10 2 8 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/reboot.c * * Copyright (C) 2013 Linus Torvalds */ #define pr_fmt(fmt) "reboot: " fmt #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/export.h> #include <linux/kexec.h> #include <linux/kmod.h> #include <linux/kmsg_dump.h> #include <linux/reboot.h> #include <linux/suspend.h> #include <linux/syscalls.h> #include <linux/syscore_ops.h> #include <linux/uaccess.h> /* * this indicates whether you can reboot with ctrl-alt-del: the default is yes */ int C_A_D = 1; struct pid *cad_pid; EXPORT_SYMBOL(cad_pid); #if defined(CONFIG_ARM) #define DEFAULT_REBOOT_MODE = REBOOT_HARD #else #define DEFAULT_REBOOT_MODE #endif enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; enum reboot_mode panic_reboot_mode = REBOOT_UNDEFINED; /* * This variable is used privately to keep track of whether or not * reboot_type is still set to its default value (i.e., reboot= hasn't * been set on the command line). This is needed so that we can * suppress DMI scanning for reboot quirks. Without it, it's * impossible to override a faulty reboot quirk without recompiling. */ int reboot_default = 1; int reboot_cpu; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; /* * If set, this is used for preparing the system to power off. */ void (*pm_power_off_prepare)(void); EXPORT_SYMBOL_GPL(pm_power_off_prepare); /** * emergency_restart - reboot the system * * Without shutting down any hardware or taking any locks * reboot the system. This is called when we know we are in * trouble so this is our best effort to reboot. This is * safe to call in interrupt context. */ void emergency_restart(void) { kmsg_dump(KMSG_DUMP_EMERG); machine_emergency_restart(); } EXPORT_SYMBOL_GPL(emergency_restart); void kernel_restart_prepare(char *cmd) { blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); system_state = SYSTEM_RESTART; usermodehelper_disable(); device_shutdown(); } /** * register_reboot_notifier - Register function to be called at reboot time * @nb: Info about notifier function to be called * * Registers a function with the list of functions * to be called at reboot time. * * Currently always returns zero, as blocking_notifier_chain_register() * always returns zero. */ int register_reboot_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&reboot_notifier_list, nb); } EXPORT_SYMBOL(register_reboot_notifier); /** * unregister_reboot_notifier - Unregister previously registered reboot notifier * @nb: Hook to be unregistered * * Unregisters a previously registered reboot * notifier function. * * Returns zero on success, or %-ENOENT on failure. */ int unregister_reboot_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); } EXPORT_SYMBOL(unregister_reboot_notifier); static void devm_unregister_reboot_notifier(struct device *dev, void *res) { WARN_ON(unregister_reboot_notifier(*(struct notifier_block **)res)); } int devm_register_reboot_notifier(struct device *dev, struct notifier_block *nb) { struct notifier_block **rcnb; int ret; rcnb = devres_alloc(devm_unregister_reboot_notifier, sizeof(*rcnb), GFP_KERNEL); if (!rcnb) return -ENOMEM; ret = register_reboot_notifier(nb); if (!ret) { *rcnb = nb; devres_add(dev, rcnb); } else { devres_free(rcnb); } return ret; } EXPORT_SYMBOL(devm_register_reboot_notifier); /* * Notifier list for kernel code which wants to be called * to restart the system. */ static ATOMIC_NOTIFIER_HEAD(restart_handler_list); /** * register_restart_handler - Register function to be called to reset * the system * @nb: Info about handler function to be called * @nb->priority: Handler priority. Handlers should follow the * following guidelines for setting priorities. * 0: Restart handler of last resort, * with limited restart capabilities * 128: Default restart handler; use if no other * restart handler is expected to be available, * and/or if restart functionality is * sufficient to restart the entire system * 255: Highest priority restart handler, will * preempt all other restart handlers * * Registers a function with code to be called to restart the * system. * * Registered functions will be called from machine_restart as last * step of the restart sequence (if the architecture specific * machine_restart function calls do_kernel_restart - see below * for details). * Registered functions are expected to restart the system immediately. * If more than one function is registered, the restart handler priority * selects which function will be called first. * * Restart handlers are expected to be registered from non-architecture * code, typically from drivers. A typical use case would be a system * where restart functionality is provided through a watchdog. Multiple * restart handlers may exist; for example, one restart handler might * restart the entire system, while another only restarts the CPU. * In such cases, the restart handler which only restarts part of the * hardware is expected to register with low priority to ensure that * it only runs if no other means to restart the system is available. * * Currently always returns zero, as atomic_notifier_chain_register() * always returns zero. */ int register_restart_handler(struct notifier_block *nb) { return atomic_notifier_chain_register(&restart_handler_list, nb); } EXPORT_SYMBOL(register_restart_handler); /** * unregister_restart_handler - Unregister previously registered * restart handler * @nb: Hook to be unregistered * * Unregisters a previously registered restart handler function. * * Returns zero on success, or %-ENOENT on failure. */ int unregister_restart_handler(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&restart_handler_list, nb); } EXPORT_SYMBOL(unregister_restart_handler); /** * do_kernel_restart - Execute kernel restart handler call chain * * Calls functions registered with register_restart_handler. * * Expected to be called from machine_restart as last step of the restart * sequence. * * Restarts the system immediately if a restart handler function has been * registered. Otherwise does nothing. */ void do_kernel_restart(char *cmd) { atomic_notifier_call_chain(&restart_handler_list, reboot_mode, cmd); } void migrate_to_reboot_cpu(void) { /* The boot cpu is always logical cpu 0 */ int cpu = reboot_cpu; cpu_hotplug_disable(); /* Make certain the cpu I'm about to reboot on is online */ if (!cpu_online(cpu)) cpu = cpumask_first(cpu_online_mask); /* Prevent races with other tasks migrating this task */ current->flags |= PF_NO_SETAFFINITY; /* Make certain I only run on the appropriate processor */ set_cpus_allowed_ptr(current, cpumask_of(cpu)); } /** * kernel_restart - reboot the system * @cmd: pointer to buffer containing command to execute for restart * or %NULL * * Shutdown everything and perform a clean reboot. * This is not safe to call in interrupt context. */ void kernel_restart(char *cmd) { kernel_restart_prepare(cmd); migrate_to_reboot_cpu(); syscore_shutdown(); if (!cmd) pr_emerg("Restarting system\n"); else pr_emerg("Restarting system with command '%s'\n", cmd); kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_restart(cmd); } EXPORT_SYMBOL_GPL(kernel_restart); static void kernel_shutdown_prepare(enum system_states state) { blocking_notifier_call_chain(&reboot_notifier_list, (state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL); system_state = state; usermodehelper_disable(); device_shutdown(); } /** * kernel_halt - halt the system * * Shutdown everything and perform a clean system halt. */ void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); migrate_to_reboot_cpu(); syscore_shutdown(); pr_emerg("System halted\n"); kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_halt(); } EXPORT_SYMBOL_GPL(kernel_halt); /** * kernel_power_off - power_off the system * * Shutdown everything and perform a clean system power_off. */ void kernel_power_off(void) { kernel_shutdown_prepare(SYSTEM_POWER_OFF); if (pm_power_off_prepare) pm_power_off_prepare(); migrate_to_reboot_cpu(); syscore_shutdown(); pr_emerg("Power down\n"); kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_power_off(); } EXPORT_SYMBOL_GPL(kernel_power_off); DEFINE_MUTEX(system_transition_mutex); /* * Reboot system call: for obvious reasons only root may call it, * and even root needs to set up some magic numbers in the registers * so that some mistake won't make this reboot the whole machine. * You can also set the meaning of the ctrl-alt-del-key here. * * reboot doesn't sync: do that yourself before calling this. */ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg) { struct pid_namespace *pid_ns = task_active_pid_ns(current); char buffer[256]; int ret = 0; /* We only trust the superuser with rebooting the system. */ if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT)) return -EPERM; /* For safety, we require "magic" arguments. */ if (magic1 != LINUX_REBOOT_MAGIC1 || (magic2 != LINUX_REBOOT_MAGIC2 && magic2 != LINUX_REBOOT_MAGIC2A && magic2 != LINUX_REBOOT_MAGIC2B && magic2 != LINUX_REBOOT_MAGIC2C)) return -EINVAL; /* * If pid namespaces are enabled and the current task is in a child * pid_namespace, the command is handled by reboot_pid_ns() which will * call do_exit(). */ ret = reboot_pid_ns(pid_ns, cmd); if (ret) return ret; /* Instead of trying to make the power_off code look like * halt when pm_power_off is not set do it the easy way. */ if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) cmd = LINUX_REBOOT_CMD_HALT; mutex_lock(&system_transition_mutex); switch (cmd) { case LINUX_REBOOT_CMD_RESTART: kernel_restart(NULL); break; case LINUX_REBOOT_CMD_CAD_ON: C_A_D = 1; break; case LINUX_REBOOT_CMD_CAD_OFF: C_A_D = 0; break; case LINUX_REBOOT_CMD_HALT: kernel_halt(); do_exit(0); panic("cannot halt"); case LINUX_REBOOT_CMD_POWER_OFF: kernel_power_off(); do_exit(0); break; case LINUX_REBOOT_CMD_RESTART2: ret = strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1); if (ret < 0) { ret = -EFAULT; break; } buffer[sizeof(buffer) - 1] = '\0'; kernel_restart(buffer); break; #ifdef CONFIG_KEXEC_CORE case LINUX_REBOOT_CMD_KEXEC: ret = kernel_kexec(); break; #endif #ifdef CONFIG_HIBERNATION case LINUX_REBOOT_CMD_SW_SUSPEND: ret = hibernate(); break; #endif default: ret = -EINVAL; break; } mutex_unlock(&system_transition_mutex); return ret; } static void deferred_cad(struct work_struct *dummy) { kernel_restart(NULL); } /* * This function gets called by ctrl-alt-del - ie the keyboard interrupt. * As it's called within an interrupt, it may NOT sync: the only choice * is whether to reboot at once, or just ignore the ctrl-alt-del. */ void ctrl_alt_del(void) { static DECLARE_WORK(cad_work, deferred_cad); if (C_A_D) schedule_work(&cad_work); else kill_cad_pid(SIGINT, 1); } char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; static const char reboot_cmd[] = "/sbin/reboot"; static int run_cmd(const char *cmd) { char **argv; static char *envp[] = { "HOME=/", "PATH=/sbin:/bin:/usr/sbin:/usr/bin", NULL }; int ret; argv = argv_split(GFP_KERNEL, cmd, NULL); if (argv) { ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); argv_free(argv); } else { ret = -ENOMEM; } return ret; } static int __orderly_reboot(void) { int ret; ret = run_cmd(reboot_cmd); if (ret) { pr_warn("Failed to start orderly reboot: forcing the issue\n"); emergency_sync(); kernel_restart(NULL); } return ret; } static int __orderly_poweroff(bool force) { int ret; ret = run_cmd(poweroff_cmd); if (ret && force) { pr_warn("Failed to start orderly shutdown: forcing the issue\n"); /* * I guess this should try to kick off some daemon to sync and * poweroff asap. Or not even bother syncing if we're doing an * emergency shutdown? */ emergency_sync(); kernel_power_off(); } return ret; } static bool poweroff_force; static void poweroff_work_func(struct work_struct *work) { __orderly_poweroff(poweroff_force); } static DECLARE_WORK(poweroff_work, poweroff_work_func); /** * orderly_poweroff - Trigger an orderly system poweroff * @force: force poweroff if command execution fails * * This may be called from any context to trigger a system shutdown. * If the orderly shutdown fails, it will force an immediate shutdown. */ void orderly_poweroff(bool force) { if (force) /* do not override the pending "true" */ poweroff_force = true; schedule_work(&poweroff_work); } EXPORT_SYMBOL_GPL(orderly_poweroff); static void reboot_work_func(struct work_struct *work) { __orderly_reboot(); } static DECLARE_WORK(reboot_work, reboot_work_func); /** * orderly_reboot - Trigger an orderly system reboot * * This may be called from any context to trigger a system reboot. * If the orderly reboot fails, it will force an immediate reboot. */ void orderly_reboot(void) { schedule_work(&reboot_work); } EXPORT_SYMBOL_GPL(orderly_reboot); /** * hw_failure_emergency_poweroff_func - emergency poweroff work after a known delay * @work: work_struct associated with the emergency poweroff function * * This function is called in very critical situations to force * a kernel poweroff after a configurable timeout value. */ static void hw_failure_emergency_poweroff_func(struct work_struct *work) { /* * We have reached here after the emergency shutdown waiting period has * expired. This means orderly_poweroff has not been able to shut off * the system for some reason. * * Try to shut down the system immediately using kernel_power_off * if populated */ pr_emerg("Hardware protection timed-out. Trying forced poweroff\n"); kernel_power_off(); /* * Worst of the worst case trigger emergency restart */ pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n"); emergency_restart(); } static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work, hw_failure_emergency_poweroff_func); /** * hw_failure_emergency_poweroff - Trigger an emergency system poweroff * * This may be called from any critical situation to trigger a system shutdown * after a given period of time. If time is negative this is not scheduled. */ static void hw_failure_emergency_poweroff(int poweroff_delay_ms) { if (poweroff_delay_ms <= 0) return; schedule_delayed_work(&hw_failure_emergency_poweroff_work, msecs_to_jiffies(poweroff_delay_ms)); } /** * hw_protection_shutdown - Trigger an emergency system poweroff * * @reason: Reason of emergency shutdown to be printed. * @ms_until_forced: Time to wait for orderly shutdown before tiggering a * forced shudown. Negative value disables the forced * shutdown. * * Initiate an emergency system shutdown in order to protect hardware from * further damage. Usage examples include a thermal protection or a voltage or * current regulator failures. * NOTE: The request is ignored if protection shutdown is already pending even * if the previous request has given a large timeout for forced shutdown. * Can be called from any context. */ void hw_protection_shutdown(const char *reason, int ms_until_forced) { static atomic_t allow_proceed = ATOMIC_INIT(1); pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason); /* Shutdown should be initiated only once. */ if (!atomic_dec_and_test(&allow_proceed)) return; /* * Queue a backup emergency shutdown in the event of * orderly_poweroff failure */ hw_failure_emergency_poweroff(ms_until_forced); orderly_poweroff(true); } EXPORT_SYMBOL_GPL(hw_protection_shutdown); static int __init reboot_setup(char *str) { for (;;) { enum reboot_mode *mode; /* * Having anything passed on the command line via * reboot= will cause us to disable DMI checking * below. */ reboot_default = 0; if (!strncmp(str, "panic_", 6)) { mode = &panic_reboot_mode; str += 6; } else { mode = &reboot_mode; } switch (*str) { case 'w': *mode = REBOOT_WARM; break; case 'c': *mode = REBOOT_COLD; break; case 'h': *mode = REBOOT_HARD; break; case 's': /* * reboot_cpu is s[mp]#### with #### being the processor * to be used for rebooting. Skip 's' or 'smp' prefix. */ str += str[1] == 'm' && str[2] == 'p' ? 3 : 1; if (isdigit(str[0])) { int cpu = simple_strtoul(str, NULL, 0); if (cpu >= num_possible_cpus()) { pr_err("Ignoring the CPU number in reboot= option. " "CPU %d exceeds possible cpu number %d\n", cpu, num_possible_cpus()); break; } reboot_cpu = cpu; } else *mode = REBOOT_SOFT; break; case 'g': *mode = REBOOT_GPIO; break; case 'b': case 'a': case 'k': case 't': case 'e': case 'p': reboot_type = *str; break; case 'f': reboot_force = 1; break; } str = strchr(str, ','); if (str) str++; else break; } return 1; } __setup("reboot=", reboot_setup); #ifdef CONFIG_SYSFS #define REBOOT_COLD_STR "cold" #define REBOOT_WARM_STR "warm" #define REBOOT_HARD_STR "hard" #define REBOOT_SOFT_STR "soft" #define REBOOT_GPIO_STR "gpio" #define REBOOT_UNDEFINED_STR "undefined" #define BOOT_TRIPLE_STR "triple" #define BOOT_KBD_STR "kbd" #define BOOT_BIOS_STR "bios" #define BOOT_ACPI_STR "acpi" #define BOOT_EFI_STR "efi" #define BOOT_PCI_STR "pci" static ssize_t mode_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *val; switch (reboot_mode) { case REBOOT_COLD: val = REBOOT_COLD_STR; break; case REBOOT_WARM: val = REBOOT_WARM_STR; break; case REBOOT_HARD: val = REBOOT_HARD_STR; break; case REBOOT_SOFT: val = REBOOT_SOFT_STR; break; case REBOOT_GPIO: val = REBOOT_GPIO_STR; break; default: val = REBOOT_UNDEFINED_STR; } return sprintf(buf, "%s\n", val); } static ssize_t mode_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { if (!capable(CAP_SYS_BOOT)) return -EPERM; if (!strncmp(buf, REBOOT_COLD_STR, strlen(REBOOT_COLD_STR))) reboot_mode = REBOOT_COLD; else if (!strncmp(buf, REBOOT_WARM_STR, strlen(REBOOT_WARM_STR))) reboot_mode = REBOOT_WARM; else if (!strncmp(buf, REBOOT_HARD_STR, strlen(REBOOT_HARD_STR))) reboot_mode = REBOOT_HARD; else if (!strncmp(buf, REBOOT_SOFT_STR, strlen(REBOOT_SOFT_STR))) reboot_mode = REBOOT_SOFT; else if (!strncmp(buf, REBOOT_GPIO_STR, strlen(REBOOT_GPIO_STR))) reboot_mode = REBOOT_GPIO; else return -EINVAL; reboot_default = 0; return count; } static struct kobj_attribute reboot_mode_attr = __ATTR_RW(mode); #ifdef CONFIG_X86 static ssize_t force_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", reboot_force); } static ssize_t force_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { bool res; if (!capable(CAP_SYS_BOOT)) return -EPERM; if (kstrtobool(buf, &res)) return -EINVAL; reboot_default = 0; reboot_force = res; return count; } static struct kobj_attribute reboot_force_attr = __ATTR_RW(force); static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *val; switch (reboot_type) { case BOOT_TRIPLE: val = BOOT_TRIPLE_STR; break; case BOOT_KBD: val = BOOT_KBD_STR; break; case BOOT_BIOS: val = BOOT_BIOS_STR; break; case BOOT_ACPI: val = BOOT_ACPI_STR; break; case BOOT_EFI: val = BOOT_EFI_STR; break; case BOOT_CF9_FORCE: val = BOOT_PCI_STR; break; default: val = REBOOT_UNDEFINED_STR; } return sprintf(buf, "%s\n", val); } static ssize_t type_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { if (!capable(CAP_SYS_BOOT)) return -EPERM; if (!strncmp(buf, BOOT_TRIPLE_STR, strlen(BOOT_TRIPLE_STR))) reboot_type = BOOT_TRIPLE; else if (!strncmp(buf, BOOT_KBD_STR, strlen(BOOT_KBD_STR))) reboot_type = BOOT_KBD; else if (!strncmp(buf, BOOT_BIOS_STR, strlen(BOOT_BIOS_STR))) reboot_type = BOOT_BIOS; else if (!strncmp(buf, BOOT_ACPI_STR, strlen(BOOT_ACPI_STR))) reboot_type = BOOT_ACPI; else if (!strncmp(buf, BOOT_EFI_STR, strlen(BOOT_EFI_STR))) reboot_type = BOOT_EFI; else if (!strncmp(buf, BOOT_PCI_STR, strlen(BOOT_PCI_STR))) reboot_type = BOOT_CF9_FORCE; else return -EINVAL; reboot_default = 0; return count; } static struct kobj_attribute reboot_type_attr = __ATTR_RW(type); #endif #ifdef CONFIG_SMP static ssize_t cpu_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", reboot_cpu); } static ssize_t cpu_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int cpunum; int rc; if (!capable(CAP_SYS_BOOT)) return -EPERM; rc = kstrtouint(buf, 0, &cpunum); if (rc) return rc; if (cpunum >= num_possible_cpus()) return -ERANGE; reboot_default = 0; reboot_cpu = cpunum; return count; } static struct kobj_attribute reboot_cpu_attr = __ATTR_RW(cpu); #endif static struct attribute *reboot_attrs[] = { &reboot_mode_attr.attr, #ifdef CONFIG_X86 &reboot_force_attr.attr, &reboot_type_attr.attr, #endif #ifdef CONFIG_SMP &reboot_cpu_attr.attr, #endif NULL, }; static const struct attribute_group reboot_attr_group = { .attrs = reboot_attrs, }; static int __init reboot_ksysfs_init(void) { struct kobject *reboot_kobj; int ret; reboot_kobj = kobject_create_and_add("reboot", kernel_kobj); if (!reboot_kobj) return -ENOMEM; ret = sysfs_create_group(reboot_kobj, &reboot_attr_group); if (ret) { kobject_put(reboot_kobj); return ret; } return 0; } late_initcall(reboot_ksysfs_init); #endif
36 23 17 24 36 396 395 20 271 249 7 7 34 33 237 13 77 78 79 79 497 18 16 76 77 77 61 5 184 13 289 287 2 5 7 32 16 48 4 4 4 4 6 6 77 6 68 18 22 4 2 18 50 19 50 50 50 31 19 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/cache.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/kernel.h> #include <linux/pid_namespace.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/completion.h> #include <linux/poll.h> #include <linux/printk.h> #include <linux/file.h> #include <linux/limits.h> #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/mount.h> #include <linux/bug.h> #include <linux/uaccess.h> #include "internal.h" static void proc_evict_inode(struct inode *inode) { struct proc_dir_entry *de; struct ctl_table_header *head; struct proc_inode *ei = PROC_I(inode); truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Stop tracking associated processes */ if (ei->pid) { proc_pid_evict_inode(ei); ei->pid = NULL; } /* Let go of any associated proc directory entry */ de = ei->pde; if (de) { pde_put(de); ei->pde = NULL; } head = ei->sysctl; if (head) { RCU_INIT_POINTER(ei->sysctl, NULL); proc_sys_evict_inode(inode, head); } } static struct kmem_cache *proc_inode_cachep __ro_after_init; static struct kmem_cache *pde_opener_cache __ro_after_init; static struct inode *proc_alloc_inode(struct super_block *sb) { struct proc_inode *ei; ei = kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL); if (!ei) return NULL; ei->pid = NULL; ei->fd = 0; ei->op.proc_get_link = NULL; ei->pde = NULL; ei->sysctl = NULL; ei->sysctl_entry = NULL; INIT_HLIST_NODE(&ei->sibling_inodes); ei->ns_ops = NULL; return &ei->vfs_inode; } static void proc_free_inode(struct inode *inode) { kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } static void init_once(void *foo) { struct proc_inode *ei = (struct proc_inode *) foo; inode_init_once(&ei->vfs_inode); } void __init proc_init_kmemcache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_ACCOUNT| SLAB_PANIC), init_once); pde_opener_cache = kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0, SLAB_ACCOUNT|SLAB_PANIC, NULL); proc_dir_entry_cache = kmem_cache_create_usercopy( "proc_dir_entry", SIZEOF_PDE, 0, SLAB_PANIC, offsetof(struct proc_dir_entry, inline_name), SIZEOF_PDE_INLINE_NAME, NULL); BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE); } void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock) { struct inode *inode; struct proc_inode *ei; struct hlist_node *node; struct super_block *old_sb = NULL; rcu_read_lock(); for (;;) { struct super_block *sb; node = hlist_first_rcu(inodes); if (!node) break; ei = hlist_entry(node, struct proc_inode, sibling_inodes); spin_lock(lock); hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(lock); inode = &ei->vfs_inode; sb = inode->i_sb; if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active)) continue; inode = igrab(inode); rcu_read_unlock(); if (sb != old_sb) { if (old_sb) deactivate_super(old_sb); old_sb = sb; } if (unlikely(!inode)) { rcu_read_lock(); continue; } if (S_ISDIR(inode->i_mode)) { struct dentry *dir = d_find_any_alias(inode); if (dir) { d_invalidate(dir); dput(dir); } } else { struct dentry *dentry; while ((dentry = d_find_alias(inode))) { d_invalidate(dentry); dput(dentry); } } iput(inode); rcu_read_lock(); } rcu_read_unlock(); if (old_sb) deactivate_super(old_sb); } static inline const char *hidepid2str(enum proc_hidepid v) { switch (v) { case HIDEPID_OFF: return "off"; case HIDEPID_NO_ACCESS: return "noaccess"; case HIDEPID_INVISIBLE: return "invisible"; case HIDEPID_NOT_PTRACEABLE: return "ptraceable"; } WARN_ONCE(1, "bad hide_pid value: %d\n", v); return "unknown"; } static int proc_show_options(struct seq_file *seq, struct dentry *root) { struct proc_fs_info *fs_info = proc_sb_info(root->d_sb); if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid)); if (fs_info->hide_pid != HIDEPID_OFF) seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid)); if (fs_info->pidonly != PROC_PIDONLY_OFF) seq_printf(seq, ",subset=pid"); return 0; } const struct super_operations proc_sops = { .alloc_inode = proc_alloc_inode, .free_inode = proc_free_inode, .drop_inode = generic_delete_inode, .evict_inode = proc_evict_inode, .statfs = simple_statfs, .show_options = proc_show_options, }; enum {BIAS = -1U<<31}; static inline int use_pde(struct proc_dir_entry *pde) { return likely(atomic_inc_unless_negative(&pde->in_use)); } static void unuse_pde(struct proc_dir_entry *pde) { if (unlikely(atomic_dec_return(&pde->in_use) == BIAS)) complete(pde->pde_unload_completion); } /* pde is locked on entry, unlocked on exit */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) __releases(&pde->pde_unload_lock) { /* * close() (proc_reg_release()) can't delete an entry and proceed: * ->release hook needs to be available at the right moment. * * rmmod (remove_proc_entry() et al) can't delete an entry and proceed: * "struct file" needs to be available at the right moment. * * Therefore, first process to enter this function does ->release() and * signals its completion to the other process which does nothing. */ if (pdeo->closing) { /* somebody else is doing that, just wait */ DECLARE_COMPLETION_ONSTACK(c); pdeo->c = &c; spin_unlock(&pde->pde_unload_lock); wait_for_completion(&c); } else { struct file *file; struct completion *c; pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); file = pdeo->file; pde->proc_ops->proc_release(file_inode(file), file); spin_lock(&pde->pde_unload_lock); /* After ->release. */ list_del(&pdeo->lh); c = pdeo->c; spin_unlock(&pde->pde_unload_lock); if (unlikely(c)) complete(c); kmem_cache_free(pde_opener_cache, pdeo); } } void proc_entry_rundown(struct proc_dir_entry *de) { DECLARE_COMPLETION_ONSTACK(c); /* Wait until all existing callers into module are done. */ de->pde_unload_completion = &c; if (atomic_add_return(BIAS, &de->in_use) != BIAS) wait_for_completion(&c); /* ->pde_openers list can't grow from now on. */ spin_lock(&de->pde_unload_lock); while (!list_empty(&de->pde_openers)) { struct pde_opener *pdeo; pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh); close_pdeo(de, pdeo); spin_lock(&de->pde_unload_lock); } spin_unlock(&de->pde_unload_lock); } static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) { struct proc_dir_entry *pde = PDE(file_inode(file)); loff_t rv = -EINVAL; if (pde_is_permanent(pde)) { return pde->proc_ops->proc_lseek(file, offset, whence); } else if (use_pde(pde)) { rv = pde->proc_ops->proc_lseek(file, offset, whence); unuse_pde(pde); } return rv; } static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp)); ssize_t ret; if (pde_is_permanent(pde)) return pde->proc_ops->proc_read_iter(iocb, iter); if (!use_pde(pde)) return -EIO; ret = pde->proc_ops->proc_read_iter(iocb, iter); unuse_pde(pde); return ret; } static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos) { typeof_member(struct proc_ops, proc_read) read; read = pde->proc_ops->proc_read; if (read) return read(file, buf, count, ppos); return -EIO; } static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (pde_is_permanent(pde)) { return pde_read(pde, file, buf, count, ppos); } else if (use_pde(pde)) { rv = pde_read(pde, file, buf, count, ppos); unuse_pde(pde); } return rv; } static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos) { typeof_member(struct proc_ops, proc_write) write; write = pde->proc_ops->proc_write; if (write) return write(file, buf, count, ppos); return -EIO; } static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (pde_is_permanent(pde)) { return pde_write(pde, file, buf, count, ppos); } else if (use_pde(pde)) { rv = pde_write(pde, file, buf, count, ppos); unuse_pde(pde); } return rv; } static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts) { typeof_member(struct proc_ops, proc_poll) poll; poll = pde->proc_ops->proc_poll; if (poll) return poll(file, pts); return DEFAULT_POLLMASK; } static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) { struct proc_dir_entry *pde = PDE(file_inode(file)); __poll_t rv = DEFAULT_POLLMASK; if (pde_is_permanent(pde)) { return pde_poll(pde, file, pts); } else if (use_pde(pde)) { rv = pde_poll(pde, file, pts); unuse_pde(pde); } return rv; } static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) { typeof_member(struct proc_ops, proc_ioctl) ioctl; ioctl = pde->proc_ops->proc_ioctl; if (ioctl) return ioctl(file, cmd, arg); return -ENOTTY; } static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (pde_is_permanent(pde)) { return pde_ioctl(pde, file, cmd, arg); } else if (use_pde(pde)) { rv = pde_ioctl(pde, file, cmd, arg); unuse_pde(pde); } return rv; } #ifdef CONFIG_COMPAT static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) { typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl; compat_ioctl = pde->proc_ops->proc_compat_ioctl; if (compat_ioctl) return compat_ioctl(file, cmd, arg); return -ENOTTY; } static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (pde_is_permanent(pde)) { return pde_compat_ioctl(pde, file, cmd, arg); } else if (use_pde(pde)) { rv = pde_compat_ioctl(pde, file, cmd, arg); unuse_pde(pde); } return rv; } #endif static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma) { typeof_member(struct proc_ops, proc_mmap) mmap; mmap = pde->proc_ops->proc_mmap; if (mmap) return mmap(file, vma); return -EIO; } static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) { struct proc_dir_entry *pde = PDE(file_inode(file)); int rv = -EIO; if (pde_is_permanent(pde)) { return pde_mmap(pde, file, vma); } else if (use_pde(pde)) { rv = pde_mmap(pde, file, vma); unuse_pde(pde); } return rv; } static unsigned long pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { typeof_member(struct proc_ops, proc_get_unmapped_area) get_area; get_area = pde->proc_ops->proc_get_unmapped_area; #ifdef CONFIG_MMU if (!get_area) get_area = current->mm->get_unmapped_area; #endif if (get_area) return get_area(file, orig_addr, len, pgoff, flags); return orig_addr; } static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct proc_dir_entry *pde = PDE(file_inode(file)); unsigned long rv = -EIO; if (pde_is_permanent(pde)) { return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); } else if (use_pde(pde)) { rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); unuse_pde(pde); } return rv; } static int proc_reg_open(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); int rv = 0; typeof_member(struct proc_ops, proc_open) open; typeof_member(struct proc_ops, proc_release) release; struct pde_opener *pdeo; if (pde_is_permanent(pde)) { open = pde->proc_ops->proc_open; if (open) rv = open(inode, file); return rv; } /* * Ensure that * 1) PDE's ->release hook will be called no matter what * either normally by close()/->release, or forcefully by * rmmod/remove_proc_entry. * * 2) rmmod isn't blocked by opening file in /proc and sitting on * the descriptor (including "rmmod foo </proc/foo" scenario). * * Save every "struct file" with custom ->release hook. */ if (!use_pde(pde)) return -ENOENT; release = pde->proc_ops->proc_release; if (release) { pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); if (!pdeo) { rv = -ENOMEM; goto out_unuse; } } open = pde->proc_ops->proc_open; if (open) rv = open(inode, file); if (release) { if (rv == 0) { /* To know what to release. */ pdeo->file = file; pdeo->closing = false; pdeo->c = NULL; spin_lock(&pde->pde_unload_lock); list_add(&pdeo->lh, &pde->pde_openers); spin_unlock(&pde->pde_unload_lock); } else kmem_cache_free(pde_opener_cache, pdeo); } out_unuse: unuse_pde(pde); return rv; } static int proc_reg_release(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); struct pde_opener *pdeo; if (pde_is_permanent(pde)) { typeof_member(struct proc_ops, proc_release) release; release = pde->proc_ops->proc_release; if (release) { return release(inode, file); } return 0; } spin_lock(&pde->pde_unload_lock); list_for_each_entry(pdeo, &pde->pde_openers, lh) { if (pdeo->file == file) { close_pdeo(pde, pdeo); return 0; } } spin_unlock(&pde->pde_unload_lock); return 0; } static const struct file_operations proc_reg_file_ops = { .llseek = proc_reg_llseek, .read = proc_reg_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; static const struct file_operations proc_iter_file_ops = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, .write = proc_reg_write, .splice_read = generic_file_splice_read, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; #ifdef CONFIG_COMPAT static const struct file_operations proc_reg_file_ops_compat = { .llseek = proc_reg_llseek, .read = proc_reg_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .compat_ioctl = proc_reg_compat_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; static const struct file_operations proc_iter_file_ops_compat = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, .splice_read = generic_file_splice_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .compat_ioctl = proc_reg_compat_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; #endif static void proc_put_link(void *p) { unuse_pde(p); } static const char *proc_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct proc_dir_entry *pde = PDE(inode); if (!use_pde(pde)) return ERR_PTR(-EINVAL); set_delayed_call(done, proc_put_link, pde); return pde->data; } const struct inode_operations proc_link_inode_operations = { .get_link = proc_get_link, }; struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) { struct inode *inode = new_inode(sb); if (!inode) { pde_put(de); return NULL; } inode->i_ino = de->low_ino; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); PROC_I(inode)->pde = de; if (is_empty_pde(de)) { make_empty_dir_inode(inode); return inode; } if (de->mode) { inode->i_mode = de->mode; inode->i_uid = de->uid; inode->i_gid = de->gid; } if (de->size) inode->i_size = de->size; if (de->nlink) set_nlink(inode, de->nlink); if (S_ISREG(inode->i_mode)) { inode->i_op = de->proc_iops; if (de->proc_ops->proc_read_iter) inode->i_fop = &proc_iter_file_ops; else inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT if (de->proc_ops->proc_compat_ioctl) { if (de->proc_ops->proc_read_iter) inode->i_fop = &proc_iter_file_ops_compat; else inode->i_fop = &proc_reg_file_ops_compat; } #endif } else if (S_ISDIR(inode->i_mode)) { inode->i_op = de->proc_iops; inode->i_fop = de->proc_dir_ops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = de->proc_iops; inode->i_fop = NULL; } else { BUG(); } return inode; }
166 165 166 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 fragment reassembly for connection tracking * * Copyright (C)2004 USAGI/WIDE Project * * Author: * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> * * Based on: net/ipv6/reassembly.c */ #define pr_fmt(fmt) "IPv6-nf: " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <net/ipv6_frag.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #include <linux/sysctl.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/kernel.h> #include <linux/module.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netns/generic.h> static const char nf_frags_cache_name[] = "nf-frags"; unsigned int nf_frag_pernet_id __read_mostly; static struct inet_frags nf_frags; static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net) { return net_generic(net, nf_frag_pernet_id); } #ifdef CONFIG_SYSCTL static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_frag6_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "nf_conntrack_frag6_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { } }; static int nf_ct_frag6_sysctl_register(struct net *net) { struct nft_ct_frag6_pernet *nf_frag; struct ctl_table *table; struct ctl_table_header *hdr; table = nf_ct_frag6_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; } nf_frag = nf_frag_pernet(net); table[0].data = &nf_frag->fqdir->timeout; table[1].data = &nf_frag->fqdir->low_thresh; table[1].extra2 = &nf_frag->fqdir->high_thresh; table[2].data = &nf_frag->fqdir->high_thresh; table[2].extra1 = &nf_frag->fqdir->low_thresh; table[2].extra2 = &nf_frag->fqdir->high_thresh; hdr = register_net_sysctl(net, "net/netfilter", table); if (hdr == NULL) goto err_reg; nf_frag->nf_frag_frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); struct ctl_table *table; table = nf_frag->nf_frag_frags_hdr->ctl_table_arg; unregister_net_sysctl_table(nf_frag->nf_frag_frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else static int nf_ct_frag6_sysctl_register(struct net *net) { return 0; } static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { } #endif static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev); static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); } static void nf_ct_frag6_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; fq = container_of(frag, struct frag_queue, q); ip6frag_expire_frag_queue(fq->q.fqdir->net, fq); } /* Creation primitives. */ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, const struct ipv6hdr *hdr, int iif) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); struct frag_v6_compare_key key = { .id = id, .saddr = hdr->saddr, .daddr = hdr->daddr, .user = user, .iif = iif, }; struct inet_frag_queue *q; q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; return container_of(q, struct frag_queue, q); } static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, const struct frag_hdr *fhdr, int nhoff) { unsigned int payload_len; struct net_device *dev; struct sk_buff *prev; int offset, end, err; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) { pr_debug("Already completed\n"); goto err; } payload_len = ntohs(ipv6_hdr(skb)->payload_len); offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (payload_len - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { pr_debug("offset is too large.\n"); return -EINVAL; } ecn = ip6_frag_ecn(ipv6_hdr(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) { const unsigned char *nh = skb_network_header(skb); skb->csum = csum_sub(skb->csum, csum_partial(nh, (u8 *)(fhdr + 1) - nh, 0)); } /* Is this the final fragment? */ if (!(fhdr->frag_off & htons(IP6_MF))) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) { pr_debug("already received last fragment\n"); goto err; } fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. * Required by the RFC. */ if (end & 0x7) { /* RFC2460 says always send parameter problem in * this case. -DaveM */ pr_debug("end of fragment not rounded to 8 bytes.\n"); inet_frag_kill(&fq->q); return -EPROTO; } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) { pr_debug("last packet already reached.\n"); goto err; } fq->q.len = end; } } if (end == offset) goto err; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) { pr_debug("queue: message is too short.\n"); goto err; } if (pskb_trim_rcsum(skb, end - offset)) { pr_debug("Can't trim\n"); goto err; } /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); prev = fq->q.fragments_tail; err = inet_frag_queue_insert(&fq->q, skb, offset, end); if (err) { if (err == IPFRAG_DUP) { /* No error for duplicates, pretend they got queued. */ kfree_skb(skb); return -EINPROGRESS; } goto insert_error; } if (dev) fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; add_frag_mem_limit(fq->q.fqdir, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. */ if (offset == 0) { fq->nhoffset = nhoff; fq->q.flags |= INET_FRAG_FIRST_IN; } if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; err = nf_ct_frag6_reasm(fq, skb, prev, dev); skb->_skb_refdst = orefdst; /* After queue has assumed skb ownership, only 0 or * -EINPROGRESS must be returned. */ return err ? -EINPROGRESS : 0; } skb_dst_drop(skb); return -EINPROGRESS; insert_error: inet_frag_kill(&fq->q); err: skb_dst_drop(skb); return -EINVAL; } /* * Check if this packet is complete. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) { void *reasm_data; int payload_len; u8 ecn; inet_frag_kill(&fq->q); ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) goto err; reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto err; payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); goto err; } /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; memmove(skb->head + sizeof(struct frag_hdr), skb->head, (skb->data - skb->head) - sizeof(struct frag_hdr)); skb->mac_header += sizeof(struct frag_hdr); skb->network_header += sizeof(struct frag_hdr); skb_reset_transport_header(skb); inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->ignore_df = 1; skb->dev = dev; ipv6_hdr(skb)->payload_len = htons(payload_len); ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_partial(skb_network_header(skb), skb_network_header_len(skb), skb->csum); fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; return 0; err: inet_frag_kill(&fq->q); return -EINVAL; } /* * find the header just before Fragment Header. * * if success return 0 and set ... * (*prevhdrp): the value of "Next Header Field" in the header * just before Fragment Header. * (*prevhoff): the offset of "Next Header Field" in the header * just before Fragment Header. * (*fhoff) : the offset of Fragment Header. * * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c * */ static int find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) { u8 nexthdr = ipv6_hdr(skb)->nexthdr; const int netoff = skb_network_offset(skb); u8 prev_nhoff = netoff + offsetof(struct ipv6hdr, nexthdr); int start = netoff + sizeof(struct ipv6hdr); int len = skb->len - start; u8 prevhdr = NEXTHDR_IPV6; while (nexthdr != NEXTHDR_FRAGMENT) { struct ipv6_opt_hdr hdr; int hdrlen; if (!ipv6_ext_hdr(nexthdr)) { return -1; } if (nexthdr == NEXTHDR_NONE) { pr_debug("next header is none\n"); return -1; } if (len < (int)sizeof(struct ipv6_opt_hdr)) { pr_debug("too short\n"); return -1; } if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) BUG(); if (nexthdr == NEXTHDR_AUTH) hdrlen = ipv6_authlen(&hdr); else hdrlen = ipv6_optlen(&hdr); prevhdr = nexthdr; prev_nhoff = start; nexthdr = hdr.nexthdr; len -= hdrlen; start += hdrlen; } if (len < 0) return -1; *prevhdrp = prevhdr; *prevhoff = prev_nhoff; *fhoff = start; return 0; } int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; u8 nexthdr = NEXTHDR_FRAGMENT; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr; u8 prevhdr; /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); return 0; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) return 0; /* Discard the first fragment if it does not include all headers * RFC 8200, Section 4.5 */ if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) { pr_debug("Drop incomplete fragment\n"); return 0; } if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; skb_set_transport_header(skb, fhoff); hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); return -ENOMEM; } spin_lock_bh(&fq->q.lock); ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); if (ret == -EPROTO) { skb->transport_header = savethdr; ret = 0; } spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q); return ret; } EXPORT_SYMBOL_GPL(nf_ct_frag6_gather); static int nf_ct_net_init(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); int res; res = fqdir_init(&nf_frag->fqdir, &nf_frags, net); if (res < 0) return res; nf_frag->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; nf_frag->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; nf_frag->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = nf_ct_frag6_sysctl_register(net); if (res < 0) fqdir_exit(nf_frag->fqdir); return res; } static void nf_ct_net_pre_exit(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); fqdir_pre_exit(nf_frag->fqdir); } static void nf_ct_net_exit(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); nf_ct_frags6_sysctl_unregister(net); fqdir_exit(nf_frag->fqdir); } static struct pernet_operations nf_ct_net_ops = { .init = nf_ct_net_init, .pre_exit = nf_ct_net_pre_exit, .exit = nf_ct_net_exit, .id = &nf_frag_pernet_id, .size = sizeof(struct nft_ct_frag6_pernet), }; static const struct rhashtable_params nfct_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .hashfn = ip6frag_key_hashfn, .obj_hashfn = ip6frag_obj_hashfn, .obj_cmpfn = ip6frag_obj_cmpfn, .automatic_shrinking = true, }; int nf_ct_frag6_init(void) { int ret = 0; nf_frags.constructor = ip6frag_init; nf_frags.destructor = NULL; nf_frags.qsize = sizeof(struct frag_queue); nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.frags_cache_name = nf_frags_cache_name; nf_frags.rhash_params = nfct_rhash_params; ret = inet_frags_init(&nf_frags); if (ret) goto out; ret = register_pernet_subsys(&nf_ct_net_ops); if (ret) inet_frags_fini(&nf_frags); out: return ret; } void nf_ct_frag6_cleanup(void) { unregister_pernet_subsys(&nf_ct_net_ops); inet_frags_fini(&nf_frags); }
28 36 18 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 /* * include/linux/ktime.h * * ktime_t - nanosecond-resolution time format. * * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes and macros. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * * Roman Zippel provided the ideas and primary code snippets of * the ktime_t union and further simplifications of the original * code. * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_KTIME_H #define _LINUX_KTIME_H #include <linux/time.h> #include <linux/jiffies.h> #include <asm/bug.h> /* Nanosecond scalar representation for kernel time values */ typedef s64 ktime_t; /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value * @secs: seconds to set * @nsecs: nanoseconds to set * * Return: The ktime_t representation of the value. */ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) { if (unlikely(secs >= KTIME_SEC_MAX)) return KTIME_MAX; return secs * NSEC_PER_SEC + (s64)nsecs; } /* Subtract two ktime_t variables. rem = lhs -rhs: */ #define ktime_sub(lhs, rhs) ((lhs) - (rhs)) /* Add two ktime_t variables. res = lhs + rhs: */ #define ktime_add(lhs, rhs) ((lhs) + (rhs)) /* * Same as ktime_add(), but avoids undefined behaviour on overflow; however, * this means that you must check the result for overflow yourself. */ #define ktime_add_unsafe(lhs, rhs) ((u64) (lhs) + (rhs)) /* * Add a ktime_t variable and a scalar nanosecond value. * res = kt + nsval: */ #define ktime_add_ns(kt, nsval) ((kt) + (nsval)) /* * Subtract a scalar nanosecod from a ktime_t variable * res = kt - nsval: */ #define ktime_sub_ns(kt, nsval) ((kt) - (nsval)) /* convert a timespec64 to ktime_t format: */ static inline ktime_t timespec64_to_ktime(struct timespec64 ts) { return ktime_set(ts.tv_sec, ts.tv_nsec); } /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec64(kt) ns_to_timespec64((kt)) /* Convert ktime_t to nanoseconds */ static inline s64 ktime_to_ns(const ktime_t kt) { return kt; } /** * ktime_compare - Compares two ktime_t variables for less, greater or equal * @cmp1: comparable1 * @cmp2: comparable2 * * Return: ... * cmp1 < cmp2: return <0 * cmp1 == cmp2: return 0 * cmp1 > cmp2: return >0 */ static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2) { if (cmp1 < cmp2) return -1; if (cmp1 > cmp2) return 1; return 0; } /** * ktime_after - Compare if a ktime_t value is bigger than another one. * @cmp1: comparable1 * @cmp2: comparable2 * * Return: true if cmp1 happened after cmp2. */ static inline bool ktime_after(const ktime_t cmp1, const ktime_t cmp2) { return ktime_compare(cmp1, cmp2) > 0; } /** * ktime_before - Compare if a ktime_t value is smaller than another one. * @cmp1: comparable1 * @cmp2: comparable2 * * Return: true if cmp1 happened before cmp2. */ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) { return ktime_compare(cmp1, cmp2) < 0; } #if BITS_PER_LONG < 64 extern s64 __ktime_divns(const ktime_t kt, s64 div); static inline s64 ktime_divns(const ktime_t kt, s64 div) { /* * Negative divisors could cause an inf loop, * so bug out here. */ BUG_ON(div < 0); if (__builtin_constant_p(div) && !(div >> 32)) { s64 ns = kt; u64 tmp = ns < 0 ? -ns : ns; do_div(tmp, div); return ns < 0 ? -tmp : tmp; } else { return __ktime_divns(kt, div); } } #else /* BITS_PER_LONG < 64 */ static inline s64 ktime_divns(const ktime_t kt, s64 div) { /* * 32-bit implementation cannot handle negative divisors, * so catch them on 64bit as well. */ WARN_ON(div < 0); return kt / div; } #endif static inline s64 ktime_to_us(const ktime_t kt) { return ktime_divns(kt, NSEC_PER_USEC); } static inline s64 ktime_to_ms(const ktime_t kt) { return ktime_divns(kt, NSEC_PER_MSEC); } static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) { return ktime_to_us(ktime_sub(later, earlier)); } static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier) { return ktime_to_ms(ktime_sub(later, earlier)); } static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) { return ktime_add_ns(kt, usec * NSEC_PER_USEC); } static inline ktime_t ktime_add_ms(const ktime_t kt, const u64 msec) { return ktime_add_ns(kt, msec * NSEC_PER_MSEC); } static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) { return ktime_sub_ns(kt, usec * NSEC_PER_USEC); } static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) { return ktime_sub_ns(kt, msec * NSEC_PER_MSEC); } extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); /** * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 * format only if the variable contains data * @kt: the ktime_t variable to convert * @ts: the timespec variable to store the result in * * Return: %true if there was a successful conversion, %false if kt was 0. */ static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, struct timespec64 *ts) { if (kt) { *ts = ktime_to_timespec64(kt); return true; } else { return false; } } #include <vdso/ktime.h> static inline ktime_t ns_to_ktime(u64 ns) { return ns; } static inline ktime_t ms_to_ktime(u64 ms) { return ms * NSEC_PER_MSEC; } # include <linux/timekeeping.h> #endif
101 1408 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_GENHD_H #define _LINUX_GENHD_H /* * genhd.h Copyright (C) 1992 Drew Eckhardt * Generic hard disk header file by * Drew Eckhardt * * <drew@colorado.edu> */ #include <linux/types.h> #include <linux/kdev_t.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/uuid.h> #include <linux/blk_types.h> #include <asm/local.h> extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; #define DISK_MAX_PARTS 256 #define DISK_NAME_LEN 32 #include <linux/major.h> #include <linux/device.h> #include <linux/smp.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/workqueue.h> #include <linux/xarray.h> #define PARTITION_META_INFO_VOLNAMELTH 64 /* * Enough for the string representation of any kind of UUID plus NULL. * EFI UUID is 36 characters. MSDOS UUID is 11 characters. */ #define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) struct partition_meta_info { char uuid[PARTITION_META_INFO_UUIDLTH]; u8 volname[PARTITION_META_INFO_VOLNAMELTH]; }; /** * DOC: genhd capability flags * * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device * gives access to removable media. * When set, the device remains present even when media is not * inserted. * Must not be set for devices which are removed entirely when the * media is removed. * * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style * device. * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl. * * ``GENHD_FL_UP`` (0x0010): indicates that the block device is "up", * with a similar meaning to network interfaces. * * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include * partition information in ``/proc/partitions`` or in the output of * printk_all_partitions(). * Used for the null block device and some MMC devices. * * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended * dynamic ``dev_t``, i.e. it wants extended device numbers * (``BLOCK_EXT_MAJOR``). * This affects the maximum number of partitions. * * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the * partition table, the device's capacity has been extended to its * native capacity; i.e. the device has hidden capacity used by one * of the partitions (this is a flag used so that native capacity is * only ever unlocked once). * * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is * blocked whenever a writer holds an exclusive lock. * * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled. * Used for loop devices in their default settings and some MMC * devices. * * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it * doesn't produce events, doesn't appear in sysfs, and doesn't have * an associated ``bdev``. * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and * ``GENHD_FL_NO_PART_SCAN``. * Used for multipath devices. */ #define GENHD_FL_REMOVABLE 0x0001 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */ /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ #define GENHD_FL_CD 0x0008 #define GENHD_FL_UP 0x0010 #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 #define GENHD_FL_NATIVE_CAPACITY 0x0080 #define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 0x0100 #define GENHD_FL_NO_PART_SCAN 0x0200 #define GENHD_FL_HIDDEN 0x0400 enum { DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ }; enum { /* Poll even if events_poll_msecs is unset */ DISK_EVENT_FLAG_POLL = 1 << 0, /* Forward events to udev */ DISK_EVENT_FLAG_UEVENT = 1 << 1, }; struct disk_events; struct badblocks; struct blk_integrity { const struct blk_integrity_profile *profile; unsigned char flags; unsigned char tuple_size; unsigned char interval_exp; unsigned char tag_size; }; struct gendisk { /* major, first_minor and minors are input parameters only, * don't use directly. Use disk_devt() and disk_max_parts(). */ int major; /* major number of driver */ int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ char disk_name[DISK_NAME_LEN]; /* name of major driver */ unsigned short events; /* supported events */ unsigned short event_flags; /* flags related to event processing */ struct xarray part_tbl; struct block_device *part0; const struct block_device_operations *fops; struct request_queue *queue; void *private_data; int flags; unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 #define GD_QUEUE_REF 2 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ struct kobject *slave_dir; struct timer_rand_state *random; atomic_t sync_io; /* RAID */ struct disk_events *ev; #ifdef CONFIG_BLK_DEV_INTEGRITY struct kobject integrity_kobj; #endif /* CONFIG_BLK_DEV_INTEGRITY */ #if IS_ENABLED(CONFIG_CDROM) struct cdrom_device_info *cdi; #endif int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; }; /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. */ #define dev_to_disk(device) \ (dev_to_bdev(device)->bd_disk) #define disk_to_dev(disk) \ (&((disk)->part0->bd_device)) #if IS_REACHABLE(CONFIG_CDROM) #define disk_to_cdi(disk) ((disk)->cdi) #else #define disk_to_cdi(disk) NULL #endif static inline int disk_max_parts(struct gendisk *disk) { if (disk->flags & GENHD_FL_EXT_DEVT) return DISK_MAX_PARTS; return disk->minors; } static inline bool disk_part_scan_enabled(struct gendisk *disk) { return disk_max_parts(disk) > 1 && !(disk->flags & GENHD_FL_NO_PART_SCAN); } static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); } void disk_uevent(struct gendisk *disk, enum kobject_action action); /* block/genhd.c */ extern void device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups); static inline void add_disk(struct gendisk *disk) { device_add_disk(NULL, disk, NULL); } extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk); static inline void add_disk_no_queue_reg(struct gendisk *disk) { device_add_disk_no_queue_reg(NULL, disk); } extern void del_gendisk(struct gendisk *gp); void set_disk_ro(struct gendisk *disk, bool read_only); static inline int get_disk_ro(struct gendisk *disk) { return disk->part0->bd_read_only || test_bit(GD_READ_ONLY, &disk->state); } extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); bool set_capacity_and_notify(struct gendisk *disk, sector_t size); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; extern void rand_initialize_disk(struct gendisk *disk); static inline sector_t get_start_sect(struct block_device *bdev) { return bdev->bd_start_sect; } static inline sector_t bdev_nr_sectors(struct block_device *bdev) { return i_size_read(bdev->bd_inode) >> 9; } static inline sector_t get_capacity(struct gendisk *disk) { return bdev_nr_sectors(disk->part0); } int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); extern struct gendisk *__alloc_disk_node(int minors, int node_id); extern void put_disk(struct gendisk *disk); #define alloc_disk_node(minors, node_id) \ ({ \ static struct lock_class_key __key; \ const char *__name; \ struct gendisk *__disk; \ \ __name = "(gendisk_completion)"#minors"("#node_id")"; \ \ __disk = __alloc_disk_node(minors, node_id); \ \ if (__disk) \ lockdep_init_map(&__disk->lockdep_map, __name, &__key, 0); \ \ __disk; \ }) #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) /** * blk_alloc_disk - allocate a gendisk structure * @node_id: numa node to allocate on * * Allocate and pre-initialize a gendisk structure for use with BIO based * drivers. * * Context: can sleep */ #define blk_alloc_disk(node_id) \ ({ \ struct gendisk *__disk = __blk_alloc_disk(node_id); \ static struct lock_class_key __key; \ \ if (__disk) \ lockdep_init_map(&__disk->lockdep_map, \ "(bio completion)", &__key, 0); \ __disk; \ }) struct gendisk *__blk_alloc_disk(int node); void blk_cleanup_disk(struct gendisk *disk); int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)); #define register_blkdev(major, name) \ __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void set_capacity(struct gendisk *disk, sector_t size); /* for drivers/char/raw.c: */ int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); #ifdef CONFIG_SYSFS int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) { return 0; } static inline void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { } #endif /* CONFIG_SYSFS */ dev_t part_devt(struct gendisk *disk, u8 partno); dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK void printk_all_partitions(void); #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } #endif /* CONFIG_BLOCK */ #endif /* _LINUX_GENHD_H */
3 3 2 12 17 4 1 5 1 6 10 60 36 19 14 1 26 4 9 2 4 2 4 28 4 18 147 106 13 5 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 // SPDX-License-Identifier: GPL-2.0 /* * Supplementary group IDs */ #include <linux/cred.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/sort.h> #include <linux/syscalls.h> #include <linux/user_namespace.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> struct group_info *groups_alloc(int gidsetsize) { struct group_info *gi; gi = kvmalloc(struct_size(gi, gid, gidsetsize), GFP_KERNEL_ACCOUNT); if (!gi) return NULL; atomic_set(&gi->usage, 1); gi->ngroups = gidsetsize; return gi; } EXPORT_SYMBOL(groups_alloc); void groups_free(struct group_info *group_info) { kvfree(group_info); } EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, const struct group_info *group_info) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; gid = from_kgid_munged(user_ns, group_info->gid[i]); if (put_user(gid, grouplist+i)) return -EFAULT; } return 0; } /* fill a group_info from a user-space array - it must be allocated already */ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; kgid_t kgid; if (get_user(gid, grouplist+i)) return -EFAULT; kgid = make_kgid(user_ns, gid); if (!gid_valid(kgid)) return -EINVAL; group_info->gid[i] = kgid; } return 0; } static int gid_cmp(const void *_a, const void *_b) { kgid_t a = *(kgid_t *)_a; kgid_t b = *(kgid_t *)_b; return gid_gt(a, b) - gid_lt(a, b); } void groups_sort(struct group_info *group_info) { sort(group_info->gid, group_info->ngroups, sizeof(*group_info->gid), gid_cmp, NULL); } EXPORT_SYMBOL(groups_sort); /* a simple bsearch */ int groups_search(const struct group_info *group_info, kgid_t grp) { unsigned int left, right; if (!group_info) return 0; left = 0; right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; if (gid_gt(grp, group_info->gid[mid])) left = mid + 1; else if (gid_lt(grp, group_info->gid[mid])) right = mid; else return 1; } return 0; } /** * set_groups - Change a group subscription in a set of credentials * @new: The newly prepared set of credentials to alter * @group_info: The group list to install */ void set_groups(struct cred *new, struct group_info *group_info) { put_group_info(new->group_info); get_group_info(group_info); new->group_info = group_info; } EXPORT_SYMBOL(set_groups); /** * set_current_groups - Change current's group subscription * @group_info: The group list to impose * * Validate a group subscription and, if valid, impose it upon current's task * security record. */ int set_current_groups(struct group_info *group_info) { struct cred *new; new = prepare_creds(); if (!new) return -ENOMEM; set_groups(new, group_info); return commit_creds(new); } EXPORT_SYMBOL(set_current_groups); SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) { const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: return i; } bool may_setgroups(void) { struct user_namespace *user_ns = current_user_ns(); return ns_capable_setid(user_ns, CAP_SETGID) && userns_may_setgroups(user_ns); } /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. */ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) { struct group_info *group_info; int retval; if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; group_info = groups_alloc(gidsetsize); if (!group_info) return -ENOMEM; retval = groups_from_user(group_info, grouplist); if (retval) { put_group_info(group_info); return retval; } groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); return retval; } /* * Check whether we're fsgid/egid or in the supplemental group.. */ int in_group_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->fsgid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_group_p); int in_egroup_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->egid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_egroup_p);
193 29 21 29 418 10 313 411 9 40 35 16 16 16 76 36 53 109 12 101 4 4 1 1 1 1 1 1 1 1 2 41 15 5 2 21 38 44 14 33 1 5 17 3 2 10 19 6 25 5 19 10 8 6 8 6 7 7 65 1 18 35 19 3 3 3 7 3 141 4 2 22 2 39 15 17 106 12 2 5 116 2 25 10 13 2 3 116 15 98 48 49 3 6 6 3 14 23 5 32 32 5 13 2 25 3 79 37 43 37 4 4 2 52 49 37 26 36 54 37 37 13 21 1 20 29 3 26 18 11 1 1 11 3 26 6 1 13 3 2 35 50 34 11 273 207 239 28 32 13 157 157 157 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 Forwarding Information Base: FIB frontend. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); hlist_add_head_rcu(&main_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); return 0; fail: fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; tb = fib_get_table(net, id); if (tb) return tb; if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, tb); break; default: break; } h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } EXPORT_SYMBOL_GPL(fib_new_table); /* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, struct fib_table *new) { #ifdef CONFIG_IP_MULTIPLE_TABLES switch (new->tb_id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, new); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, new); break; default: break; } #endif /* replace the old table in the hlist */ hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); } int fib_unmerge(struct net *net) { struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); if (!old) return 0; new = fib_trie_unmerge(old); if (!new) return -ENOMEM; /* table is already unmerged */ if (new == old) return 0; /* replace merged table with clean table */ fib_replace_table(net, old, new); fib_free_table(old); /* attempt to fetch main table if it has been allocated */ main_table = fib_get_table(net, RT_TABLE_MAIN); if (!main_table) return 0; /* flush local entries from main table */ fib_table_flush_external(main_table); return 0; } void fib_flush(struct net *net) { int flushed = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(net, tb, false); } if (flushed) rt_cache_flush(net); } /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; rcu_read_lock(); table = fib_get_table(net, tb_id); if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); if (!dev || dev == nhc->nhc_dev) ret = res.type; } } rcu_read_unlock(); return ret; } unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) { return __inet_dev_addr_type(net, NULL, addr, tb_id); } EXPORT_SYMBOL(inet_addr_type_table); unsigned int inet_addr_type(struct net *net, __be32 addr) { return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); /* inet_addr_type with dev == NULL but using the table from a dev * if one is associated */ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } EXPORT_SYMBOL(inet_addr_type_dev_table); __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct rtable *rt; struct net *net; int scope; rt = skb_rtable(skb); if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == RTCF_LOCAL) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (unlikely(fi->nh)) { dev_match = nexthop_uses_dev(fi->nh, dev); } else { int ret; for (ret = 0; ret < fib_info_num_path(fi); ret++) { const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); if (nhc_l3mdev_matches_dev(nhc, dev)) { dev_match = true; break; } } } #else if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif return dev_match; } EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. * - figure out what "logical" interface this packet arrived * and calculate "specific destination" address. * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_iif = l3mdev_master_ifindex_rcu(dev); if (!fl4.flowi4_iif) fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } else { swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST && (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) goto e_inval; fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); /* This is not common, loopback packets retain skb_dst so normally they * would not even hit this slow path. */ dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) goto last_resort; if (rpf == 1) goto e_rpf; fl4.flowi4_oif = dev->ifindex; ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; last_resort: if (rpf) goto e_rpf; *itag = 0; return 0; e_inval: return -EINVAL; e_rpf: return -EXDEV; } /* Ignore rp_filter for packets protected by IPsec. */ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); struct net *net = dev_net(dev); if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { if (IN_DEV_ACCEPT_LOCAL(idev)) goto ok; /* with custom local routes in place, checking local addresses * only will be too optimistic, with custom rules, checking * local addresses only can be too strict, e.g. due to vrf */ if (net->ipv4.fib_has_custom_local_routes || fib4_has_custom_rules(net)) goto full_check; if (inet_lookup_ifaddr_rcu(net, src)) return -EINVAL; ok: *itag = 0; return 0; } full_check: return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag); } static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } static int put_rtax(struct nlattr *mx, int len, int type, u32 value) { struct nlattr *nla; nla = (struct nlattr *) ((char *) mx + len); nla->nla_type = type; nla->nla_len = nla_attr_size(4); *(u32 *) nla_data(nla) = value; return len + nla_total_size(4); } static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; /* * Check mask for validity: * a) it must be contiguous. * b) destination must have all host bits clear. * c) if application forgot to set correct family (AF_INET), * reject request unless it is absolutely clear i.e. * both family and mask are zero. */ plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) return -EAFNOSUPPORT; } if (bad_mask(mask, addr)) return -EINVAL; plen = inet_mask_len(mask); } cfg->fc_dst_len = plen; cfg->fc_dst = addr; if (cmd != SIOCDELRT) { cfg->fc_nlflags = NLM_F_CREATE; cfg->fc_protocol = RTPROT_BOOT; } if (rt->rt_metric) cfg->fc_priority = rt->rt_metric - 1; if (rt->rt_flags & RTF_REJECT) { cfg->fc_scope = RT_SCOPE_HOST; cfg->fc_type = RTN_UNREACHABLE; return 0; } cfg->fc_scope = RT_SCOPE_NOWHERE; cfg->fc_type = RTN_UNICAST; if (rt->rt_dev) { char *colon; struct net_device *dev; char devname[IFNAMSIZ]; if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) return -EFAULT; devname[IFNAMSIZ-1] = 0; colon = strchr(devname, ':'); if (colon) *colon = 0; dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { const struct in_ifaddr *ifa; struct in_device *in_dev; in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return -ENODEV; *colon = ':'; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } rcu_read_unlock(); if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } } addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { unsigned int addr_type; cfg->fc_gw4 = addr; cfg->fc_gw_family = AF_INET; addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } if (cmd == SIOCDELRT) return 0; if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family) return -EINVAL; if (cfg->fc_scope == RT_SCOPE_NOWHERE) cfg->fc_scope = RT_SCOPE_LINK; if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { struct nlattr *mx; int len = 0; mx = kcalloc(3, nla_total_size(4), GFP_KERNEL); if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); if (rt->rt_flags & RTF_WINDOW) len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); if (rt->rt_flags & RTF_IRTT) len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); cfg->fc_mx = mx; cfg->fc_mx_len = len; } return 0; } /* * Handle IP routing ioctl calls. * These are used to manipulate the routing tables */ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) { struct fib_config cfg; int err; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); err = rtentry_to_fib_config(net, cmd, rt, &cfg); if (err == 0) { struct fib_table *tb; if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) err = fib_table_delete(net, tb, &cfg, NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) err = fib_table_insert(net, tb, &cfg, NULL); else err = -ENOBUFS; } /* allocated by rtentry_to_fib_config() */ kfree(cfg.fc_mx); } rtnl_unlock(); return err; } return -EINVAL; } const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_GATEWAY] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack) { struct rtvia *via; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA"); return -EINVAL; } via = nla_data(nla); alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); switch (via->rtvia_family) { case AF_INET: if (alen != sizeof(__be32)) { NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET; cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET6; cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr); #else NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EINVAL; #endif break; default: NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA"); return -EINVAL; } return 0; } static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_config *cfg, struct netlink_ext_ack *extack) { bool has_gw = false, has_via = false; struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) goto errout; memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); cfg->fc_dst_len = rtm->rtm_dst_len; cfg->fc_tos = rtm->rtm_tos; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; cfg->fc_scope = rtm->rtm_scope; cfg->fc_type = rtm->rtm_type; cfg->fc_flags = rtm->rtm_flags; cfg->fc_nlflags = nlh->nlmsg_flags; cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); err = -EINVAL; goto errout; } nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { switch (nla_type(attr)) { case RTA_DST: cfg->fc_dst = nla_get_be32(attr); break; case RTA_OIF: cfg->fc_oif = nla_get_u32(attr); break; case RTA_GATEWAY: has_gw = true; cfg->fc_gw4 = nla_get_be32(attr); if (cfg->fc_gw4) cfg->fc_gw_family = AF_INET; break; case RTA_VIA: has_via = true; err = fib_gw_from_via(cfg, attr, extack); if (err) goto errout; break; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; case RTA_PREFSRC: cfg->fc_prefsrc = nla_get_be32(attr); break; case RTA_METRICS: cfg->fc_mx = nla_data(attr); cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), nla_len(attr), extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; case RTA_FLOW: cfg->fc_flow = nla_get_u32(attr); break; case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; case RTA_ENCAP: cfg->fc_encap = attr; break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; break; case RTA_NH_ID: cfg->fc_nh_id = nla_get_u32(attr); break; } } if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); return -EINVAL; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); return -EINVAL; } return 0; errout: return err; } static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); err = -EINVAL; goto errout; } tb = fib_get_table(net, cfg.fc_table); if (!tb) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; goto errout; } err = fib_table_delete(net, tb, &cfg, extack); errout: return err; } static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; tb = fib_new_table(net, cfg.fc_table); if (!tb) { err = -ENOBUFS; goto errout; } err = fib_table_insert(net, tb, &cfg, extack); if (!err && cfg.fc_type == RTN_LOCAL) net->ipv4.fib_has_custom_local_routes = true; errout: return err; } int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; ASSERT_RTNL(); if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); return -EINVAL; } rtm = nlmsg_data(nlh); if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_scope) { NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) { NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & RTM_F_CLONED) filter->dump_routes = false; else filter->dump_exceptions = false; filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; filter->table_id = rtm->rtm_table; err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (!tb[i]) continue; switch (i) { case RTA_TABLE: filter->table_id = nla_get_u32(tb[i]); break; case RTA_OIF: ifindex = nla_get_u32(tb[i]); filter->dev = __dev_get_by_index(net, ifindex); if (!filter->dev) return -ENODEV; break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } if (filter->flags || filter->protocol || filter->rt_type || filter->table_id || filter->dev) { filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } return 0; } EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req); static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .dump_routes = true, .dump_exceptions = true }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; int dumped = 0, err; if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) return err; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED); } /* ipv4 does not use prefix flag */ if (filter.flags & RTM_F_PREFIX) return skb->len; if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); return -ENOENT; } rcu_read_lock(); err = fib_table_dump(tb, skb, cb, &filter); rcu_read_unlock(); return skb->len ? : err; } s_h = cb->args[0]; s_e = cb->args[1]; rcu_read_lock(); for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); if (err < 0) { if (likely(skb->len)) goto out; goto out_err; } dumped = 1; next: e++; } } out: err = skb->len; out_err: rcu_read_unlock(); cb->args[1] = e; cb->args[0] = h; return err; } /* Prepare and feed intra-kernel routing request. * Really, it should be netlink message, but :-( netlink * can be not configured, so that we feed it directly * to fib engine. It is legal, because all events occur * only when netlink is already locked. */ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa, u32 rt_priority) { struct net *net = dev_net(ifa->ifa_dev->dev); u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, .fc_type = type, .fc_dst = dst, .fc_dst_len = dst_len, .fc_priority = rt_priority, .fc_prefsrc = ifa->ifa_local, .fc_oif = ifa->ifa_dev->dev->ifindex, .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, .fc_nlinfo = { .nl_net = net, }, }; if (!tb_id) tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; tb = fib_new_table(net, tb_id); if (!tb) return; cfg.fc_table = tb->tb_id; if (type != RTN_LOCAL) cfg.fc_scope = RT_SCOPE_LINK; else cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) fib_table_insert(net, tb, &cfg, NULL); else fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *prim = ifa; __be32 mask = ifa->ifa_mask; __be32 addr = ifa->ifa_local; __be32 prefix = ifa->ifa_address & mask; if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } } fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0); if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim, ifa->ifa_rt_priority); /* Add the network broadcast address, when it makes sense */ if (ifa->ifa_prefixlen < 31) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); } } } void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) { __be32 prefix = ifa->ifa_address & ifa->ifa_mask; struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, new_metric); /* delete the old */ fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority); } /* Delete primary or secondary address. * Optionally, on secondary address promotion consider the addresses * from subnet iprim as deleted, even if they are in device list. * In this case the secondary ifa can be in device list. */ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa, *prim1 = NULL; __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 unsigned int ok = 0; int subnet = 0; /* Primary network */ int gone = 1; /* Address is missing */ int same_prefsrc = 0; /* Another primary with same IP */ if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { /* if the device has been deleted, we don't perform * address promotion */ if (!in_dev->dead) pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { pr_warn("%s: bug: iprim != prim\n", __func__); return; } } else if (!ipv4_is_zeronet(any) && (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, any, ifa->ifa_prefixlen, prim, 0); subnet = 1; } if (in_dev->dead) goto no_promotions; /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * * Scan address list to be sure that addresses are really gone. */ rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa1, in_dev) { if (ifa1 == ifa) { /* promotion, keep the IP */ gone = 0; continue; } /* Ignore IFAs from our subnet */ if (iprim && ifa1->ifa_mask == iprim->ifa_mask && inet_ifa_match(ifa1->ifa_address, iprim)) continue; /* Ignore ifa1 if it uses different primary IP (prefsrc) */ if (ifa1->ifa_flags & IFA_F_SECONDARY) { /* Another address from our subnet? */ if (ifa1->ifa_mask == prim->ifa_mask && inet_ifa_match(ifa1->ifa_address, prim)) prim1 = prim; else { /* We reached the secondaries, so * same_prefsrc should be determined. */ if (!same_prefsrc) continue; /* Search new prim1 if ifa1 is not * using the current prim1 */ if (!prim1 || ifa1->ifa_mask != prim1->ifa_mask || !inet_ifa_match(ifa1->ifa_address, prim1)) prim1 = inet_ifa_byprefix(in_dev, ifa1->ifa_address, ifa1->ifa_mask); if (!prim1) continue; if (prim1->ifa_local != prim->ifa_local) continue; } } else { if (prim->ifa_local != ifa1->ifa_local) continue; prim1 = ifa1; if (prim != prim1) same_prefsrc = 1; } if (ifa->ifa_local == ifa1->ifa_local) ok |= LOCAL_OK; if (ifa->ifa_broadcast == ifa1->ifa_broadcast) ok |= BRD_OK; if (brd == ifa1->ifa_broadcast) ok |= BRD1_OK; if (any == ifa1->ifa_broadcast) ok |= BRD0_OK; /* primary has network specific broadcasts */ if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) { __be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask; __be32 any1 = ifa1->ifa_address & ifa1->ifa_mask; if (!ipv4_is_zeronet(any1)) { if (ifa->ifa_broadcast == brd1 || ifa->ifa_broadcast == any1) ok |= BRD_OK; if (brd == brd1 || brd == any1) ok |= BRD1_OK; if (any == brd1 || any == any1) ok |= BRD0_OK; } } } rcu_read_unlock(); no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); if (subnet && ifa->ifa_prefixlen < 31) { if (!(ok & BRD1_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim, 0); if (!(ok & BRD0_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim, 0); } if (!(ok & LOCAL_OK)) { unsigned int addr_type; fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0); /* Check, that this local address finally disappeared. */ addr_type = inet_addr_type_dev_table(dev_net(dev), dev, ifa->ifa_local); if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } #undef LOCAL_OK #undef BRD_OK #undef BRD0_OK #undef BRD1_OK } static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) { struct fib_result res; struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, .flowi4_tos = frn->fl_tos, .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; rcu_read_lock(); tb = fib_get_table(net, frn->tb_id_in); frn->err = -ENOENT; if (tb) { local_bh_disable(); frn->tb_id = tb->tb_id; frn->err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); if (!frn->err) { frn->prefixlen = res.prefixlen; frn->nh_sel = res.nh_sel; frn->type = res.type; frn->scope = res.scope; } local_bh_enable(); } rcu_read_unlock(); } static void nl_fib_input(struct sk_buff *skb) { struct net *net; struct fib_result_nl *frn; struct nlmsghdr *nlh; u32 portid; net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); if (skb->len < nlmsg_total_size(sizeof(*frn)) || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(*frn)) return; skb = netlink_skb_clone(skb, GFP_KERNEL); if (!skb) return; nlh = nlmsg_hdr(skb); frn = (struct fib_result_nl *) nlmsg_data(nlh); nl_fib_lookup(net, frn); portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; struct netlink_kernel_cfg cfg = { .input = nl_fib_input, }; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); if (!sk) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; return 0; } static void nl_fib_lookup_exit(struct net *net) { netlink_kernel_release(net->ipv4.fibnl); net->ipv4.fibnl = NULL; } static void fib_disable_ip(struct net_device *dev, unsigned long event, bool force) { if (fib_sync_down_dev(dev, event, force)) fib_flush(dev_net(dev)); else rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct net_device *dev = ifa->ifa_dev->dev; struct net *net = dev_net(dev); switch (event) { case NETDEV_UP: fib_add_ifaddr(ifa); #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); atomic_inc(&net->ipv4.dev_addr_genid); if (!ifa->ifa_dev->ifa_list) { /* Last address was deleted from this interface. * Disable IP. */ fib_disable_ip(dev, event, true); } else { rt_cache_flush(dev_net(dev)); } break; } return NOTIFY_DONE; } static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *upper_info = ptr; struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); struct in_ifaddr *ifa; unsigned int flags; if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, event, true); rt_flush_dev(dev); return NOTIFY_DONE; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: in_dev_for_each_ifa_rtnl(ifa, in_dev) { fib_add_ifaddr(ifa); } #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(net); break; case NETDEV_DOWN: fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); rt_cache_flush(net); break; case NETDEV_CHANGEMTU: fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ if (upper_info->upper_dev && netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } return NOTIFY_DONE; } static struct notifier_block fib_inetaddr_notifier = { .notifier_call = fib_inetaddr_event, }; static struct notifier_block fib_netdev_notifier = { .notifier_call = fib_netdev_event, }; static int __net_init ip_fib_net_init(struct net *net) { int err; size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; err = fib4_notifier_init(net); if (err) return err; #ifdef CONFIG_IP_ROUTE_MULTIPATH /* Default to 3-tuple */ net->ipv4.sysctl_fib_multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; #endif /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv4.fib_table_hash) { err = -ENOMEM; goto err_table_hash_alloc; } err = fib4_rules_init(net); if (err < 0) goto err_rules_init; return 0; err_rules_init: kfree(net->ipv4.fib_table_hash); err_table_hash_alloc: fib4_notifier_exit(net); return err; } static void ip_fib_net_exit(struct net *net) { int i; rtnl_lock(); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif /* Destroy the tables in reverse order to guarantee that the * local table, ID 255, is destroyed before the main table, ID * 254. This is necessary as the local table may contain * references to data contained in the main table. */ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); fib_table_flush(net, tb, true); fib_free_table(tb); } } #ifdef CONFIG_IP_MULTIPLE_TABLES fib4_rules_exit(net); #endif rtnl_unlock(); kfree(net->ipv4.fib_table_hash); fib4_notifier_exit(net); } static int __net_init fib_net_init(struct net *net) { int error; #ifdef CONFIG_IP_ROUTE_CLASSID net->ipv4.fib_num_tclassid_users = 0; #endif error = ip_fib_net_init(net); if (error < 0) goto out; error = nl_fib_lookup_init(net); if (error < 0) goto out_nlfl; error = fib_proc_init(net); if (error < 0) goto out_proc; out: return error; out_proc: nl_fib_lookup_exit(net); out_nlfl: ip_fib_net_exit(net); goto out; } static void __net_exit fib_net_exit(struct net *net) { fib_proc_exit(net); nl_fib_lookup_exit(net); ip_fib_net_exit(net); } static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, }; void __init ip_fib_init(void) { fib_trie_init(); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0); rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0); rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, 0); }
7 64 43 10 7 3 4 4 8 8 9 1 6 2 9 9 11 1 1 5 3 8 8 8 8 5 3 8 8 13 13 3 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blkdev.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/frontswap.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by get_swap_page() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but get_swap_page() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 /* returns 1 if swap entry is freed */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct page *page; int ret = 0; page = find_get_page(swap_address_space(entry), offset); if (!page) return 0; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming pages. So, we hold a lock on a page, * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use try_to_free_swap() with explicit lock_page() * in usual operations. */ if (trylock_page(page)) { if ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !page_mapped(page)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(page))) ret = try_to_free_swap(page); unlock_page(page); } put_page(page); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_page_sector(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = __page_file_index(page); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO, 0)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_size(size) (size) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_size() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_size(size) 1 #endif #define LATENCY_LIMIT 256 static inline void cluster_set_flag(struct swap_cluster_info *info, unsigned int flag) { info->flags = flag; } static inline unsigned int cluster_count(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_count(struct swap_cluster_info *info, unsigned int c) { info->data = c; } static inline void cluster_set_count_flag(struct swap_cluster_info *info, unsigned int c, unsigned int f) { info->flags = f; info->data = c; } static inline unsigned int cluster_next(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_next(struct swap_cluster_info *info, unsigned int n) { info->data = n; } static inline void cluster_set_next_flag(struct swap_cluster_info *info, unsigned int n, unsigned int f) { info->flags = f; info->data = n; } static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline bool cluster_is_null(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_NEXT_NULL; } static inline void cluster_set_null(struct swap_cluster_info *info) { info->flags = CLUSTER_FLAG_NEXT_NULL; info->data = 0; } static inline bool cluster_is_huge(struct swap_cluster_info *info) { if (IS_ENABLED(CONFIG_THP_SWAP)) return info->flags & CLUSTER_FLAG_HUGE; return false; } static inline void cluster_clear_huge(struct swap_cluster_info *info) { info->flags &= ~CLUSTER_FLAG_HUGE; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); } static inline unsigned int cluster_list_first(struct swap_cluster_list *list) { return cluster_next(&list->head); } static void cluster_list_init(struct swap_cluster_list *list) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } static void cluster_list_add_tail(struct swap_cluster_list *list, struct swap_cluster_info *ci, unsigned int idx) { if (cluster_list_empty(list)) { cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); /* * Nested cluster lock, but both cluster locks are * only acquired when we held swap_info_struct->lock */ ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } static unsigned int cluster_list_del_first(struct swap_cluster_list *list, struct swap_cluster_info *ci) { unsigned int idx; idx = cluster_next(&list->head); if (cluster_next(&list->tail) == idx) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } else cluster_set_next_flag(&list->head, cluster_next(&ci[idx]), 0); return idx; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); cluster_list_add_tail(&si->free_clusters, ci, idx); } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; while (!cluster_list_empty(&si->discard_clusters)) { idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); __free_cluster(si, idx); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); unlock_cluster(ci); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); cluster_list_del_first(&si->free_clusters, ci); cluster_set_count_flag(ci + idx, 0, 0); } static void free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info + idx; VM_BUG_ON(cluster_count(ci) != 0); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, idx); return; } __free_cluster(si, idx); } /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased. */ static void inc_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) alloc_cluster(p, idx); VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) + 1); } /* * The cluster corresponding to page_nr decreases one usage. If the usage * counter becomes 0, which means no page in the cluster is in using, we can * optionally discard the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) free_cluster(p, idx); } /* * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset) { struct percpu_cluster *percpu_cluster; bool conflict; offset /= SWAPFILE_CLUSTER; conflict = !cluster_list_empty(&si->free_clusters) && offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); cluster_set_null(&percpu_cluster->index); return true; } /* * Try to get a swap entry from current cpu's swap entry pool (a cluster). This * might involve allocating a new cluster for current CPU too. */ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned long tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); if (cluster_is_null(&cluster->index)) { if (!cluster_list_empty(&si->free_clusters)) { cluster->index = si->free_clusters.head; cluster->next = cluster_next(&cluster->index) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); *scan_base = this_cpu_read(*si->cluster_next_cpu); *offset = *scan_base; goto new_cluster; } else return false; } /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster */ tmp = cluster->next; max = min_t(unsigned long, si->max, (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); if (tmp < max) { ci = lock_cluster(si, tmp); while (tmp < max) { if (!si->swap_map[tmp]) break; tmp++; } unlock_cluster(ci); } if (tmp >= max) { cluster_set_null(&cluster->index); goto new_cluster; } cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; return true; } static void __del_from_avail_list(struct swap_info_struct *p) { int nid; for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *p) { spin_lock(&swap_avail_lock); __del_from_avail_list(p); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); si->inuse_pages += nr_entries; if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); } } static void add_to_avail_list(struct swap_info_struct *p) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) { WARN_ON(!plist_node_empty(&p->avail_lists[nid])); plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); } spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); si->inuse_pages -= nr_entries; if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); frontswap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = si->lowest_bit + prandom_u32_max(si->highest_bit - si->lowest_bit + 1); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[]) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ si->flags += SWP_SCANNING; /* * Use percpu scan base for SSD to reduce lock contention on * cluster and swap cache. For HDD, sequential access is more * important. */ if (si->flags & SWP_SOLIDSTATE) scan_base = this_cpu_read(*si->cluster_next_cpu); else scan_base = si->cluster_next; offset = scan_base; /* SSD algorithm */ if (si->cluster_info) { if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } else if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info * case, just handled by scan_swap_map_try_ssd_cluster() above. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= si->highest_bit; offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (si->cluster_info) { while (scan_swap_map_ssd_cluster_conflict(si, offset)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { unlock_cluster(ci); if (!n_ret) goto scan; else goto done; } WRITE_ONCE(si->swap_map[offset], usage); inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); swap_range_alloc(si, offset, 1); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } /* try to get more slots in cluster */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; } else if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } } offset = si->lowest_bit; while (offset < scan_base) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) { unsigned long idx; struct swap_cluster_info *ci; unsigned long offset; /* * Should not even be attempting cluster allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) { VM_WARN_ON_ONCE(1); return 0; } if (cluster_list_empty(&si->free_clusters)) return 0; idx = cluster_list_first(&si->free_clusters); offset = idx * SWAPFILE_CLUSTER; ci = lock_cluster(si, offset); alloc_cluster(si, idx); cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER); unlock_cluster(ci); swap_range_alloc(si, offset, SWAPFILE_CLUSTER); *slot = swp_entry(si->type, offset); return 1; } static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) { unsigned long offset = idx * SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); cluster_set_count_flag(ci, 0, 0); free_cluster(si, idx); unlock_cluster(ci); swap_range_free(si, offset, SWAPFILE_CLUSTER); } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } if (size == SWAPFILE_CLUSTER) { if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries); spin_unlock(&si->lock); if (n_ret || size == SWAPFILE_CLUSTER) goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset; if (!entry.val) goto out; p = swp_swap_info(entry); if (!p) goto bad_nofile; if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; return p; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; p = __swap_info_get(entry); if (!p) goto out; if (data_race(!p->swap_map[swp_offset(entry)])) goto bad_free; return p; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) spin_lock(&p->lock); return p; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = p->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(p, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(p->swap_map[offset], usage); else WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff, such as page lock, page table lock, etc. The * caller must be prepared for that. For example, the following * situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(p, offset); usage = __swap_entry_free_locked(p, offset, 1); unlock_cluster_or_swap_info(p, ci); if (!usage) free_swap_slot(entry); return usage; } static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; ci = lock_cluster(p, offset); count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; dec_cluster_info_page(p, p->cluster_info, offset); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, 1); swap_range_free(p, offset, 1); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) __swap_entry_free(p, entry); } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_page(struct page *page, swp_entry_t entry) { unsigned long offset = swp_offset(entry); unsigned long idx = offset / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; int size = swap_entry_size(thp_nr_pages(page)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size == SWAPFILE_CLUSTER) { VM_BUG_ON(!cluster_is_huge(ci)); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { val = map[i]; VM_BUG_ON(!(val & SWAP_HAS_CACHE)); if (val == SWAP_HAS_CACHE) free_entries++; } cluster_clear_huge(ci); if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); swap_free_cluster(si, idx); spin_unlock(&si->lock); return; } } for (i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } #ifdef CONFIG_THP_SWAP int split_swap_cluster(swp_entry_t entry) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); si = _swap_info_get(entry); if (!si) return -EBUSY; ci = lock_cluster(si, offset); cluster_clear_huge(ci); unlock_cluster(ci); return 0; } #endif static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); prev = p; } if (p) spin_unlock(&p->lock); } /* * How many references to page are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; struct swap_cluster_info *ci; swp_entry_t entry; unsigned long offset; entry.val = page_private(page); p = _swap_info_get(entry); if (p) { offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); unlock_cluster_or_swap_info(p, ci); } return count; } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si; pgoff_t offset = swp_offset(entry); int count = 0; si = get_swap_device(entry); if (si) { count = swap_count(si->swap_map[offset]); put_swap_device(si); } return count; } static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { int count = 0; pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int __swp_swapcount(swp_entry_t entry) { int count = 0; struct swap_info_struct *si; si = get_swap_device(entry); if (si) { count = swap_swapcount(si, entry); put_swap_device(si); } return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; p = _swap_info_get(entry); if (!p) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_atomic(page); tmp_count = map[offset]; kunmap_atomic(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(p, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || !cluster_is_huge(ci)) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < SWAPFILE_CLUSTER; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool page_swapped(struct page *page) { swp_entry_t entry; struct swap_info_struct *si; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) return page_swapcount(page) != 0; page = compound_head(page); entry.val = page_private(page); si = _swap_info_get(entry); if (si) return swap_page_trans_huge_swapped(si, entry); return false; } static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, int *total_swapcount) { int i, map_swapcount, _total_mapcount, _total_swapcount; unsigned long offset = 0; struct swap_info_struct *si; struct swap_cluster_info *ci = NULL; unsigned char *map = NULL; int mapcount, swapcount = 0; /* hugetlbfs shouldn't call it */ VM_BUG_ON_PAGE(PageHuge(page), page); if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) { mapcount = page_trans_huge_mapcount(page, total_mapcount); if (PageSwapCache(page)) swapcount = page_swapcount(page); if (total_swapcount) *total_swapcount = swapcount; return mapcount + swapcount; } page = compound_head(page); _total_mapcount = _total_swapcount = map_swapcount = 0; if (PageSwapCache(page)) { swp_entry_t entry; entry.val = page_private(page); si = _swap_info_get(entry); if (si) { map = si->swap_map; offset = swp_offset(entry); } } if (map) ci = lock_cluster(si, offset); for (i = 0; i < HPAGE_PMD_NR; i++) { mapcount = atomic_read(&page[i]._mapcount) + 1; _total_mapcount += mapcount; if (map) { swapcount = swap_count(map[offset + i]); _total_swapcount += swapcount; } map_swapcount = max(map_swapcount, mapcount + swapcount); } unlock_cluster(ci); if (PageDoubleMap(page)) { map_swapcount -= 1; _total_mapcount -= HPAGE_PMD_NR; } mapcount = compound_mapcount(page); map_swapcount += mapcount; _total_mapcount += mapcount; if (total_mapcount) *total_mapcount = _total_mapcount; if (total_swapcount) *total_swapcount = _total_swapcount; return map_swapcount; } /* * We can write to an anon page without COW if there are no other references * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. * * NOTE: total_map_swapcount should not be relied upon by the caller if * reuse_swap_page() returns false, but it may be always overwritten * (see the other implementation for CONFIG_SWAP=n). */ bool reuse_swap_page(struct page *page, int *total_map_swapcount) { int count, total_mapcount, total_swapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return false; count = page_trans_huge_map_swapcount(page, &total_mapcount, &total_swapcount); if (total_map_swapcount) *total_map_swapcount = total_mapcount + total_swapcount; if (count == 1 && PageSwapCache(page) && (likely(!PageTransCompound(page)) || /* The remaining swap count will be freed soon */ total_swapcount == page_swapcount(page))) { if (!PageWriteback(page)) { page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); } else { swp_entry_t entry; struct swap_info_struct *p; entry.val = page_private(page); p = swap_info_get(entry); if (p->flags & SWP_STABLE_WRITES) { spin_unlock(&p->lock); return false; } spin_unlock(&p->lock); } } return count <= 1; } /* * If swap is getting full, or if there are no more mappings of this page, * then try_to_free_swap is called to free its swap space. */ int try_to_free_swap(struct page *page) { VM_BUG_ON_PAGE(!PageLocked(page), page); if (!PageSwapCache(page)) return 0; if (PageWriteback(page)) return 0; if (page_swapped(page)) return 0; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to try_to_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a page which has already been recorded in the * image as a clean swapcache page, and then reuse its swap for * another page of the image. On waking from hibernation, the * original page might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return 0; page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); return 1; } /* * Free the swap entry like above, but also try to * free the page cache entry if it is the last user. */ int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; unsigned char count; if (non_swap_entry(entry)) return 1; p = _swap_info_get(entry); if (p) { count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); } return p != NULL; } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { struct page *swapcache; spinlock_t *ptl; pte_t *pte; int ret = 1; swapcache = page; page = ksm_might_need_to_copy(page, vma, addr); if (unlikely(!page)) return -ENOMEM; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { ret = 0; goto out; } dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_inactive_or_unevictable(page, vma); } swap_free(entry); out: pte_unmap_unlock(pte, ptl); if (page != swapcache) { unlock_page(page); put_page(page); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct page *page; swp_entry_t entry; pte_t *pte; struct swap_info_struct *si; unsigned long offset; int ret = 0; volatile unsigned char *swap_map; si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { if (!is_swap_pte(*pte)) continue; entry = pte_to_swp_entry(*pte); if (swp_type(entry) != type) continue; offset = swp_offset(entry); if (frontswap && !frontswap_test(si, offset)) continue; pte_unmap(pte); swap_map = &si->swap_map[offset]; page = lookup_swap_cache(entry, vma, addr); if (!page) { struct vm_fault vmf = { .vma = vma, .address = addr, .pmd = pmd, }; page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!page) { if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) goto try_next; return -ENOMEM; } lock_page(page); wait_on_page_writeback(page); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret < 0) { unlock_page(page); put_page(page); goto out; } try_to_free_swap(page); unlock_page(page); put_page(page); if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { ret = FRONTSWAP_PAGES_UNUSED; goto out; } try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); ret = 0; out: return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct vm_area_struct *vma; int ret = 0; mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) { ret = unuse_vma(vma, type, frontswap, fs_pages_to_unuse); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map (or frontswap_map if frontswap parameter is true) * from current position to next entry still in use. Return 0 * if there are no inuse entries after prev till end of the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev, bool frontswap) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) if (!frontswap || frontswap_test(si, i)) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } /* * If the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */ int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct page *page; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) return 0; if (!frontswap) pages_to_unuse = 0; retry: retval = shmem_unuse(type, frontswap, &pages_to_unuse); if (retval) goto out; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); if (retval) { mmput(prev_mm); goto out; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i, frontswap)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); if (!page) continue; /* * It is conceivable that a racing task removed this page from * swap cache just before we acquired the page lock. The page * might even be back in swap cache on another swap area. But * that is okay, try_to_free_swap() only removes stale pages. */ lock_page(page); wait_on_page_writeback(page); try_to_free_swap(page); unlock_page(page); put_page(page); /* * For frontswap, we just need to unuse pages_to_unuse, if * it was specified. Need not check frontswap again here as * we already zeroed out pages_to_unuse if not frontswap. */ if (pages_to_unuse && --pages_to_unuse == 0) goto out; } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() above fails, * that mm is likely to be freeing swap from exit_mmap(), which proceeds * at its own independent pace; and even shmem_writepage() could have * been preempted after get_swap_page(), temporarily hiding that swap. * It's easy and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; retval = -EINTR; } out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. An ordered list of swap extents * is built at swapon time and is then used at swap_writepage/swap_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If * some stray blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the list. To avoid much list walking, we cache the previous * search location in `curr_swap_extent', and start new searches from there. * This is extremely effective. The average number of iterations in * map_swap_page() has been measured at about 0.3 per page. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret >= 0) sis->flags |= SWP_ACTIVATED; if (!ret) { sis->flags |= SWP_FS_OPS; ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *p) { struct block_device *bdev; if (p->bdev) bdev = p->bdev; else bdev = p->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { int i; if (prio >= 0) p->prio = prio; else p->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; for_each_node(i) { if (p->prio >= 0) p->avail_lists[i].prio = -p->prio; else { if (swap_node(p) == i) p->avail_lists[i].prio = 1; else p->avail_lists[i].prio = -p->prio; } } p->swap_map = swap_map; p->cluster_info = cluster_info; } static void _enable_swap_info(struct swap_info_struct *p) { p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for get_swap_page(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&p->list, &swap_active_head); add_to_avail_list(p); } static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } bool has_usable_swap(void) { bool ret = true; spin_lock(&swap_lock); if (plist_head_empty(&swap_active_head)) ret = false; spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } del_from_avail_list(p); spin_lock(&p->lock); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. * * We need synchronize_rcu() here to protect the accessing to * the swap cache data structure. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned int bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = si->pages << (PAGE_SHIFT - 10); inuse = si->inuse_pages << (PAGE_SHIFT - 10); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%u\t%s%u\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { int error; if (S_ISBLK(inode->i_mode)) { p->bdev = blkdev_get_by_dev(inode->i_rdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); if (IS_ERR(p->bdev)) { error = PTR_ERR(p->bdev); p->bdev = NULL; return error; } p->old_block_size = block_size(p->bdev); error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) return error; /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (blk_queue_is_zoned(p->bdev->bd_disk->queue)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } p->lowest_bit = 1; p->cluster_next = 1; p->cluster_nr = 0; maxpages = max_swapfile_size(); last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), last_page << (PAGE_SHIFT - 10)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ cluster_list_init(&p->free_clusters); cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; /* * Haven't marked the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, page_nr); } } /* Haven't marked the cluster free yet, no list operation involved */ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(p, cluster_info, i); if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; /* * Not mark the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); if (nr_extents < 0) return nr_extents; nr_good_pages = p->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } if (!cluster_info) return nr_extents; /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { idx = i * SWAP_CLUSTER_COLS + j; if (idx >= nr_clusters) continue; if (cluster_count(&cluster_info[idx])) continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } return nr_extents; } /* * Helper to sys_swapon determining if a given swap * backing device queue supports DISCARD operations. */ static bool swap_discardable(struct swap_info_struct *si) { struct request_queue *q = bdev_get_queue(si->bdev); if (!q || !blk_queue_discard(q)) return false; return true; } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); INIT_WORK(&p->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; inode = mapping->host; error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->readpage) { error = -EINVAL; goto bad_swap_unlock_inode; } page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap_unlock_inode; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { int cpu; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; p->cluster_next_cpu = alloc_percpu(unsigned int); if (!p->cluster_next_cpu) { error = -ENOMEM; goto bad_swap_unlock_inode; } /* * select a random position to start with to help wear leveling * SSD */ for_each_possible_cpu(cpu) { per_cpu(*p->cluster_next_cpu, cpu) = 1 + prandom_u32_max(p->highest_bit); } nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; goto bad_swap_unlock_inode; } for (ci = 0; ci < nr_cluster; ci++) spin_lock_init(&((cluster_info + ci)->lock)); p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap_unlock_inode; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_map = kvcalloc(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL); if (p->bdev && (swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) p->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) p->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", p, err); } } error = init_swap_address_space(p->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_address_space; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", (p->flags & SWP_AREA_DISCARD) ? "s" : "", (p->flags & SWP_PAGE_DISCARD) ? "c" : "", (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_address_space: exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); p->swap_file = NULL; p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (page && !IS_ERR(page)) { kunmap(page); put_page(page); } if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += si->inuse_pages; } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that a swap entry is valid and increment its swap map count. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used.