread_blkcg(); if (!css) css = task_css(current, io_cgrp_id); while (css) { if (atomic_read(&css->cgroup->congestion_count)) { ret = true; break; } css = css->parent; } rcu_read_unlock(); return ret; } /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning * blkg. The idea is we do bio_blkcg() to look up the actual context for the * bio and attach the appropriate blkg to the bio. Then we call this helper and * if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */ static inline bool bio_issue_as_root_blkg(struct bio *bio) { return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; } /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * __blkg_lookup - internal version of blkg_lookup() * @blkcg: blkcg of interest * @q: request_queue of interest * @update_hint: whether to update lookup hint with the result or not * * This is internal version and shouldn't be used by policy * implementations. Looks up blkgs for the @blkcg - @q pair regardless of * @q's bypass state. If @update_hint is %true, the caller should be * holding @q->queue_lock and lookup hint is updated on success. */ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, bool update_hint) { struct blkcg_gq *blkg; if (blkcg == &blkcg_root) return q->root_blkg; blkg = rcu_dereference(blkcg->blkg_hint); if (blkg && blkg->q == q) return blkg; return blkg_lookup_slowpath(blkcg, q, update_hint); } /** * blkg_lookup - lookup blkg for the specified blkcg - q pair * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. This function should be called * under RCU read lock. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); return __blkg_lookup(blkcg, q, false); } /** * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair * @q: request_queue of interest * * Lookup blkg for @q at the root level. See also blkg_lookup(). */ static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { return q->root_blkg; } /** * blkg_to_pdata - get policy private data * @blkg: blkg of interest * @pol: policy of interest * * Return pointer to private data associated with the @blkg-@pol pair. */ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return blkg ? blkg->pd[pol->plid] : NULL; } static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, struct blkcg_policy *pol) { return blkcg ? blkcg->cpd[pol->plid] : NULL; } /** * pdata_to_blkg - get blkg associated with policy private data * @pd: policy private data of interest * * @pd is policy private data. Determine the blkg it's associated with. */ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return pd ? pd->blkg : NULL; } static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) { return cpd ? cpd->blkcg : NULL; } extern void blkcg_destroy_blkgs(struct blkcg *blkcg); #ifdef CONFIG_CGROUP_WRITEBACK /** * blkcg_cgwb_get - get a reference for blkcg->cgwb_list * @blkcg: blkcg of interest * * This is used to track the number of active wb's related to a blkcg. */ static inline void blkcg_cgwb_get(struct blkcg *blkcg) { refcount_inc(&blkcg->cgwb_refcnt); } /** * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list * @blkcg: blkcg of interest * * This is used to track the number of active wb's related to a blkcg. * When this count goes to zero, all active wb has finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. */ static inline void blkcg_cgwb_put(struct blkcg *blkcg) { if (refcount_dec_and_test(&blkcg->cgwb_refcnt)) blkcg_destroy_blkgs(blkcg); } #else static inline void blkcg_cgwb_get(struct blkcg *blkcg) { } static inline void blkcg_cgwb_put(struct blkcg *blkcg) { /* wb isn't being accounted, so trigger destruction right away */ blkcg_destroy_blkgs(blkcg); } #endif /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest * @buf: target buffer * @buflen: target buffer length * * Format the path of the cgroup of @blkg into @buf. */ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) { return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); } /** * blkg_get - get a blkg reference * @blkg: blkg to get * * The caller should be holding an existing reference. */ static inline void blkg_get(struct blkcg_gq *blkg) { percpu_ref_get(&blkg->refcnt); } /** * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ static inline bool blkg_tryget(struct blkcg_gq *blkg) { return blkg && percpu_ref_tryget(&blkg->refcnt); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @blkg: blkg to get * * This needs to be called rcu protected. As the failure mode here is to walk * up the blkg tree, this ensure that the blkg->parent pointers are always * valid. This returns the blkg that it ended up taking a reference on or %NULL * if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) { struct blkcg_gq *ret_blkg = NULL; WARN_ON_ONCE(!rcu_read_lock_held()); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } return ret_blkg; } /** * blkg_put - put a blkg reference * @blkg: blkg to put */ static inline void blkg_put(struct blkcg_gq *blkg) { percpu_ref_put(&blkg->refcnt); } /** * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU * read locked. If called under either blkcg or queue lock, the iteration * is guaranteed to include all and only online blkgs. The caller may * update @pos_css by calling css_rightmost_descendant() to skip subtree. * @p_blkg is included in the iteration and the first node to be visited. */ #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) /** * blkg_for_each_descendant_post - post-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Similar to blkg_for_each_descendant_pre() but performs post-order * traversal instead. Synchronization rules are the same. @p_blkg is * included in the iteration and the last node to be visited. */ #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) { int i, ret; for (i = 0; i < BLKG_RWSTAT_NR; i++) { ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); if (ret) { while (--i >= 0) percpu_counter_destroy(&rwstat->cpu_cnt[i]); return ret; } atomic64_set(&rwstat->aux_cnt[i], 0); } return 0; } static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) { int i; for (i = 0; i < BLKG_RWSTAT_NR; i++) percpu_counter_destroy(&rwstat->cpu_cnt[i]); } /** * blkg_rwstat_add - add a value to a blkg_rwstat * @rwstat: target blkg_rwstat * @op: REQ_OP and flags * @val: value to add * * Add @val to @rwstat. The counters are chosen according to @rw. The * caller is responsible for synchronizing calls to this function. */ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, unsigned int op, uint64_t val) { struct percpu_counter *cnt; if (op_is_discard(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; else if (op_is_write(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); if (op_is_sync(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); } /** * blkg_rwstat_read - read the current values of a blkg_rwstat * @rwstat: blkg_rwstat to read * * Read the current snapshot of @rwstat and return it in the aux counts. */ static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, struct blkg_rwstat_sample *result) { int i; for (i = 0; i < BLKG_RWSTAT_NR; i++) result->cnt[i] = percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); } /** * blkg_rwstat_total - read the total count of a blkg_rwstat * @rwstat: blkg_rwstat to read * * Return the total count of @rwstat regardless of the IO direction. This * function can be called without synchronization and takes care of u64 * atomicity. */ static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) { struct blkg_rwstat_sample tmp = { }; blkg_rwstat_read(rwstat, &tmp); return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; } /** * blkg_rwstat_reset - reset a blkg_rwstat * @rwstat: blkg_rwstat to reset */ static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) { int i; for (i = 0; i < BLKG_RWSTAT_NR; i++) { percpu_counter_set(&rwstat->cpu_cnt[i], 0); atomic64_set(&rwstat->aux_cnt[i], 0); } } /** * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count * @to: the destination blkg_rwstat * @from: the source * * Add @from's count including the aux one to @to's aux count. */ static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, struct blkg_rwstat *from) { u64 sum[BLKG_RWSTAT_NR]; int i; for (i = 0; i < BLKG_RWSTAT_NR; i++) sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); for (i = 0; i < BLKG_RWSTAT_NR; i++) atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]), &to->aux_cnt[i]); } #ifdef CONFIG_BLK_DEV_THROTTLING extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio); #else static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio) { return false; } #endif bool __blkcg_punt_bio_submit(struct bio *bio); static inline bool blkcg_punt_bio_submit(struct bio *bio) { if (bio->bi_opf & REQ_CGROUP_PUNT) return __blkcg_punt_bio_submit(bio); else return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { bio_issue_init(&bio->bi_issue, bio_sectors(bio)); } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); if (!bio->bi_blkg) { char b[BDEVNAME_SIZE]; WARN_ONCE(1, "no blkg associated for bio on block-device: %s\n", bio_devname(bio, b)); bio_associate_blkg(bio); } blkg = bio->bi_blkg; throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the * size of the bio. */ if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, bio->bi_iter.bi_size); blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } blkcg_bio_issue_init(bio); rcu_read_unlock(); return !throtl; } static inline void blkcg_use_delay(struct blkcg_gq *blkg) { if (atomic_add_return(1, &blkg->use_delay) == 1) atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); } /** * blk_cgroup_mergeable - Determine whether to allow or disallow merges * @rq: request to merge into * @bio: bio to merge * * @bio and @rq should belong to the same cgroup and their issue_as_root should * match. The latter is necessary as we don't want to throttle e.g. a metadata * update because it happens to be next to a regular IO. */ static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return rq->bio->bi_blkg == bio->bi_blkg && bio_issue_as_root_blkg(rq->bio) == bio_issue_as_root_blkg(bio); } static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); if (old == 0) return 0; /* * We do this song and dance because we can race with somebody else * adding or removing delay. If we just did an atomic_dec we'd end up * negative and we'd already be in trouble. We need to subtract 1 and * then check to see if we were the last delay so we can drop the * congestion count on the cgroup. */ while (old) { int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); if (cur == old) break; old = cur; } if (old == 0) return 0; if (old == 1) atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); return 1; } static inline void blkcg_clear_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); if (!old) return; /* We only want 1 person clearing the congestion count for this blkg. */ while (old) { int cur = atomic_cmpxchg(&blkg->use_delay, old, 0); if (cur == old) { atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); break; } old = cur; } } void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); #else /* CONFIG_BLK_CGROUP */ struct blkcg { }; struct blkg_policy_data { }; struct blkcg_policy_data { }; struct blkcg_gq { }; struct blkcg_policy { }; #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } #ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } static inline void blkcg_exit_queue(struct request_queue *q) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } static inline int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol) { return 0; } static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return NULL; } static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return true; } #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) #endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ #endif /* _BLK_CGROUP_H */ |
| 86 59 22 11 18 9 16 21 14 22 16 15 9 14 33 32 37 1 2 1 16 18 7 1 6 9 5 3 32 1 6 26 17 7 6 1 1 1 5 21 1 2 1 1 14 2 6 6 40 1 12 15 22 10 5 3 3 6 30 8 6 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Longest prefix match list implementation * * Copyright (c) 2016,2017 Daniel Mack * Copyright (c) 2016 David Herrmann */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <net/ipv6.h> #include <uapi/linux/btf.h> /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) struct lpm_trie_node; struct lpm_trie_node { struct rcu_head rcu; struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; u8 data[0]; }; struct lpm_trie { struct bpf_map map; struct lpm_trie_node __rcu *root; size_t n_entries; size_t max_prefixlen; size_t data_size; raw_spinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to * match IP addresses to a stored set of ranges. * * Data stored in @data of struct bpf_lpm_key and struct lpm_trie_node is * interpreted as big endian, so data[0] stores the most significant byte. * * Match ranges are internally stored in instances of struct lpm_trie_node * which each contain their prefix length as well as two pointers that may * lead to more nodes containing more specific matches. Each node also stores * a value that is defined by and returned to userspace via the update_elem * and lookup functions. * * For instance, let's start with a trie that was created with a prefix length * of 32, so it can be used for IPv4 addresses, and one single element that * matches 192.168.0.0/16. The data array would hence contain * [0xc0, 0xa8, 0x00, 0x00] in big-endian notation. This documentation will * stick to IP-address notation for readability though. * * As the trie is empty initially, the new node (1) will be places as root * node, denoted as (R) in the example below. As there are no other node, both * child pointers are %NULL. * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * * Next, let's add a new node (2) matching 192.168.0.0/24. As there is already * a node with the same data and a smaller prefix (ie, a less specific one), * node (2) will become a child of (1). In child index depends on the next bit * that is outside of what (1) matches, and that bit is 0, so (2) will be * child[0] of (1): * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | * +----------------+ * | (2) | * | 192.168.0.0/24 | * | value: 2 | * | [0] [1] | * +----------------+ * * The child[1] slot of (1) could be filled with another node which has bit #17 * (the next bit after the ones that (1) matches on) set to 1. For instance, * 192.168.128.0/24: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (2) | | (3) | * | 192.168.0.0/24 | | 192.168.128.0/24 | * | value: 2 | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * * Let's add another node (4) to the game for 192.168.1.0/24. In order to place * it, node (1) is looked at first, and because (4) of the semantics laid out * above (bit #17 is 0), it would normally be attached to (1) as child[0]. * However, that slot is already allocated, so a new node is needed in between. * That node does not have a value attached to it and it will never be * returned to users as result of a lookup. It is only there to differentiate * the traversal further. It will get a prefix as wide as necessary to * distinguish its two children: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (4) (I) | | (3) | * | 192.168.0.0/23 | | 192.168.128.0/24 | * | value: --- | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * | | * +----------------+ +----------------+ * | (2) | | (5) | * | 192.168.0.0/24 | | 192.168.1.0/24 | * | value: 2 | | value: 5 | * | [0] [1] | | [0] [1] | * +----------------+ +----------------+ * * 192.168.1.1/32 would be a child of (5) etc. * * An intermediate node will be turned into a 'real' node on demand. In the * example above, (4) would be re-used if 192.168.0.0/23 is added to the trie. * * A fully populated trie would have a height of 32 nodes, as the trie was * created with a prefix length of 32. * * The lookup starts at the root node. If the current node matches and if there * is a child that can be used to become more specific, the trie is traversed * downwards. The last node in the traversal that is a non-intermediate one is * returned. */ static inline int extract_bit(const u8 *data, size_t index) { return !!(data[index / 8] & (1 << (7 - (index % 8)))); } /** * longest_prefix_match() - determine the longest prefix * @trie: The trie to get internal sizes from * @node: The node to operate on * @key: The key to compare to @node * * Determine the longest prefix of @node that matches the bits in @key. */ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, const struct bpf_lpm_trie_key *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) /* data_size >= 16 has very small probability. * We do not use a loop for optimal code generation. */ if (trie->data_size >= 8) { u64 diff = be64_to_cpu(*(__be64 *)node->data ^ *(__be64 *)key->data); prefixlen = 64 - fls64(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i = 8; } #endif while (trie->data_size >= i + 4) { u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^ *(__be32 *)&key->data[i]); prefixlen += 32 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 4; } if (trie->data_size >= i + 2) { u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^ *(__be16 *)&key->data[i]); prefixlen += 16 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 2; } if (trie->data_size >= i + 1) { prefixlen += 8 - fls(node->data[i] ^ key->data[i]); if (prefixlen >= limit) return limit; } return prefixlen; } /* Called from syscall or from eBPF program */ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; struct bpf_lpm_trie_key *key = _key; /* Start walking the trie from the root node ... */ for (node = rcu_dereference(trie->root); node;) { unsigned int next_bit; size_t matchlen; /* Determine the longest prefix of @node that matches @key. * If it's the maximum possible prefix for this trie, we have * an exact match and can return it directly. */ matchlen = longest_prefix_match(trie, node, key); if (matchlen == trie->max_prefixlen) { found = node; break; } /* If the number of bits that match is smaller than the prefix * length of @node, bail out and return the node we have seen * last in the traversal (ie, the parent). */ if (matchlen < node->prefixlen) break; /* Consider this node as return candidate unless it is an * artificially added intermediate one. */ if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) found = node; /* If the node match is fully satisfied, let's see if we can * become more specific. Determine the next bit in the key and * traverse down. */ next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } if (!found) return NULL; return found->data + trie->data_size; } static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, const void *value) { struct lpm_trie_node *node; size_t size = sizeof(struct lpm_trie_node) + trie->data_size; if (value) size += trie->map.value_size; node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, trie->map.numa_node); if (!node) return NULL; node->flags = 0; if (value) memcpy(node->data + trie->data_size, value, trie->map.value_size); return node; } /* Called from syscall or from eBPF program */ static int trie_update_elem(struct bpf_map *map, void *_key, void *value, u64 flags) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (unlikely(flags > BPF_EXIST)) return -EINVAL; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; raw_spin_lock_irqsave(&trie->lock, irq_flags); /* Allocate and fill a new node */ if (trie->n_entries == trie->map.max_entries) { ret = -ENOSPC; goto out; } new_node = lpm_trie_node_alloc(trie, value); if (!new_node) { ret = -ENOMEM; goto out; } trie->n_entries++; new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); RCU_INIT_POINTER(new_node->child[1], NULL); memcpy(new_node->data, key->data, trie->data_size); /* Now find a slot to attach the new node. To do that, walk the tree * from the root and match as many bits as possible for each node until * we either find an empty slot or a slot that needs to be replaced by * an intermediate node. */ slot = &trie->root; while ((node = rcu_dereference_protected(*slot, lockdep_is_held(&trie->lock)))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen || node->prefixlen == trie->max_prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); slot = &node->child[next_bit]; } /* If the slot is empty (a free child pointer or an empty root), * simply assign the @new_node to that slot and be done. */ if (!node) { rcu_assign_pointer(*slot, new_node); goto out; } /* If the slot we picked already exists, replace it with @new_node * which already has the correct data array set. */ if (node->prefixlen == matchlen) { new_node->child[0] = node->child[0]; new_node->child[1] = node->child[1]; if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) trie->n_entries--; rcu_assign_pointer(*slot, new_node); kfree_rcu(node, rcu); goto out; } /* If the new node matches the prefix completely, it must be inserted * as an ancestor. Simply insert it between @node and *@slot. */ if (matchlen == key->prefixlen) { next_bit = extract_bit(node->data, matchlen); rcu_assign_pointer(new_node->child[next_bit], node); rcu_assign_pointer(*slot, new_node); goto out; } im_node = lpm_trie_node_alloc(trie, NULL); if (!im_node) { ret = -ENOMEM; goto out; } im_node->prefixlen = matchlen; im_node->flags |= LPM_TREE_NODE_FLAG_IM; memcpy(im_node->data, node->data, trie->data_size); /* Now determine which child to install in which slot */ if (extract_bit(key->data, matchlen)) { rcu_assign_pointer(im_node->child[0], node); rcu_assign_pointer(im_node->child[1], new_node); } else { rcu_assign_pointer(im_node->child[0], new_node); rcu_assign_pointer(im_node->child[1], node); } /* Finally, assign the intermediate node to the determined spot */ rcu_assign_pointer(*slot, im_node); out: if (ret) { if (new_node) trie->n_entries--; kfree(new_node); kfree(im_node); } raw_spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } /* Called from syscall or from eBPF program */ static int trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; raw_spin_lock_irqsave(&trie->lock, irq_flags); /* Walk the tree looking for an exact key/length match and keeping * track of the path we traverse. We will need to know the node * we wish to delete, and the slot that points to the node we want * to delete. We may also need to know the nodes parent and the * slot that contains it. */ trim = &trie->root; trim2 = trim; parent = NULL; while ((node = rcu_dereference_protected( *trim, lockdep_is_held(&trie->lock)))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; parent = node; trim2 = trim; next_bit = extract_bit(key->data, node->prefixlen); trim = &node->child[next_bit]; } if (!node || node->prefixlen != key->prefixlen || node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; } trie->n_entries--; /* If the node we are removing has two children, simply mark it * as intermediate and we are done. */ if (rcu_access_pointer(node->child[0]) && rcu_access_pointer(node->child[1])) { node->flags |= LPM_TREE_NODE_FLAG_IM; goto out; } /* If the parent of the node we are about to delete is an intermediate * node, and the deleted node doesn't have any children, we can delete * the intermediate parent as well and promote its other child * up the tree. Doing this maintains the invariant that all * intermediate nodes have exactly 2 children and that there are no * unnecessary intermediate nodes in the tree. */ if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) && !node->child[0] && !node->child[1]) { if (node == rcu_access_pointer(parent->child[0])) rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[1])); else rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[0])); kfree_rcu(parent, rcu); kfree_rcu(node, rcu); goto out; } /* The node we are removing has either zero or one child. If there * is a child, move it into the removed node's slot then delete * the node. Otherwise just clear the slot and delete the node. */ if (node->child[0]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0])); else if (node->child[1]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); else RCU_INIT_POINTER(*trim, NULL); kfree_rcu(node, rcu); out: raw_spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } #define LPM_DATA_SIZE_MAX 256 #define LPM_DATA_SIZE_MIN 1 #define LPM_VAL_SIZE_MAX (KMALLOC_MAX_SIZE - LPM_DATA_SIZE_MAX - \ sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 #define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) #define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK) static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; u64 cost = sizeof(*trie), cost_per_node; int ret; if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); /* check sanity of attributes */ if (attr->max_entries == 0 || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->map_flags & ~LPM_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || attr->value_size > LPM_VAL_SIZE_MAX) return ERR_PTR(-EINVAL); trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN); if (!trie) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; cost_per_node = sizeof(struct lpm_trie_node) + attr->value_size + trie->data_size; cost += (u64) attr->max_entries * cost_per_node; ret = bpf_map_charge_init(&trie->map.memory, cost); if (ret) goto out_err; raw_spin_lock_init(&trie->lock); return &trie->map; out_err: kfree(trie); return ERR_PTR(ret); } static void trie_free(struct bpf_map *map) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; /* Wait for outstanding programs to complete * update/lookup/delete/get_next_key and free the trie. */ synchronize_rcu(); /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent * and start over. */ for (;;) { slot = &trie->root; for (;;) { node = rcu_dereference_protected(*slot, 1); if (!node) goto out; if (rcu_access_pointer(node->child[0])) { slot = &node->child[0]; continue; } if (rcu_access_pointer(node->child[1])) { slot = &node->child[1]; continue; } kfree(node); RCU_INIT_POINTER(*slot, NULL); break; } } out: kfree(trie); } static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; size_t matchlen; /* The get_next_key follows postorder. For the 4 node example in * the top of this file, the trie_get_next_key() returns the following * one after another: * 192.168.0.0/24 * 192.168.1.0/24 * 192.168.128.0/24 * 192.168.0.0/16 * * The idea is to return more specific keys before less specific ones. */ /* Empty trie */ search_root = rcu_dereference(trie->root); if (!search_root) return -ENOENT; /* For invalid key, find the leftmost node in the trie */ if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; node_stack = kmalloc_array(trie->max_prefixlen, sizeof(struct lpm_trie_node *), GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) return -ENOMEM; /* Try to find the exact node for the given key */ for (node = search_root; node;) { node_stack[++stack_ptr] = node; matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } if (!node || node->prefixlen != key->prefixlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) goto find_leftmost; /* The node with the exactly-matching key has been found, * find the first node in postorder after the matched node. */ node = node_stack[stack_ptr]; while (stack_ptr > 0) { parent = node_stack[stack_ptr - 1]; if (rcu_dereference(parent->child[0]) == node) { search_root = rcu_dereference(parent->child[1]); if (search_root) goto find_leftmost; } if (!(parent->flags & LPM_TREE_NODE_FLAG_IM)) { next_node = parent; goto do_copy; } node = parent; stack_ptr--; } /* did not find anything */ err = -ENOENT; goto free_stack; find_leftmost: /* Find the leftmost non-intermediate node, all intermediate nodes * have exact two children, so this function will never return NULL. */ for (node = search_root; node;) { if (node->flags & LPM_TREE_NODE_FLAG_IM) { node = rcu_dereference(node->child[0]); } else { next_node = node; node = rcu_dereference(node->child[0]); if (!node) node = rcu_dereference(next_node->child[1]); } } do_copy: next_key->prefixlen = next_node->prefixlen; memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); return err; } static int trie_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { /* Keys must have struct bpf_lpm_trie_key embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } const struct bpf_map_ops trie_map_ops = { .map_alloc = trie_alloc, .map_free = trie_free, .map_get_next_key = trie_get_next_key, .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, .map_check_btf = trie_check_btf, }; |
| 84 84 5 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | #include <linux/dcache.h> #include "internal.h" unsigned name_to_int(const struct qstr *qstr) { const char *name = qstr->name; int len = qstr->len; unsigned n = 0; if (len > 1 && *name == '0') goto out; do { unsigned c = *name++ - '0'; if (c > 9) goto out; if (n >= (~0U-9)/10) goto out; n *= 10; n += c; } while (--len > 0); return n; out: return ~0U; } |
| 258 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: LGPL-2.1 /* * Copyright (c) 2012 Taobao. * Written by Tao Ma <boyu.mt@taobao.com> */ #include <linux/iomap.h> #include <linux/fiemap.h> #include <linux/iversion.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "truncate.h" #include <trace/events/android_fs.h> #define EXT4_XATTR_SYSTEM_DATA "data" #define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) #define EXT4_INLINE_DOTDOT_OFFSET 2 #define EXT4_INLINE_DOTDOT_SIZE 4 static int ext4_get_inline_size(struct inode *inode) { if (EXT4_I(inode)->i_inline_off) return EXT4_I(inode)->i_inline_size; return 0; } static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_iloc *iloc) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; void *end; int free, min_offs; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; min_offs = EXT4_SB(inode->i_sb)->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - EXT4_I(inode)->i_extra_isize - sizeof(struct ext4_xattr_ibody_header); /* * We need to subtract another sizeof(__u32) since an in-inode xattr * needs an empty 4 bytes to indicate the gap between the xattr entry * and the name/value pair. */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return EXT4_XATTR_SIZE(min_offs - EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)) - EXT4_XATTR_ROUND - sizeof(__u32)); raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; /* Compute min_offs. */ while (!IS_LAST_ENTRY(entry)) { void *next = EXT4_XATTR_NEXT(entry); if (next >= end) { EXT4_ERROR_INODE(inode, "corrupt xattr in inline inode"); return 0; } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); if (EXT4_I(inode)->i_inline_off) { entry = (struct ext4_xattr_entry *) ((void *)raw_inode + EXT4_I(inode)->i_inline_off); free += EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)); goto out; } free -= EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)); if (free > EXT4_XATTR_ROUND) free = EXT4_XATTR_SIZE(free - EXT4_XATTR_ROUND); else free = 0; out: return free; } /* * Get the maximum size we now can store in an inode. * If we can't find the space for a xattr entry, don't use the space * of the extents since we have no space to indicate the inline data. */ int ext4_get_max_inline_size(struct inode *inode) { int error, max_inline_size; struct ext4_iloc iloc; if (EXT4_I(inode)->i_extra_isize == 0) return 0; error = ext4_get_inode_loc(inode, &iloc); if (error) { ext4_error_inode(inode, __func__, __LINE__, 0, "can't get inode location %lu", inode->i_ino); return 0; } down_read(&EXT4_I(inode)->xattr_sem); max_inline_size = get_max_inline_xattr_value_size(inode, &iloc); up_read(&EXT4_I(inode)->xattr_sem); brelse(iloc.bh); if (!max_inline_size) return 0; return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE; } /* * this function does not take xattr_sem, which is OK because it is * currently only used in a code path coming form ext4_iget, before * the new inode has been unlocked */ int ext4_find_inline_data_nolock(struct inode *inode) { struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; int error; if (EXT4_I(inode)->i_extra_isize == 0) return 0; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; if (!is.s.not_found) { if (is.s.here->e_value_inum) { EXT4_ERROR_INODE(inode, "inline data xattr refers " "to an external xattr inode"); error = -EFSCORRUPTED; goto out; } EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); } out: brelse(is.iloc.bh); return error; } static int ext4_read_inline_data(struct inode *inode, void *buffer, unsigned int len, struct ext4_iloc *iloc) { struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; int cp_len = 0; struct ext4_inode *raw_inode; if (!len) return 0; BUG_ON(len > EXT4_I(inode)->i_inline_size); cp_len = len < EXT4_MIN_INLINE_DATA_SIZE ? len : EXT4_MIN_INLINE_DATA_SIZE; raw_inode = ext4_raw_inode(iloc); memcpy(buffer, (void *)(raw_inode->i_block), cp_len); len -= cp_len; buffer += cp_len; if (!len) goto out; header = IHDR(inode, raw_inode); entry = (struct ext4_xattr_entry *)((void *)raw_inode + EXT4_I(inode)->i_inline_off); len = min_t(unsigned int, len, (unsigned int)le32_to_cpu(entry->e_value_size)); memcpy(buffer, (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs), len); cp_len += len; out: return cp_len; } /* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, void *buffer, loff_t pos, unsigned int len) { struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; int cp_len = 0; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return; BUG_ON(!EXT4_I(inode)->i_inline_off); BUG_ON(pos + len > EXT4_I(inode)->i_inline_size); raw_inode = ext4_raw_inode(iloc); buffer += pos; if (pos < EXT4_MIN_INLINE_DATA_SIZE) { cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ? EXT4_MIN_INLINE_DATA_SIZE - pos : len; memcpy((void *)raw_inode->i_block + pos, buffer, cp_len); len -= cp_len; buffer += cp_len; pos += cp_len; } if (!len) return; pos -= EXT4_MIN_INLINE_DATA_SIZE; header = IHDR(inode, raw_inode); entry = (struct ext4_xattr_entry *)((void *)raw_inode + EXT4_I(inode)->i_inline_off); memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos, buffer, len); } static int ext4_create_inline_data(handle_t *handle, struct inode *inode, unsigned len) { int error; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, is.iloc.bh); if (error) goto out; if (len > EXT4_MIN_INLINE_DATA_SIZE) { value = EXT4_ZERO_XATTR_VALUE; len -= EXT4_MIN_INLINE_DATA_SIZE; } else { value = ""; len = 0; } /* Insert the the xttr entry. */ i.value = value; i.value_len = len; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; BUG_ON(!is.s.not_found); error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); goto out; } memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE; ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); out: brelse(is.iloc.bh); return error; } static int ext4_update_inline_data(handle_t *handle, struct inode *inode, unsigned int len) { int error; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; /* If the old space is ok, write the data directly. */ if (len <= EXT4_I(inode)->i_inline_size) return 0; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; BUG_ON(is.s.not_found); len -= EXT4_MIN_INLINE_DATA_SIZE; value = kzalloc(len, GFP_NOFS); if (!value) { error = -ENOMEM; goto out; } error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); if (error < 0) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, is.iloc.bh); if (error) goto out; /* Update the xttr entry. */ i.value = value; i.value_len = len; error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); out: kfree(value); brelse(is.iloc.bh); return error; } static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, unsigned int len) { int ret, size, no_expand; struct ext4_inode_info *ei = EXT4_I(inode); if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) return -ENOSPC; size = ext4_get_max_inline_size(inode); if (size < len) return -ENOSPC; ext4_write_lock_xattr(inode, &no_expand); if (ei->i_inline_off) ret = ext4_update_inline_data(handle, inode, len); else ret = ext4_create_inline_data(handle, inode, len); ext4_write_unlock_xattr(inode, &no_expand); return ret; } static int ext4_destroy_inline_data_nolock(handle_t *handle, struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_xattr_ibody_find is = { .s = { .not_found = 0, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, .value = NULL, .value_len = 0, }; int error; if (!ei->i_inline_off) return 0; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, is.iloc.bh); if (error) goto out; error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE); if (ext4_has_feature_extents(inode->i_sb)) { if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode); } } ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); EXT4_I(inode)->i_inline_off = 0; EXT4_I(inode)->i_inline_size = 0; ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); out: brelse(is.iloc.bh); if (error == -ENODATA) error = 0; return error; } static int ext4_read_inline_page(struct inode *inode, struct page *page) { void *kaddr; int ret = 0; size_t len; struct ext4_iloc iloc; BUG_ON(!PageLocked(page)); BUG_ON(!ext4_has_inline_data(inode)); BUG_ON(page->index); if (!EXT4_I(inode)->i_inline_off) { ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.", inode->i_ino); goto out; } ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out; len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode)); kaddr = kmap_atomic(page); ret = ext4_read_inline_data(inode, kaddr, len, &iloc); flush_dcache_page(page); kunmap_atomic(kaddr); zero_user_segment(page, len, PAGE_SIZE); SetPageUptodate(page); brelse(iloc.bh); out: return ret; } int ext4_readpage_inline(struct inode *inode, struct page *page) { int ret = 0; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); return -EAGAIN; } if (trace_android_fs_dataread_start_enabled()) { char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; path = android_fstrace_get_pathname(pathbuf, MAX_TRACE_PATHBUF_LEN, inode); trace_android_fs_dataread_start(inode, page_offset(page), PAGE_SIZE, current->pid, path, current->comm); } /* * Current inline data can only exist in the 1st page, * So for all the other pages, just set them uptodate. */ if (!page->index) ret = ext4_read_inline_page(inode, page); else if (!PageUptodate(page)) { zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); } trace_android_fs_dataread_end(inode, page_offset(page), PAGE_SIZE); up_read(&EXT4_I(inode)->xattr_sem); unlock_page(page); return ret >= 0 ? 0 : ret; } static int ext4_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, unsigned flags) { int ret, needed_blocks, no_expand; handle_t *handle = NULL; int retries = 0, sem_held = 0; struct page *page = NULL; unsigned from, to; struct ext4_iloc iloc; if (!ext4_has_inline_data(inode)) { /* * clear the flag so that no new write * will trap here again. */ ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; } needed_blocks = ext4_writepage_trans_blocks(inode); ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; retry: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { ret = PTR_ERR(handle); handle = NULL; goto out; } /* We cannot recurse into the filesystem as the transaction is already * started */ flags |= AOP_FLAG_NOFS; page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; goto out; } ext4_write_lock_xattr(inode, &no_expand); sem_held = 1; /* If some one has already done this for us, just exit. */ if (!ext4_has_inline_data(inode)) { ret = 0; goto out; } from = 0; to = ext4_get_inline_size(inode); if (!PageUptodate(page)) { ret = ext4_read_inline_page(inode, page); if (ret < 0) goto out; } ret = ext4_destroy_inline_data_nolock(handle, inode); if (ret) goto out; if (ext4_should_dioread_nolock(inode)) { ret = __block_write_begin(page, from, to, ext4_get_block_unwritten); } else ret = __block_write_begin(page, from, to, ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); } if (ret) { unlock_page(page); put_page(page); page = NULL; ext4_orphan_add(handle, inode); ext4_write_unlock_xattr(inode, &no_expand); sem_held = 0; ext4_journal_stop(handle); handle = NULL; ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; if (page) block_commit_write(page, from, to); out: if (page) { unlock_page(page); put_page(page); } if (sem_held) ext4_write_unlock_xattr(inode, &no_expand); if (handle) ext4_journal_stop(handle); brelse(iloc.bh); return ret; } /* * Try to write data in the inode. * If the inode has inline data, check whether the new write can be * in the inode also. If not, create the page the handle, move the data * to the page make it update and let the later codes create extent for it. */ int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, unsigned flags, struct page **pagep) { int ret; handle_t *handle; struct page *page; struct ext4_iloc iloc; if (pos + len > ext4_get_max_inline_size(inode)) goto convert; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; /* * The possible write could happen in the inode, * so try to reserve the space in inode first. */ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); handle = NULL; goto out; } ret = ext4_prepare_inline_data(handle, inode, pos + len); if (ret && ret != -ENOSPC) goto out; /* We don't have space in inline inode, so convert it to extent. */ if (ret == -ENOSPC) { ext4_journal_stop(handle); brelse(iloc.bh); goto convert; } ret = ext4_journal_get_write_access(handle, iloc.bh); if (ret) goto out; flags |= AOP_FLAG_NOFS; page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; goto out; } *pagep = page; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { ret = 0; unlock_page(page); put_page(page); goto out_up_read; } if (!PageUptodate(page)) { ret = ext4_read_inline_page(inode, page); if (ret < 0) { unlock_page(page); put_page(page); goto out_up_read; } } ret = 1; handle = NULL; out_up_read: up_read(&EXT4_I(inode)->xattr_sem); out: if (handle && (ret != 1)) ext4_journal_stop(handle); brelse(iloc.bh); return ret; convert: return ext4_convert_inline_data_to_extent(mapping, inode, flags); } int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { int ret, no_expand; void *kaddr; struct ext4_iloc iloc; if (unlikely(copied < len) && !PageUptodate(page)) return 0; ret = ext4_get_inode_loc(inode, &iloc); if (ret) { ext4_std_error(inode->i_sb, ret); return ret; } ext4_write_lock_xattr(inode, &no_expand); BUG_ON(!ext4_has_inline_data(inode)); /* * ei->i_inline_off may have changed since ext4_write_begin() * called ext4_try_to_write_inline_data() */ (void) ext4_find_inline_data_nolock(inode); kaddr = kmap_atomic(page); ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); kunmap_atomic(kaddr); SetPageUptodate(page); /* clear page dirty so that writepages wouldn't work for us. */ ClearPageDirty(page); ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); mark_inode_dirty(inode); return copied; } struct buffer_head * ext4_journalled_write_inline_data(struct inode *inode, unsigned len, struct page *page) { int ret, no_expand; void *kaddr; struct ext4_iloc iloc; ret = ext4_get_inode_loc(inode, &iloc); if (ret) { ext4_std_error(inode->i_sb, ret); return NULL; } ext4_write_lock_xattr(inode, &no_expand); kaddr = kmap_atomic(page); ext4_write_inline_data(inode, &iloc, kaddr, 0, len); kunmap_atomic(kaddr); ext4_write_unlock_xattr(inode, &no_expand); return iloc.bh; } /* * Try to make the page cache and handle ready for the inline data case. * We can call this function in 2 cases: * 1. The inode is created and the first write exceeds inline size. We can * clear the inode state safely. * 2. The inode has inline data, then we need to read the data, make it * update and dirty so that ext4_da_writepages can handle it. We don't * need to start the journal since the file's metatdata isn't changed now. */ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, unsigned flags, void **fsdata) { int ret = 0, inline_size; struct page *page; page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) return -ENOMEM; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); goto out; } inline_size = ext4_get_inline_size(inode); if (!PageUptodate(page)) { ret = ext4_read_inline_page(inode, page); if (ret < 0) goto out; } ret = __block_write_begin(page, 0, inline_size, ext4_da_get_block_prep); if (ret) { up_read(&EXT4_I(inode)->xattr_sem); unlock_page(page); put_page(page); ext4_truncate_failed_write(inode); return ret; } SetPageDirty(page); SetPageUptodate(page); ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); *fsdata = (void *)CONVERT_INLINE_DATA; out: up_read(&EXT4_I(inode)->xattr_sem); if (page) { unlock_page(page); put_page(page); } return ret; } /* * Prepare the write for the inline data. * If the the data can be written into the inode, we just read * the page and make it uptodate, and start the journal. * Otherwise read the page, makes it dirty so that it can be * handle in writepages(the i_disksize update is left to the * normal ext4_da_write_end). */ int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { int ret, inline_size; handle_t *handle; struct page *page; struct ext4_iloc iloc; int retries = 0; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; retry_journal: handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; } inline_size = ext4_get_max_inline_size(inode); ret = -ENOSPC; if (inline_size >= pos + len) { ret = ext4_prepare_inline_data(handle, inode, pos + len); if (ret && ret != -ENOSPC) goto out_journal; } /* * We cannot recurse into the filesystem as the transaction * is already started. */ flags |= AOP_FLAG_NOFS; if (ret == -ENOSPC) { ext4_journal_stop(handle); ret = ext4_da_convert_inline_data_to_extent(mapping, inode, flags, fsdata); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; goto out; } page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; goto out_journal; } down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { ret = 0; goto out_release_page; } if (!PageUptodate(page)) { ret = ext4_read_inline_page(inode, page); if (ret < 0) goto out_release_page; } ret = ext4_journal_get_write_access(handle, iloc.bh); if (ret) goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); *pagep = page; brelse(iloc.bh); return 1; out_release_page: up_read(&EXT4_I(inode)->xattr_sem); unlock_page(page); put_page(page); out_journal: ext4_journal_stop(handle); out: brelse(iloc.bh); return ret; } int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { int ret; ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { unlock_page(page); put_page(page); return ret; } copied = ret; /* * No need to use i_size_read() here, the i_size * cannot change under us because we hold i_mutex. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos+copied > inode->i_size) i_size_write(inode, pos+copied); unlock_page(page); put_page(page); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ mark_inode_dirty(inode); return copied; } #ifdef INLINE_DIR_DEBUG void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, void *inline_start, int inline_size) { int offset; unsigned short de_len; struct ext4_dir_entry_2 *de = inline_start; void *dlimit = inline_start + inline_size; trace_printk("inode %lu\n", dir->i_ino); offset = 0; while ((void *)de < dlimit) { de_len = ext4_rec_len_from_disk(de->rec_len, inline_size); trace_printk("de: off %u rlen %u name %.*s nlen %u ino %u\n", offset, de_len, de->name_len, de->name, de->name_len, le32_to_cpu(de->inode)); if (ext4_check_dir_entry(dir, NULL, de, bh, inline_start, inline_size, offset)) BUG(); offset += de_len; de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); } } #else #define ext4_show_inline_dir(dir, bh, inline_start, inline_size) #endif /* * Add a new entry into a inline dir. * It will return -ENOSPC if no space is available, and -EIO * and -EEXIST if directory entry already exists. */ static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode, struct ext4_iloc *iloc, void *inline_start, int inline_size) { int err; struct ext4_dir_entry_2 *de; err = ext4_find_dest_de(dir, inode, iloc->bh, inline_start, inline_size, fname, &de); if (err) return err; BUFFER_TRACE(iloc->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, iloc->bh); if (err) return err; ext4_insert_dentry(dir, inode, de, inline_size, fname); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); /* * XXX shouldn't update any times until successful * completion of syscall, but too many callers depend * on this. * * XXX similarly, too many callers depend on * ext4_new_inode() setting the times, but error * recovery deletes the inode, so the worst that can * happen is that the times are slightly out of date * and/or different from the directory change time. */ dir->i_mtime = dir->i_ctime = current_time(dir); ext4_update_dx_flag(dir); inode_inc_iversion(dir); return 1; } static void *ext4_get_inline_xattr_pos(struct inode *inode, struct ext4_iloc *iloc) { struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; BUG_ON(!EXT4_I(inode)->i_inline_off); header = IHDR(inode, ext4_raw_inode(iloc)); entry = (struct ext4_xattr_entry *)((void *)ext4_raw_inode(iloc) + EXT4_I(inode)->i_inline_off); return (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs); } /* Set the final de to cover the whole block. */ static void ext4_update_final_de(void *de_buf, int old_size, int new_size) { struct ext4_dir_entry_2 *de, *prev_de; void *limit; int de_len; de = (struct ext4_dir_entry_2 *)de_buf; if (old_size) { limit = de_buf + old_size; do { prev_de = de; de_len = ext4_rec_len_from_disk(de->rec_len, old_size); de_buf += de_len; de = (struct ext4_dir_entry_2 *)de_buf; } while (de_buf < limit); prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size - old_size, new_size); } else { /* this is just created, so create an empty entry. */ de->inode = 0; de->rec_len = ext4_rec_len_to_disk(new_size, new_size); } } static int ext4_update_inline_dir(handle_t *handle, struct inode *dir, struct ext4_iloc *iloc) { int ret; int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; int new_size = get_max_inline_xattr_value_size(dir, iloc); if (new_size - old_size <= ext4_dir_rec_len(1, NULL)) return -ENOSPC; ret = ext4_update_inline_data(handle, dir, new_size + EXT4_MIN_INLINE_DATA_SIZE); if (ret) return ret; ext4_update_final_de(ext4_get_inline_xattr_pos(dir, iloc), old_size, EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE); dir->i_size = EXT4_I(dir)->i_disksize = EXT4_I(dir)->i_inline_size; return 0; } static void ext4_restore_inline_data(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc, void *buf, int inline_size) { int ret; ret = ext4_create_inline_data(handle, inode, inline_size); if (ret) { ext4_msg(inode->i_sb, KERN_EMERG, "error restoring inline_data for inode -- potential data loss! (inode %lu, error %d)", inode->i_ino, ret); return; } ext4_write_inline_data(inode, iloc, buf, 0, inline_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } static int ext4_finish_convert_inline_dir(handle_t *handle, struct inode *inode, struct buffer_head *dir_block, void *buf, int inline_size) { int err, csum_size = 0, header_size = 0; struct ext4_dir_entry_2 *de; void *target = dir_block->b_data; /* * First create "." and ".." and then copy the dir information * back to the block. */ de = (struct ext4_dir_entry_2 *)target; de = ext4_init_dot_dotdot(inode, de, inode->i_sb->s_blocksize, csum_size, le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1); header_size = (void *)de - target; memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); inode->i_size = inode->i_sb->s_blocksize; i_size_write(inode, inode->i_sb->s_blocksize); EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; ext4_update_final_de(dir_block->b_data, inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size, inode->i_sb->s_blocksize - csum_size); if (csum_size) ext4_initialize_dirent_tail(dir_block, inode->i_sb->s_blocksize); set_buffer_uptodate(dir_block); unlock_buffer(dir_block); err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) return err; set_buffer_verified(dir_block); return ext4_mark_inode_dirty(handle, inode); } static int ext4_convert_inline_data_nolock(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { int error; void *buf = NULL; struct buffer_head *data_bh = NULL; struct ext4_map_blocks map; int inline_size; inline_size = ext4_get_inline_size(inode); buf = kmalloc(inline_size, GFP_NOFS); if (!buf) { error = -ENOMEM; goto out; } error = ext4_read_inline_data(inode, buf, inline_size, iloc); if (error < 0) goto out; /* * Make sure the inline directory entries pass checks before we try to * convert them, so that we avoid touching stuff that needs fsck. */ if (S_ISDIR(inode->i_mode)) { error = ext4_check_all_de(inode, iloc->bh, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); if (error) goto out; } error = ext4_destroy_inline_data_nolock(handle, inode); if (error) goto out; map.m_lblk = 0; map.m_len = 1; map.m_flags = 0; error = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE); if (error < 0) goto out_restore; if (!(map.m_flags & EXT4_MAP_MAPPED)) { error = -EIO; goto out_restore; } data_bh = sb_getblk(inode->i_sb, map.m_pblk); if (!data_bh) { error = -ENOMEM; goto out_restore; } lock_buffer(data_bh); error = ext4_journal_get_create_access(handle, data_bh); if (error) { unlock_buffer(data_bh); error = -EIO; goto out_restore; } memset(data_bh->b_data, 0, inode->i_sb->s_blocksize); if (!S_ISDIR(inode->i_mode)) { memcpy(data_bh->b_data, buf, inline_size); set_buffer_uptodate(data_bh); unlock_buffer(data_bh); error = ext4_handle_dirty_metadata(handle, inode, data_bh); } else { error = ext4_finish_convert_inline_dir(handle, inode, data_bh, buf, inline_size); } out_restore: if (error) ext4_restore_inline_data(handle, inode, iloc, buf, inline_size); out: brelse(data_bh); kfree(buf); return error; } /* * Try to add the new entry to the inline data. * If succeeds, return 0. If not, extended the inline dir and copied data to * the new created block. */ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode) { int ret, inline_size, no_expand; void *inline_start; struct ext4_iloc iloc; ret = ext4_get_inode_loc(dir, &iloc); if (ret) return ret; ext4_write_lock_xattr(dir, &no_expand); if (!ext4_has_inline_data(dir)) goto out; inline_start = (void *)ext4_raw_inode(&iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); if (ret != -ENOSPC) goto out; /* check whether it can be inserted to inline xattr space. */ inline_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; if (!inline_size) { /* Try to use the xattr space.*/ ret = ext4_update_inline_dir(handle, dir, &iloc); if (ret && ret != -ENOSPC) goto out; inline_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; } if (inline_size) { inline_start = ext4_get_inline_xattr_pos(dir, &iloc); ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); if (ret != -ENOSPC) goto out; } /* * The inline space is filled up, so create a new block for it. * As the extent tree will be created, we have to save the inline * dir first. */ ret = ext4_convert_inline_data_nolock(handle, dir, &iloc); out: ext4_write_unlock_xattr(dir, &no_expand); ext4_mark_inode_dirty(handle, dir); brelse(iloc.bh); return ret; } /* * This function fills a red-black tree with information from an * inlined dir. It returns the number directory entries loaded * into the tree. If there is an error it is returned in err. */ int ext4_inlinedir_to_tree(struct file *dir_file, struct inode *dir, ext4_lblk_t block, struct dx_hash_info *hinfo, __u32 start_hash, __u32 start_minor_hash, int *has_inline_data) { int err = 0, count = 0; unsigned int parent_ino; int pos; struct ext4_dir_entry_2 *de; struct inode *inode = file_inode(dir_file); int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; struct ext4_dir_entry_2 fake; struct fscrypt_str tmp_str; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); *has_inline_data = 0; goto out; } inline_size = ext4_get_inline_size(inode); dir_buf = kmalloc(inline_size, GFP_NOFS); if (!dir_buf) { ret = -ENOMEM; up_read(&EXT4_I(inode)->xattr_sem); goto out; } ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); up_read(&EXT4_I(inode)->xattr_sem); if (ret < 0) goto out; pos = 0; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); while (pos < inline_size) { /* * As inlined dir doesn't store any information about '.' and * only the inode number of '..' is stored, we have to handle * them differently. */ if (pos == 0) { fake.inode = cpu_to_le32(inode->i_ino); fake.name_len = 1; strcpy(fake.name, "."); fake.rec_len = ext4_rec_len_to_disk( ext4_dir_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_OFFSET; } else if (pos == EXT4_INLINE_DOTDOT_OFFSET) { fake.inode = cpu_to_le32(parent_ino); fake.name_len = 2; strcpy(fake.name, ".."); fake.rec_len = ext4_rec_len_to_disk( ext4_dir_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_SIZE; } else { de = (struct ext4_dir_entry_2 *)(dir_buf + pos); pos += ext4_rec_len_from_disk(de->rec_len, inline_size); if (ext4_check_dir_entry(inode, dir_file, de, iloc.bh, dir_buf, inline_size, pos)) { ret = count; goto out; } } if (ext4_hash_in_dirent(dir)) { hinfo->hash = EXT4_DIRENT_HASH(de); hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); } else { ext4fs_dirhash(dir, de->name, de->name_len, hinfo); } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) continue; if (de->inode == 0) continue; tmp_str.name = de->name; tmp_str.len = de->name_len; err = ext4_htree_store_dirent(dir_file, hinfo->hash, hinfo->minor_hash, de, &tmp_str); if (err) { ret = err; goto out; } count++; } ret = count; out: kfree(dir_buf); brelse(iloc.bh); return ret; } /* * So this function is called when the volume is mkfsed with * dir_index disabled. In order to keep f_pos persistent * after we convert from an inlined dir to a blocked based, * we just pretend that we are a normal dir and return the * offset as if '.' and '..' really take place. * */ int ext4_read_inline_dir(struct file *file, struct dir_context *ctx, int *has_inline_data) { unsigned int offset, parent_ino; int i; struct ext4_dir_entry_2 *de; struct super_block *sb; struct inode *inode = file_inode(file); int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; int dotdot_offset, dotdot_size, extra_offset, extra_size; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); *has_inline_data = 0; goto out; } inline_size = ext4_get_inline_size(inode); dir_buf = kmalloc(inline_size, GFP_NOFS); if (!dir_buf) { ret = -ENOMEM; up_read(&EXT4_I(inode)->xattr_sem); goto out; } ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); up_read(&EXT4_I(inode)->xattr_sem); if (ret < 0) goto out; ret = 0; sb = inode->i_sb; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); offset = ctx->pos; /* * dotdot_offset and dotdot_size is the real offset and * size for ".." and "." if the dir is block based while * the real size for them are only EXT4_INLINE_DOTDOT_SIZE. * So we will use extra_offset and extra_size to indicate them * during the inline dir iteration. */ dotdot_offset = ext4_dir_rec_len(1, NULL); dotdot_size = dotdot_offset + ext4_dir_rec_len(2, NULL); extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; extra_size = extra_offset + inline_size; /* * If the version has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the inline * dir to make sure. */ if (!inode_eq_iversion(inode, file->f_version)) { for (i = 0; i < extra_size && i < offset;) { /* * "." is with offset 0 and * ".." is dotdot_offset. */ if (!i) { i = dotdot_offset; continue; } else if (i == dotdot_offset) { i = dotdot_size; continue; } /* for other entry, the real offset in * the buf has to be tuned accordingly. */ de = (struct ext4_dir_entry_2 *) (dir_buf + i - extra_offset); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, extra_size) < ext4_dir_rec_len(1, NULL)) break; i += ext4_rec_len_from_disk(de->rec_len, extra_size); } offset = i; ctx->pos = offset; file->f_version = inode_query_iversion(inode); } while (ctx->pos < extra_size) { if (ctx->pos == 0) { if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR)) goto out; ctx->pos = dotdot_offset; continue; } if (ctx->pos == dotdot_offset) { if (!dir_emit(ctx, "..", 2, parent_ino, DT_DIR)) goto out; ctx->pos = dotdot_size; continue; } de = (struct ext4_dir_entry_2 *) (dir_buf + ctx->pos - extra_offset); if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf, extra_size, ctx->pos)) goto out; if (le32_to_cpu(de->inode)) { if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto out; } ctx->pos += ext4_rec_len_from_disk(de->rec_len, extra_size); } out: kfree(dir_buf); brelse(iloc.bh); return ret; } struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval) { struct ext4_iloc iloc; *retval = ext4_get_inode_loc(inode, &iloc); if (*retval) return NULL; *parent_de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; return iloc.bh; } /* * Try to create the inline data for the new dir. * If it succeeds, return 0, otherwise return the error. * In case of ENOSPC, the caller should create the normal disk layout dir. */ int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, struct inode *inode) { int ret, inline_size = EXT4_MIN_INLINE_DATA_SIZE; struct ext4_iloc iloc; struct ext4_dir_entry_2 *de; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; ret = ext4_prepare_inline_data(handle, inode, inline_size); if (ret) goto out; /* * For inline dir, we only save the inode information for the ".." * and create a fake dentry to cover the left space. */ de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; de->inode = cpu_to_le32(parent->i_ino); de = (struct ext4_dir_entry_2 *)((void *)de + EXT4_INLINE_DOTDOT_SIZE); de->inode = 0; de->rec_len = ext4_rec_len_to_disk( inline_size - EXT4_INLINE_DOTDOT_SIZE, inline_size); set_nlink(inode, 2); inode->i_size = EXT4_I(inode)->i_disksize = inline_size; out: brelse(iloc.bh); return ret; } struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, int *has_inline_data) { int ret; struct ext4_iloc iloc; void *inline_start; int inline_size; if (ext4_get_inode_loc(dir, &iloc)) return NULL; down_read(&EXT4_I(dir)->xattr_sem); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; goto out; } inline_start = (void *)ext4_raw_inode(&iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; ret = ext4_search_dir(iloc.bh, inline_start, inline_size, dir, fname, 0, res_dir); if (ret == 1) goto out_find; if (ret < 0) goto out; if (ext4_get_inline_size(dir) == EXT4_MIN_INLINE_DATA_SIZE) goto out; inline_start = ext4_get_inline_xattr_pos(dir, &iloc); inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; ret = ext4_search_dir(iloc.bh, inline_start, inline_size, dir, fname, 0, res_dir); if (ret == 1) goto out_find; out: brelse(iloc.bh); iloc.bh = NULL; out_find: up_read(&EXT4_I(dir)->xattr_sem); return iloc.bh; } int ext4_delete_inline_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, int *has_inline_data) { int err, inline_size, no_expand; struct ext4_iloc iloc; void *inline_start; err = ext4_get_inode_loc(dir, &iloc); if (err) return err; ext4_write_lock_xattr(dir, &no_expand); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; goto out; } if ((void *)de_del - ((void *)ext4_raw_inode(&iloc)->i_block) < EXT4_MIN_INLINE_DATA_SIZE) { inline_start = (void *)ext4_raw_inode(&iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; } else { inline_start = ext4_get_inline_xattr_pos(dir, &iloc); inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; } BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); if (err) goto out; err = ext4_generic_delete_entry(handle, dir, de_del, bh, inline_start, inline_size, 0); if (err) goto out; ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size); out: ext4_write_unlock_xattr(dir, &no_expand); if (likely(err == 0)) err = ext4_mark_inode_dirty(handle, dir); brelse(iloc.bh); if (err != -ENOENT) ext4_std_error(dir->i_sb, err); return err; } /* * Get the inline dentry at offset. */ static inline struct ext4_dir_entry_2 * ext4_get_inline_entry(struct inode *inode, struct ext4_iloc *iloc, unsigned int offset, void **inline_start, int *inline_size) { void *inline_pos; BUG_ON(offset > ext4_get_inline_size(inode)); if (offset < EXT4_MIN_INLINE_DATA_SIZE) { inline_pos = (void *)ext4_raw_inode(iloc)->i_block; *inline_size = EXT4_MIN_INLINE_DATA_SIZE; } else { inline_pos = ext4_get_inline_xattr_pos(inode, iloc); offset -= EXT4_MIN_INLINE_DATA_SIZE; *inline_size = ext4_get_inline_size(inode) - EXT4_MIN_INLINE_DATA_SIZE; } if (inline_start) *inline_start = inline_pos; return (struct ext4_dir_entry_2 *)(inline_pos + offset); } bool empty_inline_dir(struct inode *dir, int *has_inline_data) { int err, inline_size; struct ext4_iloc iloc; size_t inline_len; void *inline_pos; unsigned int offset; struct ext4_dir_entry_2 *de; bool ret = true; err = ext4_get_inode_loc(dir, &iloc); if (err) { EXT4_ERROR_INODE(dir, "error %d getting inode %lu block", err, dir->i_ino); return true; } down_read(&EXT4_I(dir)->xattr_sem); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; goto out; } de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; if (!le32_to_cpu(de->inode)) { ext4_warning(dir->i_sb, "bad inline directory (dir #%lu) - no `..'", dir->i_ino); ret = true; goto out; } inline_len = ext4_get_inline_size(dir); offset = EXT4_INLINE_DOTDOT_SIZE; while (offset < inline_len) { de = ext4_get_inline_entry(dir, &iloc, offset, &inline_pos, &inline_size); if (ext4_check_dir_entry(dir, NULL, de, iloc.bh, inline_pos, inline_size, offset)) { ext4_warning(dir->i_sb, "bad inline directory (dir #%lu) - " "inode %u, rec_len %u, name_len %d" "inline size %d", dir->i_ino, le32_to_cpu(de->inode), le16_to_cpu(de->rec_len), de->name_len, inline_size); ret = true; goto out; } if (le32_to_cpu(de->inode)) { ret = false; goto out; } offset += ext4_rec_len_from_disk(de->rec_len, inline_size); } out: up_read(&EXT4_I(dir)->xattr_sem); brelse(iloc.bh); return ret; } int ext4_destroy_inline_data(handle_t *handle, struct inode *inode) { int ret, no_expand; ext4_write_lock_xattr(inode, &no_expand); ret = ext4_destroy_inline_data_nolock(handle, inode); ext4_write_unlock_xattr(inode, &no_expand); return ret; } int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap) { __u64 addr; int error = -EAGAIN; struct ext4_iloc iloc; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) goto out; error = ext4_get_inode_loc(inode, &iloc); if (error) goto out; addr = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits; addr += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; addr += offsetof(struct ext4_inode, i_block); brelse(iloc.bh); iomap->addr = addr; iomap->offset = 0; iomap->length = min_t(loff_t, ext4_get_inline_size(inode), i_size_read(inode)); iomap->type = IOMAP_INLINE; iomap->flags = 0; out: up_read(&EXT4_I(inode)->xattr_sem); return error; } int ext4_inline_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, int *has_inline, __u64 start, __u64 len) { __u64 physical = 0; __u64 inline_len; __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED | FIEMAP_EXTENT_LAST; int error = 0; struct ext4_iloc iloc; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { *has_inline = 0; goto out; } inline_len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode)); if (start >= inline_len) goto out; if (start + len < inline_len) inline_len = start + len; inline_len -= start; error = ext4_get_inode_loc(inode, &iloc); if (error) goto out; physical = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits; physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; physical += offsetof(struct ext4_inode, i_block); brelse(iloc.bh); out: up_read(&EXT4_I(inode)->xattr_sem); if (physical) error = fiemap_fill_next_extent(fieinfo, start, physical, inline_len, flags); return (error < 0 ? error : 0); } int ext4_inline_data_truncate(struct inode *inode, int *has_inline) { handle_t *handle; int inline_size, value_len, needed_blocks, no_expand, err = 0; size_t i_size; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; needed_blocks = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_write_lock_xattr(inode, &no_expand); if (!ext4_has_inline_data(inode)) { ext4_write_unlock_xattr(inode, &no_expand); *has_inline = 0; ext4_journal_stop(handle); return 0; } if ((err = ext4_orphan_add(handle, inode)) != 0) goto out; if ((err = ext4_get_inode_loc(inode, &is.iloc)) != 0) goto out; down_write(&EXT4_I(inode)->i_data_sem); i_size = inode->i_size; inline_size = ext4_get_inline_size(inode); EXT4_I(inode)->i_disksize = i_size; if (i_size < inline_size) { /* Clear the content in the xattr space. */ if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) { if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0) goto out_error; BUG_ON(is.s.not_found); value_len = le32_to_cpu(is.s.here->e_value_size); value = kmalloc(value_len, GFP_NOFS); if (!value) { err = -ENOMEM; goto out_error; } err = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, value_len); if (err <= 0) goto out_error; i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; } /* Clear the content within i_blocks. */ if (i_size < EXT4_MIN_INLINE_DATA_SIZE) { void *p = (void *) ext4_raw_inode(&is.iloc)->i_block; memset(p + i_size, 0, EXT4_MIN_INLINE_DATA_SIZE - i_size); } EXT4_I(inode)->i_inline_size = i_size < EXT4_MIN_INLINE_DATA_SIZE ? EXT4_MIN_INLINE_DATA_SIZE : i_size; } out_error: up_write(&EXT4_I(inode)->i_data_sem); out: brelse(is.iloc.bh); ext4_write_unlock_xattr(inode, &no_expand); kfree(value); if (inode->i_nlink) ext4_orphan_del(handle, inode); if (err == 0) { inode->i_mtime = inode->i_ctime = current_time(inode); err = ext4_mark_inode_dirty(handle, inode); if (IS_SYNC(inode)) ext4_handle_sync(handle); } ext4_journal_stop(handle); return err; } int ext4_convert_inline_data(struct inode *inode) { int error, needed_blocks, no_expand; handle_t *handle; struct ext4_iloc iloc; if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; } else if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { /* * Inode has inline data but EXT4_STATE_MAY_INLINE_DATA is * cleared. This means we are in the middle of moving of * inline data to delay allocated block. Just force writeout * here to finish conversion. */ error = filemap_flush(inode->i_mapping); if (error) return error; if (!ext4_has_inline_data(inode)) return 0; } needed_blocks = ext4_writepage_trans_blocks(inode); iloc.bh = NULL; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto out_free; } ext4_write_lock_xattr(inode, &no_expand); if (ext4_has_inline_data(inode)) error = ext4_convert_inline_data_nolock(handle, inode, &iloc); ext4_write_unlock_xattr(inode, &no_expand); ext4_journal_stop(handle); out_free: brelse(iloc.bh); return error; } |
| 2924 244 1045 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/pagevec.h * * In many places it is efficient to batch an operation up against multiple * pages. A pagevec is a multipage container which is used for that. */ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H #include <linux/xarray.h> /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 struct page; struct address_space; struct pagevec { unsigned char nr; bool percpu_pvec_drained; struct page *pages[PAGEVEC_SIZE]; }; void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end); static inline unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start) { return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); } unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } static inline void pagevec_init(struct pagevec *pvec) { pvec->nr = 0; pvec->percpu_pvec_drained = false; } static inline void pagevec_reinit(struct pagevec *pvec) { pvec->nr = 0; } static inline unsigned pagevec_count(struct pagevec *pvec) { return pvec->nr; } static inline unsigned pagevec_space(struct pagevec *pvec) { return PAGEVEC_SIZE - pvec->nr; } /* * Add a page to a pagevec. Returns the number of slots still available. */ static inline unsigned pagevec_add(struct pagevec *pvec, struct page *page) { pvec->pages[pvec->nr++] = page; return pagevec_space(pvec); } static inline void pagevec_release(struct pagevec *pvec) { if (pagevec_count(pvec)) __pagevec_release(pvec); } #endif /* _LINUX_PAGEVEC_H */ |
| 3367 3693 113 6485 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <asm/processor.h> #include <linux/cpumask.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active __read_mostly; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL void rcu_user_enter(void); void rcu_user_exit(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } #endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. * * RCU read-side critical sections are forbidden in the inner idle loop, * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU * will happily ignore any such read-side critical sections. However, * things like powertop need tracepoints in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) * will tell RCU that it needs to pay attention, invoke its argument * (in this example, calling the do_something_with_RCU() function), * and then tell RCU to go back to ignoring this CPU. It is permissible * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is * on the order of a million or so, even on 32-bit systems). It is * not legal to block within RCU_NONIDLE(), nor is it permissible to * transfer control either into or out of RCU_NONIDLE()'s statement. */ #define RCU_NONIDLE(a) \ do { \ rcu_irq_enter_irqson(); \ do { a; } while (0); \ rcu_irq_exit_irqson(); \ } while (0) /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU #define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPT kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current); \ cond_resched(); \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, 1, _THIS_IP_); } extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(.data.unlikely) __warned; \ if (debug_lockdep_rcu_enabled() && !__warned && (c)) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_check(p, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define rcu_dereference_raw(p) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) ________p1 = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_swap_protected() - swap an RCU and a regular pointer * @rcu_ptr: RCU pointer * @ptr: regular pointer * @c: the conditions under which the dereference will take place * * Perform swap(@rcu_ptr, @ptr) where @rcu_ptr is an RCU-annotated pointer and * @c is the argument that is passed to the rcu_dereference_protected() call * used to read that pointer. */ #define rcu_swap_protected(rcu_ptr, ptr, c) do { \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ (ptr) = __tmp; \ } while (0) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as * is the case in the context of the RCU callback that is freeing up * the data, or after a synchronize_rcu() returns. This can be useful * when tearing down multi-linked structures after a grace period * has elapsed. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPT kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In most situations, rcu_read_unlock() is immune from deadlock. * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() * is responsible for deboosting, which it does via rt_mutex_unlock(). * Unfortunately, this function acquires the scheduler's runqueue and * priority-inheritance spinlocks. This means that deadlock could result * if the caller of rcu_read_unlock() already holds one of these locks or * any lock that is ever acquired while holding them. * * That said, RCU readers are never priority boosted unless they were * preempted. Therefore, one way to avoid deadlock is to make sure * that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with one of * rt_mutex_unlock()'s locks held. Such preemption can be avoided in * a number of ways, for example, by invoking preempt_disable() before * critical section's outermost rcu_read_lock(). * * Given that the set of locks acquired by rt_mutex_unlock() might change * at any time, a somewhat more future-proofed approach is to make sure * that that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with irqs disabled. * This approach relies on the fact that rt_mutex_unlock() currently only * acquires irq-disabled locks. * * The second of these two approaches is best in most situations, * however, the first approach can also be useful, at least to those * developers willing to keep abreast of the set of locks acquired by * rt_mutex_unlock(). * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); __release(RCU); __rcu_read_unlock(); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as * an RCU read-side critical section. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /* * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent of rcu_read_lock(), but disables preemption. * Read-side critical sections can also be introduced by anything else * that disables preemption, including local_irq_disable() and friends. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /* * rcu_read_unlock_sched - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kfree_rcu()? */ #define __is_kfree_rcu_offset(offset) ((offset) < 4096) /* * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. */ #define __kfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ kfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in __kfree_rcu(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * Note that the allowable offset might decrease in the future, for example, * to allow something like kmem_cache_free_rcu(). * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) \ __kfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } #endif /* __LINUX_RCUPDATE_H */ |
| 1 1058 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/bad_inode.c * * Copyright (C) 1997, Stephen Tweedie * * Provide stub functions for unreadable inodes * * Fabian Frederick : August 2003 - All file operations assigned to EIO */ #include <linux/fs.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/time.h> #include <linux/namei.h> #include <linux/poll.h> static int bad_file_open(struct inode *inode, struct file *filp) { return -EIO; } static const struct file_operations bad_file_ops = { .open = bad_file_open, }; static int bad_inode_create (struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return -EIO; } static struct dentry *bad_inode_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-EIO); } static int bad_inode_link (struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_unlink(struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_symlink (struct inode *dir, struct dentry *dentry, const char *symname) { return -EIO; } static int bad_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { return -EIO; } static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_mknod (struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { return -EIO; } static int bad_inode_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { return -EIO; } static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, int buflen) { return -EIO; } static int bad_inode_permission(struct inode *inode, int mask) { return -EIO; } static int bad_inode_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { return -EIO; } static int bad_inode_setattr(struct dentry *direntry, struct iattr *attrs) { return -EIO; } static ssize_t bad_inode_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { return -EIO; } static const char *bad_inode_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return ERR_PTR(-EIO); } static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type) { return ERR_PTR(-EIO); } static int bad_inode_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { return -EIO; } static int bad_inode_update_time(struct inode *inode, struct timespec64 *time, int flags) { return -EIO; } static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry, struct file *file, unsigned int open_flag, umode_t create_mode) { return -EIO; } static int bad_inode_tmpfile(struct inode *inode, struct dentry *dentry, umode_t mode) { return -EIO; } static int bad_inode_set_acl(struct inode *inode, struct posix_acl *acl, int type) { return -EIO; } static const struct inode_operations bad_inode_ops = { .create = bad_inode_create, .lookup = bad_inode_lookup, .link = bad_inode_link, .unlink = bad_inode_unlink, .symlink = bad_inode_symlink, .mkdir = bad_inode_mkdir, .rmdir = bad_inode_rmdir, .mknod = bad_inode_mknod, .rename = bad_inode_rename2, .readlink = bad_inode_readlink, .permission = bad_inode_permission, .getattr = bad_inode_getattr, .setattr = bad_inode_setattr, .listxattr = bad_inode_listxattr, .get_link = bad_inode_get_link, .get_acl = bad_inode_get_acl, .fiemap = bad_inode_fiemap, .update_time = bad_inode_update_time, .atomic_open = bad_inode_atomic_open, .tmpfile = bad_inode_tmpfile, .set_acl = bad_inode_set_acl, }; /* * When a filesystem is unable to read an inode due to an I/O error in * its read_inode() function, it can call make_bad_inode() to return a * set of stubs which will return EIO errors as required. * * We only need to do limited initialisation: all other fields are * preinitialised to zero automatically. */ /** * make_bad_inode - mark an inode bad due to an I/O error * @inode: Inode to mark bad * * When an inode cannot be read due to a media or remote network * failure this function makes the inode "bad" and causes I/O operations * on it to fail from this point on. */ void make_bad_inode(struct inode *inode) { remove_inode_hash(inode); inode->i_mode = S_IFREG; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_op = &bad_inode_ops; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &bad_file_ops; } EXPORT_SYMBOL(make_bad_inode); /* * This tests whether an inode has been flagged as bad. The test uses * &bad_inode_ops to cover the case of invalidated inodes as well as * those created by make_bad_inode() above. */ /** * is_bad_inode - is an inode errored * @inode: inode to test * * Returns true if the inode in question has been marked as bad. */ bool is_bad_inode(struct inode *inode) { return (inode->i_op == &bad_inode_ops); } EXPORT_SYMBOL(is_bad_inode); /** * iget_failed - Mark an under-construction inode as dead and release it * @inode: The inode to discard * * Mark an under-construction inode as dead and release it. */ void iget_failed(struct inode *inode) { make_bad_inode(inode); unlock_new_inode(inode); iput(inode); } EXPORT_SYMBOL(iget_failed); |
| 938 938 938 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | // SPDX-License-Identifier: GPL-2.0 #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> #define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) #define get_bucket(x) ((x) >> BUCKET_SPACE) #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) extern struct list_head ptype_all __read_mostly; extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct net_device *dev; struct hlist_head *h; unsigned int count = 0, offset = get_offset(*pos); h = &net->dev_name_head[get_bucket(*pos)]; hlist_for_each_entry_rcu(dev, h, name_hlist) { if (++count == offset) return dev; } return NULL; } static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) { struct net_device *dev; unsigned int bucket; do { dev = dev_from_same_bucket(seq, pos); if (dev) return dev; bucket = get_bucket(*pos) + 1; *pos = set_bucket_offset(bucket, 1); } while (bucket < NETDEV_HASHENTRIES); return NULL; } /* * This is invoked by the /proc filesystem handler to display a device * in detail. */ static void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; if (get_bucket(*pos) >= NETDEV_HASHENTRIES) return NULL; return dev_from_bucket(seq, pos); } static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return dev_from_bucket(seq, pos); } static void dev_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, stats->rx_fifo_errors, stats->rx_length_errors + stats->rx_over_errors + stats->rx_crc_errors + stats->rx_frame_errors, stats->rx_compressed, stats->multicast, stats->tx_bytes, stats->tx_packets, stats->tx_errors, stats->tx_dropped, stats->tx_fifo_errors, stats->collisions, stats->tx_carrier_errors + stats->tx_aborted_errors + stats->tx_window_errors + stats->tx_heartbeat_errors, stats->tx_compressed); } /* * Called from the PROCfs module. This now uses the new arbitrary sized * /proc/net interface to create /proc/net/dev */ static int dev_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Inter-| Receive " " | Transmit\n" " face |bytes packets errs drop fifo frame " "compressed multicast|bytes packets errs " "drop fifo colls carrier compressed\n"); else dev_seq_printf_stats(seq, v); return 0; } static struct softnet_data *softnet_get_online(loff_t *pos) { struct softnet_data *sd = NULL; while (*pos < nr_cpu_ids) if (cpu_online(*pos)) { sd = &per_cpu(softnet_data, *pos); break; } else ++*pos; return sd; } static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) { return softnet_get_online(pos); } static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return softnet_get_online(pos); } static void softnet_seq_stop(struct seq_file *seq, void *v) { } static int softnet_seq_show(struct seq_file *seq, void *v) { struct softnet_data *sd = v; unsigned int flow_limit_count = 0; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) flow_limit_count = fl->count; rcu_read_unlock(); #endif seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ sd->received_rps, flow_limit_count); return 0; } static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_seq_show, }; static const struct seq_operations softnet_seq_ops = { .start = softnet_seq_start, .next = softnet_seq_next, .stop = softnet_seq_stop, .show = softnet_seq_show, }; static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; loff_t i = 0; int t; for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { if (i == pos) return pt; ++i; } } list_for_each_entry_rcu(pt, &ptype_all, list) { if (i == pos) return pt; ++i; } for (t = 0; t < PTYPE_HASH_SIZE; t++) { list_for_each_entry_rcu(pt, &ptype_base[t], list) { if (i == pos) return pt; ++i; } } return NULL; } static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash; ++*pos; if (v == SEQ_START_TOKEN) return ptype_get_idx(seq, 0); pt = v; nxt = pt->list.next; if (pt->dev) { if (nxt != &pt->dev->ptype_all) goto found; dev = pt->dev; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { if (!list_empty(&dev->ptype_all)) { nxt = dev->ptype_all.next; goto found; } } nxt = ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: if (nxt != &ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; nxt = ptype_base[hash].next; } found: return list_entry(nxt, struct packet_type, list); } static void ptype_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ptype_seq_show(struct seq_file *seq, void *v) { struct packet_type *pt = v; if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", pt->dev ? pt->dev->name : "", pt->func); } return 0; } static const struct seq_operations ptype_seq_ops = { .start = ptype_seq_start, .next = ptype_seq_next, .stop = ptype_seq_stop, .show = ptype_seq_show, }; static int __net_init dev_proc_net_init(struct net *net) { int rc = -ENOMEM; if (!proc_create_net("dev", 0444, net->proc_net, &dev_seq_ops, sizeof(struct seq_net_private))) goto out; if (!proc_create_seq("softnet_stat", 0444, net->proc_net, &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, sizeof(struct seq_net_private))) goto out_softnet; if (wext_proc_init(net)) goto out_ptype; rc = 0; out: return rc; out_ptype: remove_proc_entry("ptype", net->proc_net); out_softnet: remove_proc_entry("softnet_stat", net->proc_net); out_dev: remove_proc_entry("dev", net->proc_net); goto out; } static void __net_exit dev_proc_net_exit(struct net *net) { wext_proc_exit(net); remove_proc_entry("ptype", net->proc_net); remove_proc_entry("softnet_stat", net->proc_net); remove_proc_entry("dev", net->proc_net); } static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, }; static int dev_mc_seq_show(struct seq_file *seq, void *v) { struct netdev_hw_addr *ha; struct net_device *dev = v; if (v == SEQ_START_TOKEN) return 0; netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", dev->ifindex, dev->name, ha->refcount, ha->global_use, (int)dev->addr_len, ha->addr); } netif_addr_unlock_bh(dev); return 0; } static const struct seq_operations dev_mc_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_mc_seq_show, }; static int __net_init dev_mc_net_init(struct net *net) { if (!proc_create_net("dev_mcast", 0, net->proc_net, &dev_mc_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static void __net_exit dev_mc_net_exit(struct net *net) { remove_proc_entry("dev_mcast", net->proc_net); } static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, }; int __init dev_proc_init(void) { int ret = register_pernet_subsys(&dev_proc_ops); if (!ret) return register_pernet_subsys(&dev_mc_net_ops); return ret; } |
| 652 3573 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ #include <asm/processor-flags.h> #ifndef __ASSEMBLY__ #include <asm/nospec-branch.h> /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __attribute__((__section__(".cpuidle.text"))) /* * Interrupt control: */ /* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ extern inline unsigned long native_save_fl(void); extern inline unsigned long native_save_fl(void) { unsigned long flags; /* * "=rm" is safe here, because "pop" adjusts the stack before * it evaluates its effective address -- this is part of the * documented behavior of the "pop" instruction. */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" : "=rm" (flags) : /* no input */ : "memory"); return flags; } extern inline void native_restore_fl(unsigned long flags); extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ :"g" (flags) :"memory", "cc"); } static inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); } static inline void native_irq_enable(void) { asm volatile("sti": : :"memory"); } static inline __cpuidle void native_safe_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } #endif #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ #include <linux/types.h> static inline notrace unsigned long arch_local_save_flags(void) { return native_save_fl(); } static inline notrace void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } static inline notrace void arch_local_irq_disable(void) { native_irq_disable(); } static inline notrace void arch_local_irq_enable(void) { native_irq_enable(); } /* * Used in the idle loop; sti takes one instruction cycle * to complete: */ static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } /* * Used when interrupts are already enabled or to * shutdown the processor: */ static inline __cpuidle void halt(void) { native_halt(); } /* * For spinlocks, etc: */ static inline notrace unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); return flags; } #else #define ENABLE_INTERRUPTS(x) sti #define DISABLE_INTERRUPTS(x) cli #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(x) pushfq; popq %rax #endif #define SWAPGS swapgs /* * Currently paravirt can't handle swapgs nicely when we * don't have a stack we can rely on (such as a user space * stack). So we either find a way around these or just fault * and emulate if a guest tries to call swapgs directly. * * Either way, this is a good way to document that we don't * have a reliable stack. x86_64 only. */ #define SWAPGS_UNSAFE_STACK swapgs #define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; #define USERGS_SYSRET32 \ swapgs; \ sysretl #else #define INTERRUPT_RETURN iret #endif #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLY__ static inline int arch_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static inline int arch_irqs_disabled(void) { unsigned long flags = arch_local_save_flags(); return arch_irqs_disabled_flags(flags); } #endif /* !__ASSEMBLY__ */ #ifdef __ASSEMBLY__ #ifdef CONFIG_TRACE_IRQFLAGS # define TRACE_IRQS_ON call trace_hardirqs_on_thunk; # define TRACE_IRQS_OFF call trace_hardirqs_off_thunk; #else # define TRACE_IRQS_ON # define TRACE_IRQS_OFF #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_X86_64 # define LOCKDEP_SYS_EXIT call lockdep_sys_exit_thunk # define LOCKDEP_SYS_EXIT_IRQ \ TRACE_IRQS_ON; \ sti; \ call lockdep_sys_exit_thunk; \ cli; \ TRACE_IRQS_OFF; # else # define LOCKDEP_SYS_EXIT \ pushl %eax; \ pushl %ecx; \ pushl %edx; \ call lockdep_sys_exit; \ popl %edx; \ popl %ecx; \ popl %eax; # define LOCKDEP_SYS_EXIT_IRQ # endif #else # define LOCKDEP_SYS_EXIT # define LOCKDEP_SYS_EXIT_IRQ #endif #endif /* __ASSEMBLY__ */ #endif |
| 6 6 6 6 6 6 6 2 4 6 6 6 6 6 1354 1353 2 2 2 32 32 32 55 54 55 1342 1342 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/genhd.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/blk-cgroup.h> #include <linux/tracehook.h> #include <linux/psi.h> #include "blk.h" #define MAX_KEY_LEN 100 /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static struct workqueue_struct *blkcg_punt_bio_wq; static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { return pol && test_bit(pol->plid, q->blkcg_pols); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { int i; if (!blkg) return; for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); blkg_rwstat_exit(&blkg->stat_ios); blkg_rwstat_exit(&blkg->stat_bytes); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); WARN_ON(!bio_list_empty(&blkg->async_bios)); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); if (blkg->parent) blkg_put(blkg->parent); wb_congested_put(blkg->wb_congested); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; /* as long as there are pending bios, @blkg can't go away */ spin_lock_bh(&blkg->async_bio_lock); bio_list_merge(&bios, &blkg->async_bios); bio_list_init(&blkg->async_bios); spin_unlock_bh(&blkg->async_bio_lock); while ((bio = bio_list_pop(&bios))) submit_bio(bio); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @q: request_queue the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg assocating @blkcg and @q. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto err_free; if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) || blkg_rwstat_init(&blkg->stat_ios, gfp_mask)) goto err_free; blkg->q = q; INIT_LIST_HEAD(&blkg->q_node); spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); blkg->blkcg = blkcg; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(q, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(gfp_mask, q, blkcg); if (!pd) goto err_free; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; } return blkg; err_free: blkg_free(blkg); return NULL; } struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint) { struct blkcg_gq *blkg; /* * Hint didn't match. Look up from the radix tree. Note that the * hint can only be updated under queue_lock as otherwise @blkg * could have already been removed from blkg_tree. The caller is * responsible for grabbing queue_lock if @update_hint. */ blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id); if (blkg && blkg->q == q) { if (update_hint) { lockdep_assert_held(&q->queue_lock); rcu_assign_pointer(blkcg->blkg_hint, blkg); } return blkg; } return NULL; } EXPORT_SYMBOL_GPL(blkg_lookup_slowpath); /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct request_queue *q, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; struct bdi_writeback_congested *wb_congested; int i, ret; WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(&q->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(q)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } wb_congested = wb_congested_get_create(q->backing_dev_info, blkcg->css.id, GFP_NOWAIT | __GFP_NOWARN); if (!wb_congested) { ret = -ENOMEM; goto err_put_css; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_congested; } } blkg = new_blkg; blkg->wb_congested = wb_congested; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_congested; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &q->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_congested: wb_congested_put(wb_congested); err_put_css: css_put(&blkcg->css); err_free_blkg: blkg_free(new_blkg); return ERR_PTR(ret); } /** * __blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and @q->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q) { struct blkcg_gq *blkg; WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(&q->queue_lock); blkg = __blkg_lookup(blkcg, q, true); if (blkg) return blkg; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = __blkg_lookup(parent, q, false); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, q, NULL); if (IS_ERR(blkg)) return ret_blkg; if (pos == blkcg) return blkg; } } /** * blkg_lookup_create - find or create a blkg * @blkcg: target block cgroup * @q: target request_queue * * This looks up or creates the blkg representing the unique pair * of the blkcg and the request_queue. */ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q) { struct blkcg_gq *blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { unsigned long flags; spin_lock_irqsave(&q->queue_lock, flags); blkg = __blkg_lookup_create(blkcg, q); spin_unlock_irqrestore(&q->queue_lock, flags); } return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; struct blkcg_gq *parent = blkg->parent; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* Something wrong if we are trying to remove same group twice */ WARN_ON_ONCE(list_empty(&blkg->q_node)); WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node)); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } if (parent) { blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); list_del_init(&blkg->q_node); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } /** * blkg_destroy_all - destroy all blkgs associated with a request_queue * @q: request_queue of interest * * Destroy all blkgs associated with @q. */ static void blkg_destroy_all(struct request_queue *q) { struct blkcg_gq *blkg, *n; spin_lock_irq(&q->queue_lock); list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { blkg_rwstat_reset(&blkg->stat_bytes); blkg_rwstat_reset(&blkg->stat_ios); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { /* some drivers (floppy) instantiate a queue w/o disk registered */ if (blkg->q->backing_dev_info->dev) return dev_name(blkg->q->backing_dev_info->dev); return NULL; } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device assocaited with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /** * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat * @sf: seq_file to print to * @pd: policy private data of interest * @rwstat: rwstat to print * * Print @rwstat to @sf for the device assocaited with @pd. */ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, const struct blkg_rwstat_sample *rwstat) { static const char *rwstr[] = { [BLKG_RWSTAT_READ] = "Read", [BLKG_RWSTAT_WRITE] = "Write", [BLKG_RWSTAT_SYNC] = "Sync", [BLKG_RWSTAT_ASYNC] = "Async", [BLKG_RWSTAT_DISCARD] = "Discard", }; const char *dname = blkg_dev_name(pd->blkg); u64 v; int i; if (!dname) return 0; for (i = 0; i < BLKG_RWSTAT_NR; i++) seq_printf(sf, "%s %s %llu\n", dname, rwstr[i], rwstat->cnt[i]); v = rwstat->cnt[BLKG_RWSTAT_READ] + rwstat->cnt[BLKG_RWSTAT_WRITE] + rwstat->cnt[BLKG_RWSTAT_DISCARD]; seq_printf(sf, "%s Total %llu\n", dname, v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat); /** * blkg_prfill_rwstat - prfill callback for blkg_rwstat * @sf: seq_file to print to * @pd: policy private data of interest * @off: offset to the blkg_rwstat in @pd * * prfill callback for printing a blkg_rwstat. */ u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkg_rwstat_sample rwstat = { }; blkg_rwstat_read((void *)pd + off, &rwstat); return __blkg_prfill_rwstat(sf, pd, &rwstat); } EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); static u64 blkg_prfill_rwstat_field(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkg_rwstat_sample rwstat = { }; blkg_rwstat_read((void *)pd->blkg + off, &rwstat); return __blkg_prfill_rwstat(sf, pd, &rwstat); } /** * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes * @sf: seq_file to print to * @v: unused * * To be used as cftype->seq_show to print blkg->stat_bytes. * cftype->private must be set to the blkcg_policy. */ int blkg_print_stat_bytes(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, offsetof(struct blkcg_gq, stat_bytes), true); return 0; } EXPORT_SYMBOL_GPL(blkg_print_stat_bytes); /** * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios * @sf: seq_file to print to * @v: unused * * To be used as cftype->seq_show to print blkg->stat_ios. cftype->private * must be set to the blkcg_policy. */ int blkg_print_stat_ios(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, offsetof(struct blkcg_gq, stat_ios), true); return 0; } EXPORT_SYMBOL_GPL(blkg_print_stat_ios); static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkg_rwstat_sample rwstat; blkg_rwstat_recursive_sum(pd->blkg, NULL, off, &rwstat); return __blkg_prfill_rwstat(sf, pd, &rwstat); } /** * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes * @sf: seq_file to print to * @v: unused */ int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat_field_recursive, (void *)seq_cft(sf)->private, offsetof(struct blkcg_gq, stat_bytes), true); return 0; } EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive); /** * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios * @sf: seq_file to print to * @v: unused */ int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat_field_recursive, (void *)seq_cft(sf)->private, offsetof(struct blkcg_gq, stat_ios), true); return 0; } EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive); /** * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat * @blkg: blkg of interest * @pol: blkcg_policy which contains the blkg_rwstat * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg * @sum: blkg_rwstat_sample structure containing the results * * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its * online descendants and their aux counts. The caller must be holding the * queue lock for online tests. * * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it * is at @off bytes into @blkg's blkg_policy_data of the policy. */ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, int off, struct blkg_rwstat_sample *sum) { struct blkcg_gq *pos_blkg; struct cgroup_subsys_state *pos_css; unsigned int i; lockdep_assert_held(&blkg->q->queue_lock); rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { struct blkg_rwstat *rwstat; if (!pos_blkg->online) continue; if (pol) rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off; else rwstat = (void *)pos_blkg + off; for (i = 0; i < BLKG_RWSTAT_NR; i++) sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); /* Performs queue bypass and policy enabled checks then looks up blkg. */ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, const struct blkcg_policy *pol, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) return ERR_PTR(-EOPNOTSUPP); return __blkg_lookup(blkcg, q, true /* update_hint */); } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @inputp: input string pointer * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update * from @input and get and return the matching gendisk. *@inputp is * updated to point past the device node prefix. Returns an ERR_PTR() * value on error. * * Use this function iff blkg_conf_prep() can't be used for some reason. */ struct gendisk *blkcg_conf_get_disk(char **inputp) { char *input = *inputp; unsigned int major, minor; struct gendisk *disk; int key_len, part; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return ERR_PTR(-EINVAL); input += key_len; if (!isspace(*input)) return ERR_PTR(-EINVAL); input = skip_spaces(input); disk = get_gendisk(MKDEV(major, minor), &part); if (!disk) return ERR_PTR(-ENODEV); if (part) { put_disk_and_module(disk); return ERR_PTR(-ENODEV); } *inputp = input; return disk; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @input: input string * @ctx: blkg_conf_ctx to be filled * * Parse per-blkg config update from @input and initialize @ctx with the * result. @ctx->blkg points to the blkg to be updated and @ctx->body the * part of @input following MAJ:MIN. This function returns with RCU read * lock and queue lock held and must be paired with blkg_conf_finish(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx) __acquires(rcu) __acquires(&disk->queue->queue_lock) { struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; disk = blkcg_conf_get_disk(&input); if (IS_ERR(disk)) return PTR_ERR(disk); q = disk->queue; rcu_read_lock(); spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_check(blkcg, pol, q); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_unlock; } if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !__blkg_lookup(parent, q, false)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); new_blkg = blkg_alloc(pos, q, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail; } rcu_read_lock(); spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_check(pos, pol, q); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); blkg_free(new_blkg); goto fail_preloaded; } if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, q, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: ctx->disk = disk; ctx->blkg = blkg; ctx->body = input; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); fail: put_disk_and_module(disk); /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_finish - finish up per-blkg config update * @ctx: blkg_conf_ctx intiailized by blkg_conf_prep() * * Finish up after per-blkg config update. This function must be paired * with blkg_conf_prep(). */ void blkg_conf_finish(struct blkg_conf_ctx *ctx) __releases(&ctx->disk->queue->queue_lock) __releases(rcu) { spin_unlock_irq(&ctx->disk->queue->queue_lock); rcu_read_unlock(); put_disk_and_module(ctx->disk); } EXPORT_SYMBOL_GPL(blkg_conf_finish); static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { const char *dname; char *buf; struct blkg_rwstat_sample rwstat; u64 rbytes, wbytes, rios, wios, dbytes, dios; size_t size = seq_get_buf(sf, &buf), off = 0; int i; bool has_stats = false; spin_lock_irq(&blkg->q->queue_lock); if (!blkg->online) goto skip; dname = blkg_dev_name(blkg); if (!dname) goto skip; /* * Hooray string manipulation, count is the size written NOT * INCLUDING THE \0, so size is now count+1 less than what we * had before, but we want to start writing the next bit from * the \0 so we only add count to buf. */ off += scnprintf(buf+off, size-off, "%s ", dname); blkg_rwstat_recursive_sum(blkg, NULL, offsetof(struct blkcg_gq, stat_bytes), &rwstat); rbytes = rwstat.cnt[BLKG_RWSTAT_READ]; wbytes = rwstat.cnt[BLKG_RWSTAT_WRITE]; dbytes = rwstat.cnt[BLKG_RWSTAT_DISCARD]; blkg_rwstat_recursive_sum(blkg, NULL, offsetof(struct blkcg_gq, stat_ios), &rwstat); rios = rwstat.cnt[BLKG_RWSTAT_READ]; wios = rwstat.cnt[BLKG_RWSTAT_WRITE]; dios = rwstat.cnt[BLKG_RWSTAT_DISCARD]; if (rbytes || wbytes || rios || wios) { has_stats = true; off += scnprintf(buf+off, size-off, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { has_stats = true; off += scnprintf(buf+off, size-off, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), (unsigned long long)atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; size_t written; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off); if (written) has_stats = true; off += written; } if (has_stats) { if (off < size - 1) { off += scnprintf(buf+off, size-off, "\n"); seq_commit(sf, off); } else { seq_commit(sf, -1); } } skip: spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(blkcg); /* put the base cgwb reference allowing step 2 to be triggered */ blkcg_cgwb_put(blkcg); } /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; struct cgroup_subsys_state *ret; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) { ret = ERR_PTR(-ENOMEM); goto unlock; } } for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) { ret = ERR_PTR(-ENOMEM); goto free_pd_blkcg; } blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; if (pol->cpd_init_fn) pol->cpd_init_fn(cpd); } spin_lock_init(&blkcg->lock); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); refcount_set(&blkcg->cgwb_refcnt, 1); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ret; } /** * blkcg_init_queue - initialize blkcg part of request queue * @q: request_queue to initialize * * Called from blk_alloc_queue_node(). Responsible for initializing blkcg * part of new request_queue @q. * * RETURNS: * 0 on success, -errno on failure. */ int blkcg_init_queue(struct request_queue *q) { struct blkcg_gq *new_blkg, *blkg; bool preloaded; int ret; new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ rcu_read_lock(); spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, q, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); ret = blk_throtl_init(q); if (ret) goto err_destroy_all; ret = blk_iolatency_init(q); if (ret) { blk_throtl_exit(q); goto err_destroy_all; } return 0; err_destroy_all: blkg_destroy_all(q); return ret; err_unlock: spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } /** * blkcg_drain_queue - drain blkcg part of request_queue * @q: request_queue to drain * * Called from blk_drain_queue(). Responsible for draining blkcg part. */ void blkcg_drain_queue(struct request_queue *q) { lockdep_assert_held(&q->queue_lock); /* * @q could be exiting and already have destroyed all blkgs as * indicated by NULL root_blkg. If so, don't confuse policies. */ if (!q->root_blkg) return; blk_throtl_drain(q); } /** * blkcg_exit_queue - exit and release blkcg part of request_queue * @q: request_queue being released * * Called from blk_exit_queue(). Responsible for exiting blkcg part. */ void blkcg_exit_queue(struct request_queue *q) { blkg_destroy_all(q); blk_throtl_exit(q); } /* * We cannot support shared io contexts, as we have no mean to support * two tasks with the same ioc in two different groups without major rework * of the main cic data structures. For now we allow a task to change * its cgroup only if it's the only owner of its ioc. */ static int blkcg_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *dst_css; struct io_context *ioc; int ret = 0; /* task_lock() is needed to avoid races with exit_io_context() */ cgroup_taskset_for_each(task, dst_css, tset) { task_lock(task); ioc = task->io_context; if (ioc && atomic_read(&ioc->nr_tasks) > 1) ret = -EINVAL; task_unlock(task); if (ret) break; } return ret; } static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; mutex_lock(&blkcg_pol_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg *blkcg; if (!pol || !pol->cpd_bind_fn) continue; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) if (blkcg->cpd[pol->plid]) pol->cpd_bind_fn(blkcg->cpd[pol->plid]); } mutex_unlock(&blkcg_pol_mutex); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_queue) blk_put_queue(tsk->throttle_queue); tsk->throttle_queue = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .can_attach = blkcg_can_attach, .bind = blkcg_bind, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a request_queue * @q: request_queue of interest * @pol: blkcg policy to activate * * Activate @pol on @q. Requires %GFP_KERNEL context. @q goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @q bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol) { struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; if (blkcg_policy_enabled(q, pol)) return 0; if (queue_is_mq(q)) blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to allocate parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, blkg->blkcg); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, blkg->blkcg); if (pd_prealloc) goto retry; else goto enomem; } blkg->pd[pol->plid] = pd; pd->blkg = blkg; pd->plid = pol->plid; } /* all allocated, init in the same order */ if (pol->pd_init_fn) list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_init_fn(blkg->pd[pol->plid]); if (pol->pd_online_fn) list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_online_fn(blkg->pd[pol->plid]); __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, nothing's initialized yet, free everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue * @q: request_queue of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @q. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { struct blkcg_gq *blkg; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) goto err_unlock; /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto err_free_cpds; blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; if (pol->cpd_init_fn) pol->cpd_init_fn(cpd); } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes) WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { struct blkcg *blkcg; mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); bool __blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; /* consume the flag first */ bio->bi_opf &= ~REQ_CGROUP_PUNT; /* never bounce for the root cgroup */ if (!blkg->parent) return false; spin_lock_bh(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock_bh(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); return true; } /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_cmpxchg(&blkg->delay_start, old, now) == old) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; u64 now = ktime_to_ns(ktime_get()); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { if (atomic_read(&blkg->use_delay)) { blkcg_scale_delay(blkg, now); delay_nsec = max_t(u64, delay_nsec, atomic64_read(&blkg->delay_nsec)); } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 1 second. If there's 10's of seconds worth of delay then * the tasks will be delayed for 1 second for every syscall. */ delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_queue is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct request_queue *q = current->throttle_queue; struct cgroup_subsys_state *css; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!q) return; current->throttle_queue = NULL; current->use_memdelay = false; rcu_read_lock(); css = kthread_blkcg(); if (css) blkcg = css_to_blkcg(css); else blkcg = css_to_blkcg(task_css(current, io_cgrp_id)); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, q); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); blk_put_queue(q); return; out: rcu_read_unlock(); blk_put_queue(q); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @q: the request queue IO was submitted on * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a request_queue at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (!blk_get_queue(q)) return; if (current->throttle_queue) blk_put_queue(current->throttle_queue); current->throttle_queue = q; if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } static int __init blkcg_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_init); module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 938 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | /* * This file implement the Wireless Extensions proc API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * * (As all part of the Linux kernel, this file is GPL) */ /* * The /proc/net/wireless file is a human readable user-space interface * exporting various wireless specific statistics from the wireless devices. * This is the most popular part of the Wireless Extensions ;-) * * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). * The content of the file is basically the content of "struct iw_statistics". */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/wireless.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <net/iw_handler.h> #include <net/wext.h> static void wireless_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { /* Get stats from the driver */ struct iw_statistics *stats = get_wireless_stats(dev); static struct iw_statistics nullstats = {}; /* show device if it's wireless regardless of current stats */ if (!stats) { #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) stats = &nullstats; #endif #ifdef CONFIG_CFG80211 if (dev->ieee80211_ptr) stats = &nullstats; #endif } if (stats) { seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " "%6d %6d %6d\n", dev->name, stats->status, stats->qual.qual, stats->qual.updated & IW_QUAL_QUAL_UPDATED ? '.' : ' ', ((__s32) stats->qual.level) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_LEVEL_UPDATED ? '.' : ' ', ((__s32) stats->qual.noise) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_NOISE_UPDATED ? '.' : ' ', stats->discard.nwid, stats->discard.code, stats->discard.fragment, stats->discard.retries, stats->discard.misc, stats->miss.beacon); if (stats != &nullstats) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; } } /* ---------------------------------------------------------------- */ /* * Print info for /proc/net/wireless (print all entries) */ static int wireless_dev_seq_show(struct seq_file *seq, void *v) { might_sleep(); if (v == SEQ_START_TOKEN) seq_printf(seq, "Inter-| sta-| Quality | Discarded " "packets | Missed | WE\n" " face | tus | link level noise | nwid " "crypt frag retry misc | beacon | %d\n", WIRELESS_EXT); else wireless_seq_printf_stats(seq, v); return 0; } static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; rtnl_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; for_each_netdev(net, dev) if (off++ == *pos) return dev; return NULL; } static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); ++*pos; return v == SEQ_START_TOKEN ? first_net_device(net) : next_net_device(v); } static void wireless_dev_seq_stop(struct seq_file *seq, void *v) { rtnl_unlock(); } static const struct seq_operations wireless_seq_ops = { .start = wireless_dev_seq_start, .next = wireless_dev_seq_next, .stop = wireless_dev_seq_stop, .show = wireless_dev_seq_show, }; int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ if (!proc_create_net("wireless", 0444, net->proc_net, &wireless_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } void __net_exit wext_proc_exit(struct net *net) { remove_proc_entry("wireless", net->proc_net); } |
| 102 109 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002, 2003 Andi Kleen, SuSE Labs. * * Wrappers of assembly checksum functions for x86-64. */ #include <asm/checksum.h> #include <linux/export.h> #include <linux/uaccess.h> #include <asm/smap.h> /** * csum_partial_copy_from_user - Copy and checksum from user space. * @src: source address (user space) * @dst: destination address * @len: number of bytes to be copied. * @isum: initial sum that is added into the result (32bit unfolded) * @errp: set to -EFAULT for an bad source address. * * Returns an 32bit unfolded checksum of the buffer. * src and dst are best aligned to 64bits. */ __wsum csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum isum, int *errp) { might_sleep(); *errp = 0; if (!likely(access_ok(src, len))) goto out_err; /* * Why 6, not 7? To handle odd addresses aligned we * would need to do considerable complications to fix the * checksum which is defined as an 16bit accumulator. The * fix alignment code is primarily for performance * compatibility with 32bit and that will handle odd * addresses slowly too. */ if (unlikely((unsigned long)src & 6)) { while (((unsigned long)src & 6) && len >= 2) { __u16 val16; if (__get_user(val16, (const __u16 __user *)src)) goto out_err; *(__u16 *)dst = val16; isum = (__force __wsum)add32_with_carry( (__force unsigned)isum, val16); src += 2; dst += 2; len -= 2; } } stac(); isum = csum_partial_copy_generic((__force const void *)src, dst, len, isum, errp, NULL); clac(); if (unlikely(*errp)) goto out_err; return isum; out_err: *errp = -EFAULT; memset(dst, 0, len); return isum; } EXPORT_SYMBOL(csum_partial_copy_from_user); /** * csum_partial_copy_to_user - Copy and checksum to user space. * @src: source address * @dst: destination address (user space) * @len: number of bytes to be copied. * @isum: initial sum that is added into the result (32bit unfolded) * @errp: set to -EFAULT for an bad destination address. * * Returns an 32bit unfolded checksum of the buffer. * src and dst are best aligned to 64bits. */ __wsum csum_partial_copy_to_user(const void *src, void __user *dst, int len, __wsum isum, int *errp) { __wsum ret; might_sleep(); if (unlikely(!access_ok(dst, len))) { *errp = -EFAULT; return 0; } if (unlikely((unsigned long)dst & 6)) { while (((unsigned long)dst & 6) && len >= 2) { __u16 val16 = *(__u16 *)src; isum = (__force __wsum)add32_with_carry( (__force unsigned)isum, val16); *errp = __put_user(val16, (__u16 __user *)dst); if (*errp) return isum; src += 2; dst += 2; len -= 2; } } *errp = 0; stac(); ret = csum_partial_copy_generic(src, (void __force *)dst, len, isum, NULL, errp); clac(); return ret; } EXPORT_SYMBOL(csum_partial_copy_to_user); /** * csum_partial_copy_nocheck - Copy and checksum. * @src: source address * @dst: destination address * @len: number of bytes to be copied. * @sum: initial sum that is added into the result (32bit unfolded) * * Returns an 32bit unfolded checksum of the buffer. */ __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum) { return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL); } EXPORT_SYMBOL(csum_partial_copy_nocheck); __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum sum) { __u64 rest, sum64; rest = (__force __u64)htonl(len) + (__force __u64)htons(proto) + (__force __u64)sum; asm(" addq (%[saddr]),%[sum]\n" " adcq 8(%[saddr]),%[sum]\n" " adcq (%[daddr]),%[sum]\n" " adcq 8(%[daddr]),%[sum]\n" " adcq $0,%[sum]\n" : [sum] "=r" (sum64) : "[sum]" (rest), [saddr] "r" (saddr), [daddr] "r" (daddr)); return csum_fold( (__force __wsum)add32_with_carry(sum64 & 0xffffffff, sum64>>32)); } EXPORT_SYMBOL(csum_ipv6_magic); |
| 859 1935 277 1433 919 8 78 3 2 2411 2411 2410 2403 3754 99 474 2574 2521 487 395 2574 2573 2390 168 2573 2407 36 99 99 2120 2403 1475 8 1160 1160 1291 1292 4 4 455 455 455 1024 1019 11 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include <linux/kernel_stat.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> #include <linux/jiffies.h> #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> #include "tick-internal.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of * LVL_SIZE buckets. Each level is driven by its own clock and therefor each * level has a different granularity. * * The level granularity is: LVL_CLK_DIV ^ lvl * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and * therefor the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading * the timers into the lower array levels. The previous 'classic' timer wheel * implementation of the kernel already violated the 'exact' expiry by adding * slack to the expiry time to provide batched expiration. The granularity * levels provide implicit batching. * * This is an optimization of the original timer wheel implementation for the * majority of the timer wheel use cases: timeouts. The vast majority of * timeout timers (networking, disk I/O ...) are canceled before expiry. If * the timeout expires it indicates that normal operation is disturbed, so it * does not matter much whether the timeout comes with a slight delay. * * The only exception to this are networking timers with a small expiry * time. They rely on the granularity. Those fit into the first wheel level, * which has HZ granularity. * * We don't have cascading anymore. timers with a expiry time above the * capacity of the last wheel level are force expired at the maximum timeout * value of the last wheel level. From data sampling we know that the maximum * value observed is 5 days (network connection tracking), so this should not * be an issue. * * The currently chosen array constants values are a good compromise between * array size and granularity. * * This results in the following granularity and range levels: * * HZ 1000 steps * Level Offset Granularity Range * 0 0 1 ms 0 ms - 63 ms * 1 64 8 ms 64 ms - 511 ms * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) * * HZ 300 * Level Offset Granularity Range * 0 0 3 ms 0 ms - 210 ms * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) * * HZ 250 * Level Offset Granularity Range * 0 0 4 ms 0 ms - 255 ms * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) * * HZ 100 * Level Offset Granularity Range * 0 0 10 ms 0 ms - 630 ms * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ /* Clock divisor for the next level */ #define LVL_CLK_SHIFT 3 #define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) #define LVL_CLK_MASK (LVL_CLK_DIV - 1) #define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) #define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) /* * The time start value for each level to select the bucket at enqueue * time. */ #define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) /* Size of each clock level */ #define LVL_BITS 6 #define LVL_SIZE (1UL << LVL_BITS) #define LVL_MASK (LVL_SIZE - 1) #define LVL_OFFS(n) ((n) * LVL_SIZE) /* Level depth */ #if HZ > 100 # define LVL_DEPTH 9 # else # define LVL_DEPTH 8 #endif /* The cutoff (max. capacity of the wheel) */ #define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) #define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) /* * The resulting wheel size. If NOHZ is configured we allocate two * wheels so we have a separate storage for the deferrable timers. */ #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON # define NR_BASES 2 # define BASE_STD 0 # define BASE_DEF 1 #else # define NR_BASES 1 # define BASE_STD 0 # define BASE_DEF 0 #endif struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; #ifdef CONFIG_PREEMPT_RT spinlock_t expiry_lock; atomic_t timer_waiters; #endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; bool is_idle; bool must_forward_clk; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #ifdef CONFIG_NO_HZ_COMMON static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { if (sysctl_timer_migration && tick_nohz_active) static_branch_enable(&timers_migration_enabled); else static_branch_disable(&timers_migration_enabled); } #else static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ static void timer_update_keys(struct work_struct *work) { mutex_lock(&timer_keys_mutex); timers_update_migration(); static_branch_enable(&timers_nohz_active); mutex_unlock(&timer_keys_mutex); } void timers_update_nohz(void) { schedule_work(&timer_update_work); } int timer_migration_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&timer_keys_mutex); ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(); mutex_unlock(&timer_keys_mutex); return ret; } static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); } #else static inline bool is_timers_nohz_active(void) { return false; } #endif /* NO_HZ_COMMON */ static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { int rem; unsigned long original = j; /* * We don't want all cpus firing their timers at once hitting the * same lock or cachelines, so we skew each extra cpu with an extra * 3 jiffies. This 3 jiffies came originally from the mm/ code which * already did this. * The skew is done by adding 3*cpunr, then round, then subtract this * extra offset again. */ j += cpu * 3; rem = j % HZ; /* * If the target jiffie is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. * But never round down if @force_up is set. */ if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; /* * Make sure j is still in the future. Otherwise return the * unmodified value. */ return time_is_after_jiffies(j) ? j : original; } /** * __round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, false); } EXPORT_SYMBOL_GPL(__round_jiffies); /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); /** * __round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, true); } EXPORT_SYMBOL_GPL(__round_jiffies_up); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, true) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), true); } EXPORT_SYMBOL_GPL(round_jiffies_up); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { return __round_jiffies_up_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); static inline unsigned int timer_get_idx(struct timer_list *timer) { return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; } static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | idx << TIMER_ARRAYSHIFT; } /* * Helper function to calculate the array index for a given expiry * time. */ static inline unsigned calc_index(unsigned expires, unsigned lvl) { expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } static int calc_wheel_index(unsigned long expires, unsigned long clk) { unsigned long delta = expires - clk; unsigned int idx; if (delta < LVL_START(1)) { idx = calc_index(expires, 0); } else if (delta < LVL_START(2)) { idx = calc_index(expires, 1); } else if (delta < LVL_START(3)) { idx = calc_index(expires, 2); } else if (delta < LVL_START(4)) { idx = calc_index(expires, 3); } else if (delta < LVL_START(5)) { idx = calc_index(expires, 4); } else if (delta < LVL_START(6)) { idx = calc_index(expires, 5); } else if (delta < LVL_START(7)) { idx = calc_index(expires, 6); } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { idx = calc_index(expires, 7); } else if ((long) delta < 0) { idx = clk & LVL_MASK; } else { /* * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ if (delta >= WHEEL_TIMEOUT_CUTOFF) expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1); } return idx; } /* * Enqueue the timer into the hash bucket, mark it pending in * the bitmap and store the index in the timer flags. */ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, unsigned int idx) { hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); trace_timer_start(timer, timer->expires, timer->flags); } static void __internal_add_timer(struct timer_base *base, struct timer_list *timer) { unsigned int idx; idx = calc_wheel_index(timer->expires, base->clk); enqueue_timer(base, timer, idx); } static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { if (!is_timers_nohz_active()) return; /* * TODO: This wants some optimizing similar to the code below, but we * will do that when we switch from push to pull for deferrable timers. */ if (timer->flags & TIMER_DEFERRABLE) { if (tick_nohz_full_cpu(base->cpu)) wake_up_nohz_cpu(base->cpu); return; } /* * We might have to IPI the remote CPU if the base is idle and the * timer is not deferrable. If the other CPU is on the way to idle * then it can't set base->is_idle as we hold the base lock: */ if (!base->is_idle) return; /* Check whether this is the new first expiring timer: */ if (time_after_eq(timer->expires, base->next_expiry)) return; /* * Set the next expiry time and kick the CPU so it can reevaluate the * wheel: */ if (time_before(timer->expires, base->clk)) { /* * Prevent from forward_timer_base() moving the base->clk * backward */ base->next_expiry = base->clk; } else { base->next_expiry = timer->expires; } wake_up_nohz_cpu(base->cpu); } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { __internal_add_timer(base, timer); trigger_dyntick_cpu(base, timer); } #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static struct debug_obj_descr timer_debug_descr; static void *timer_debug_hint(void *addr) { return ((struct timer_list *) addr)->function; } static bool timer_is_static_object(void *addr) { struct timer_list *timer = addr; return (timer->entry.pprev == NULL && timer->entry.next == TIMER_ENTRY_STATIC); } /* * fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_init(timer, &timer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static void stub_timer(struct timer_list *unused) { WARN_ON(1); } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; case ODEBUG_STATE_ACTIVE: WARN_ON(1); /* fall through */ default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_free(timer, &timer_debug_descr); return true; default: return false; } } /* * fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; default: return false; } } static struct debug_obj_descr timer_debug_descr = { .name = "timer_list", .debug_hint = timer_debug_hint, .is_static_object = timer_is_static_object, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) { debug_object_init(timer, &timer_debug_descr); } static inline void debug_timer_activate(struct timer_list *timer) { debug_object_activate(timer, &timer_debug_descr); } static inline void debug_timer_deactivate(struct timer_list *timer) { debug_object_deactivate(timer, &timer_debug_descr); } static inline void debug_timer_free(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL_GPL(init_timer_on_stack_key); void destroy_timer_on_stack(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_timer_on_stack); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { debug_timer_init(timer); trace_timer_init(timer); } static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); trace_timer_cancel(timer); } static inline void debug_assert_init(struct timer_list *timer) { debug_timer_assert_init(timer); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { timer->entry.pprev = NULL; timer->function = func; timer->flags = flags | raw_smp_processor_id(); lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** * init_timer_key - initialize a timer * @timer: the timer to be initialized * @func: timer callback function * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * * init_timer_key() must be done to a timer prior calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_init(timer); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL(init_timer_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct hlist_node *entry = &timer->entry; debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL; entry->next = LIST_POISON2; } static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { unsigned idx = timer_get_idx(timer); if (!timer_pending(timer)) return 0; if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) __clear_bit(idx, base->pending_map); detach_timer(timer, clear_pending); return 1; } static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); return base; } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = this_cpu_ptr(&timer_bases[BASE_DEF]); return base; } static inline struct timer_base *get_timer_base(u32 tflags) { return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } static inline struct timer_base * get_target_base(struct timer_base *base, unsigned tflags) { #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !(tflags & TIMER_PINNED)) return get_timer_cpu_base(tflags, get_nohz_timer_target()); #endif return get_timer_this_cpu_base(tflags); } static inline void forward_timer_base(struct timer_base *base) { #ifdef CONFIG_NO_HZ_COMMON unsigned long jnow; /* * We only forward the base when we are idle or have just come out of * idle (must_forward_clk logic), and have a delta between base clock * and jiffies. In the common case, run_timers will take care of it. */ if (likely(!base->must_forward_clk)) return; jnow = READ_ONCE(jiffies); base->must_forward_clk = base->is_idle; if ((long)(jnow - base->clk) < 2) return; /* * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ if (time_after(base->next_expiry, jnow)) { base->clk = jnow; } else { if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) return; base->clk = base->next_expiry; } #endif } /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means * that all timers which are tied to this base are locked, and the base itself * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found in the base->vectors array. * * When a timer is migrating then the TIMER_MIGRATING flag is set and we need * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { for (;;) { struct timer_base *base; u32 tf; /* * We need to use READ_ONCE() here, otherwise the compiler * might re-read @tf between the check for TIMER_MIGRATING * and spin_lock(). */ tf = READ_ONCE(timer->flags); if (!(tf & TIMER_MIGRATING)) { base = get_timer_base(tf); raw_spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; raw_spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } #define MOD_TIMER_PENDING_ONLY 0x01 #define MOD_TIMER_REDUCE 0x02 static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { struct timer_base *base, *new_base; unsigned int idx = UINT_MAX; unsigned long clk = 0, flags; int ret = 0; BUG_ON(!timer->function); /* * This is a common optimization triggered by the networking code - if * the timer is re-modified to have the same timeout or ends up in the * same array bucket then just return: */ if (timer_pending(timer)) { /* * The downside of this optimization is that it can result in * larger granularity than you would get from adding a new * timer with this expiry. */ long diff = timer->expires - expires; if (!diff) return 1; if (options & MOD_TIMER_REDUCE && diff <= 0) return 1; /* * We lock timer base and calculate the bucket index right * here. If the timer ends up in the same bucket, then we * just update the expiry time and avoid the whole * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && time_before_eq(timer->expires, expires)) { ret = 1; goto out_unlock; } clk = base->clk; idx = calc_wheel_index(expires, clk); /* * Retrieve and compare the array index of the pending * timer. If it matches set the expiry to the new value so a * subsequent call will exit in the expires check above. */ if (idx == timer_get_idx(timer)) { if (!(options & MOD_TIMER_REDUCE)) timer->expires = expires; else if (time_after(timer->expires, expires)) timer->expires = expires; ret = 1; goto out_unlock; } } else { base = lock_timer_base(timer, &flags); forward_timer_base(base); } ret = detach_if_pending(timer, base, false); if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; new_base = get_target_base(base, timer->flags); if (base != new_base) { /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise del_timer_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); forward_timer_base(base); } } debug_timer_activate(timer); timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance * between calculating 'idx' and possibly switching the base, only * enqueue_timer() and trigger_dyntick_cpu() is required. Otherwise * we need to (re)calculate the wheel index via * internal_add_timer(). */ if (idx != UINT_MAX && clk == base->clk) { enqueue_timer(base, timer, idx); trigger_dyntick_cpu(base, timer); } else { internal_add_timer(base, timer); } out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * mod_timer_pending - modify a pending timer's timeout * @timer: the pending timer to be modified * @expires: new timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), * but will not re-activate and modify already deleted timers. * * It is useful for unserialized use of timers. */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY); } EXPORT_SYMBOL(mod_timer_pending); /** * mod_timer - modify a timer's timeout * @timer: the timer to be modified * @expires: new timeout in jiffies * * mod_timer() is a more efficient way to update the expire field of an * active timer (if the timer is inactive it will be activated) * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_time |