1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 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 // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? */ int page_cluster; /* Protecting only lru_rotate.pvec which requires disabling interrupts */ struct lru_rotate { local_lock_t lock; struct pagevec pvec; }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * The following struct pagevec are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ struct lru_pvecs { local_lock_t lock; struct pagevec lru_add; struct pagevec lru_deactivate_file; struct pagevec lru_deactivate; struct pagevec lru_lazyfree; #ifdef CONFIG_SMP struct pagevec activate_page; #endif }; static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. */ static void __page_cache_release(struct page *page) { if (PageLRU(page)) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; unsigned long flags; spin_lock_irqsave(&pgdat->lru_lock, flags); lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); spin_unlock_irqrestore(&pgdat->lru_lock, flags); } __ClearPageWaiters(page); } static void __put_single_page(struct page *page) { __page_cache_release(page); mem_cgroup_uncharge(page); free_unref_page(page); } static void __put_compound_page(struct page *page) { /* * __page_cache_release() is supposed to be called for thp, not for * hugetlb. This is because hugetlb page does never have PageLRU set * (it's never listed to any LRU lists) and no memcg routines should * be called for hugetlb (it has a separate hugetlb_cgroup.) */ if (!PageHuge(page)) __page_cache_release(page); destroy_compound_page(page); } void __put_page(struct page *page) { if (is_zone_device_page(page)) { put_dev_pagemap(page->pgmap); /* * The page belongs to the device that created pgmap. Do * not return it to page allocator. */ return; } if (unlikely(PageCompound(page))) __put_compound_page(page); else __put_single_page(page); } EXPORT_SYMBOL(__put_page); /** * put_pages_list() - release a list of pages * @pages: list of pages threaded on page->lru * * Release a list of pages which are strung together on page.lru. Currently * used by read_cache_pages() and related error recovery code. */ void put_pages_list(struct list_head *pages) { while (!list_empty(pages)) { struct page *victim; victim = lru_to_page(pages); list_del(&victim->lru); put_page(victim); } } EXPORT_SYMBOL(put_pages_list); /* * get_kernel_pages() - pin kernel pages in memory * @kiov: An array of struct kvec structures * @nr_segs: number of segments to pin * @write: pinning for read/write, currently ignored * @pages: array that receives pointers to the pages pinned. * Should be at least nr_segs long. * * Returns number of pages pinned. This may be fewer than the number * requested. If nr_pages is 0 or negative, returns 0. If no pages * were pinned, returns -errno. Each page returned must be released * with a put_page() call when it is finished with. */ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, struct page **pages) { int seg; for (seg = 0; seg < nr_segs; seg++) { if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) return seg; pages[seg] = kmap_to_page(kiov[seg].iov_base); get_page(pages[seg]); } return seg; } EXPORT_SYMBOL_GPL(get_kernel_pages); /* * get_kernel_page() - pin a kernel page in memory * @start: starting kernel address * @write: pinning for read/write, currently ignored * @pages: array that receives pointer to the page pinned. * Must be at least nr_segs long. * * Returns 1 if page is pinned. If the page was not pinned, returns * -errno. The page returned must be released with a put_page() call * when it is finished with. */ int get_kernel_page(unsigned long start, int write, struct page **pages) { const struct kvec kiov = { .iov_base = (void *)start, .iov_len = PAGE_SIZE }; return get_kernel_pages(&kiov, 1, write, pages); } EXPORT_SYMBOL_GPL(get_kernel_page); static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), void *arg) { int i; struct pglist_data *pgdat = NULL; struct lruvec *lruvec; unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); pgdat = pagepgdat; spin_lock_irqsave(&pgdat->lru_lock, flags); } lruvec = mem_cgroup_page_lruvec(page, pgdat); (*move_fn)(page, lruvec, arg); } if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); release_pages(pvec->pages, pvec->nr); pagevec_reinit(pvec); } static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, void *arg) { int *pgmoved = arg; if (PageLRU(page) && !PageUnevictable(page)) { del_page_from_lru_list(page, lruvec, page_lru(page)); ClearPageActive(page); add_page_to_lru_list_tail(page, lruvec, page_lru(page)); (*pgmoved) += thp_nr_pages(page); } } /* * pagevec_move_tail() must be called with IRQ disabled. * Otherwise this may cause nasty races. */ static void pagevec_move_tail(struct pagevec *pvec) { int pgmoved = 0; pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved); __count_vm_events(PGROTATED, pgmoved); } /* * Writeback is about to end against a page which has been marked for immediate * reclaim. If it still appears to be reclaimable, move it to the tail of the * inactive list. */ void rotate_reclaimable_page(struct page *page) { if (!PageLocked(page) && !PageDirty(page) && !PageUnevictable(page) && PageLRU(page)) { struct pagevec *pvec; unsigned long flags; get_page(page); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { do { unsigned long lrusize; /* Record cost event */ if (file) lruvec->file_cost += nr_pages; else lruvec->anon_cost += nr_pages; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_page(struct page *page) { lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), page_is_file_lru(page), thp_nr_pages(page)); } static void __activate_page(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru); SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); trace_mm_lru_activate(page); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } } #ifdef CONFIG_SMP static void activate_page_drain(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, __activate_page, NULL); } static bool need_activate_page_drain(int cpu) { return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; } static void activate_page(struct page *page) { page = compound_head(page); if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.activate_page); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); local_unlock(&lru_pvecs.lock); } } #else static inline void activate_page_drain(int cpu) { } static void activate_page(struct page *page) { pg_data_t *pgdat = page_pgdat(page); page = compound_head(page); spin_lock_irq(&pgdat->lru_lock); __activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL); spin_unlock_irq(&pgdat->lru_lock); } #endif static void __lru_cache_activate_page(struct page *page) { struct pagevec *pvec; int i; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); /* * Search backwards on the optimistic assumption that the page being * activated has just been added to this pagevec. Note that only * the local pagevec is examined as a !PageLRU page could be in the * process of being released, reclaimed, migrated or on a remote * pagevec that is currently being drained. Furthermore, marking * a remote pagevec's page PageActive potentially hits a race where * a page is marked PageActive just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = pagevec_count(pvec) - 1; i >= 0; i--) { struct page *pagevec_page = pvec->pages[i]; if (pagevec_page == page) { SetPageActive(page); break; } } local_unlock(&lru_pvecs.lock); } /* * Mark a page as having seen activity. * * inactive,unreferenced -> inactive,referenced * inactive,referenced -> active,unreferenced * active,unreferenced -> active,referenced * * When a newly allocated page is not yet visible, so safe for non-atomic ops, * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). */ void mark_page_accessed(struct page *page) { page = compound_head(page); if (!PageReferenced(page)) { SetPageReferenced(page); } else if (PageUnevictable(page)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * evictable page accessed has no effect. */ } else if (!PageActive(page)) { /* * If the page is on the LRU, queue it for activation via * lru_pvecs.activate_page. Otherwise, assume the page is on a * pagevec, mark it active and it'll be moved to the active * LRU on the next drain. */ if (PageLRU(page)) activate_page(page); else __lru_cache_activate_page(page); ClearPageReferenced(page); workingset_activation(page); } if (page_is_idle(page)) clear_page_idle(page); } EXPORT_SYMBOL(mark_page_accessed); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. * * Queue the page for addition to the LRU via pagevec. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * pagevec is drained. This gives a chance for the caller of lru_cache_add() * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { struct pagevec *pvec; VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); get_page(page); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } EXPORT_SYMBOL(lru_cache_add); /** * lru_cache_add_inactive_or_unevictable * @page: the page to be added to LRU * @vma: vma in which page is mapped for determining reclaimability * * Place @page on the inactive or unevictable LRU list, depending on its * evictability. */ void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { bool unevictable; VM_BUG_ON_PAGE(PageLRU(page), page); unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } lru_cache_add(page); } /* * If the page can not be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the page isn't page_mapped and dirty/writeback, the page * could reclaim asap using PG_reclaim. * * 1. active, mapped page -> none * 2. active, dirty/writeback page -> inactive, head, PG_reclaim * 3. inactive, mapped page -> none * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, why it moves inactive's head, the VM expects the page would * be write it out by flusher threads as this is much more effective * than the single-page writeout from reclaim. */ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, void *arg) { int lru; bool active; int nr_pages = thp_nr_pages(page); if (!PageLRU(page)) return; if (PageUnevictable(page)) return; /* Some processes are using the page */ if (page_mapped(page)) return; active = PageActive(page); lru = page_lru_base_type(page); del_page_from_lru_list(page, lruvec, lru + active); ClearPageActive(page); ClearPageReferenced(page); if (PageWriteback(page) || PageDirty(page)) { /* * PG_reclaim could be raced with end_page_writeback * It can make readahead confusing. But race window * is _really_ small and it's non-critical problem. */ add_page_to_lru_list(page, lruvec, lru); SetPageReclaim(page); } else { /* * The page's writeback ends up during pagevec * We moves tha page into tail of inactive. */ add_page_to_lru_list_tail(page, lruvec, lru); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); ClearPageActive(page); ClearPageReferenced(page); add_page_to_lru_list(page, lruvec, lru); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { bool active = PageActive(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, LRU_INACTIVE_ANON + active); ClearPageActive(page); ClearPageReferenced(page); /* * Lazyfree pages are clean anonymous pages. They have * PG_swapbacked flag cleared, to distinguish them from normal * anonymous pages */ ClearPageSwapBacked(page); add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } } /* * Drain pages out of the cpu's pagevecs. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu); if (pagevec_count(pvec)) __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate.pvec, cpu); /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(pagevec_count(pvec))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&lru_rotate.lock, flags); pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); activate_page_drain(cpu); } /** * deactivate_file_page - forcefully deactivate a file page * @page: page to deactivate * * This function hints the VM that @page is a good reclaim candidate, * for example if its invalidation fails due to the page being dirty * or under writeback. */ void deactivate_file_page(struct page *page) { /* * In a workload with many unevictable page such as mprotect, * unevictable page deactivation for accelerating reclaim is pointless. */ if (PageUnevictable(page)) return; if (likely(get_page_unless_zero(page))) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); local_unlock(&lru_pvecs.lock); } } /* * deactivate_page - deactivate a page * @page: page to deactivate * * deactivate_page() moves @page to the inactive list if @page was on the active * list and was not an unevictable page. This is done to accelerate the reclaim * of @page. */ void deactivate_page(struct page *page) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); local_unlock(&lru_pvecs.lock); } } /** * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate * * mark_page_lazyfree() moves @page to the inactive file list. * This is done to accelerate the reclaim of @page. */ void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); local_unlock(&lru_pvecs.lock); } } void lru_add_drain(void) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&lru_pvecs.lock); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ void lru_add_drain_all(void) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee pagevec counter stores visible by this CPU are visible to * other CPUs before loading the current drain generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the new global * drain generation number is stored before loading pagevec counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ /** * release_pages - batched put_page() * @pages: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @pages. If it * fell to zero, remove the page from the LRU and free it. */ void release_pages(struct page **pages, int nr) { int i; LIST_HEAD(pages_to_free); struct pglist_data *locked_pgdat = NULL; struct lruvec *lruvec; unsigned long flags; unsigned int lock_batch; for (i = 0; i < nr; i++) { struct page *page = pages[i]; /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the * same pgdat. The lock is held only if pgdat != NULL. */ if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } page = compound_head(page); if (is_huge_zero_page(page)) continue; if (is_zone_device_page(page)) { if (locked_pgdat) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } /* * ZONE_DEVICE pages that return 'false' from * page_is_devmap_managed() do not require special * processing, and instead, expect a call to * put_page_testzero(). */ if (page_is_devmap_managed(page)) { put_devmap_managed_page(page); continue; } } if (!put_page_testzero(page)) continue; if (PageCompound(page)) { if (locked_pgdat) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } __put_compound_page(page); continue; } if (PageLRU(page)) { struct pglist_data *pgdat = page_pgdat(page); if (pgdat != locked_pgdat) { if (locked_pgdat) spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); lock_batch = 0; locked_pgdat = pgdat; spin_lock_irqsave(&locked_pgdat->lru_lock, flags); } lruvec = mem_cgroup_page_lruvec(page, locked_pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); } __ClearPageWaiters(page); list_add(&page->lru, &pages_to_free); } if (locked_pgdat) spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); mem_cgroup_uncharge_list(&pages_to_free); free_unref_page_list(&pages_to_free); } EXPORT_SYMBOL(release_pages); /* * The pages which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those pages may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __pagevec_release() will drain those queues here. __pagevec_lru_add() * and __pagevec_lru_add_active() call release_pages() directly to avoid * mutual recursion. */ void __pagevec_release(struct pagevec *pvec) { if (!pvec->percpu_pvec_drained) { lru_add_drain(); pvec->percpu_pvec_drained = true; } release_pages(pvec->pages, pagevec_count(pvec)); pagevec_reinit(pvec); } EXPORT_SYMBOL(__pagevec_release); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* used by __split_huge_page_refcount() */ void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *list) { VM_BUG_ON_PAGE(!PageHead(page), page); VM_BUG_ON_PAGE(PageCompound(page_tail), page); VM_BUG_ON_PAGE(PageLRU(page_tail), page); lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock); if (!list) SetPageLRU(page_tail); if (likely(PageLRU(page))) list_add_tail(&page_tail->lru, &page->lru); else if (list) { /* page reclaim is reclaiming a huge page */ get_page(page_tail); list_add_tail(&page_tail->lru, list); } else { /* * Head page has not yet been counted, as an hpage, * so we must account for each subpage individually. * * Put page_tail on the list at the correct position * so they all end up in order. */ add_page_to_lru_list_tail(page_tail, lruvec, page_lru(page_tail)); } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, void *arg) { enum lru_list lru; int was_unevictable = TestClearPageUnevictable(page); int nr_pages = thp_nr_pages(page); VM_BUG_ON_PAGE(PageLRU(page), page); /* * Page becomes evictable in two ways: * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()]. * 2) Before acquiring LRU lock to put the page to correct LRU and then * a) do PageLRU check with lock [check_move_unevictable_pages] * b) do PageLRU check before lock [clear_page_mlock] * * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need * following strict ordering: * * #0: __pagevec_lru_add_fn #1: clear_page_mlock * * SetPageLRU() TestClearPageMlocked() * smp_mb() // explicit ordering // above provides strict * // ordering * PageMlocked() PageLRU() * * * if '#1' does not observe setting of PG_lru by '#0' and fails * isolation, the explicit barrier will make sure that page_evictable * check will put the page in correct LRU. Without smp_mb(), SetPageLRU * can be reordered after PageMlocked check and can make '#1' to fail * the isolation of the page whose Mlocked bit is cleared (#0 is also * looking at the same page) and the evictable page will be stranded * in an unevictable LRU. */ SetPageLRU(page); smp_mb__after_atomic(); if (page_evictable(page)) { lru = page_lru(page); if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { lru = LRU_UNEVICTABLE; ClearPageActive(page); SetPageUnevictable(page); if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } add_page_to_lru_list(page, lruvec, lru); trace_mm_lru_insertion(page, lru); } /* * Add the passed pages to the LRU, then drop the caller's refcount * on them. Reinitialises the caller's pagevec. */ void __pagevec_lru_add(struct pagevec *pvec) { pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL); } /** * pagevec_lookup_entries - gang pagecache lookup * @pvec: Where the resulting entries are placed * @mapping: The address_space to search * @start: The starting entry index * @nr_entries: The maximum number of pages * @indices: The cache indices corresponding to the entries in @pvec * * pagevec_lookup_entries() will search for and return a group of up * to @nr_pages pages and shadow entries in the mapping. All * entries are placed in @pvec. pagevec_lookup_entries() takes a * reference against actual pages in @pvec. * * The search returns a group of mapping-contiguous entries with * ascending indexes. There may be holes in the indices due to * not-present entries. * * Only one subpage of a Transparent Huge Page is returned in one call: * allowing truncate_inode_pages_range() to evict the whole THP without * cycling through a pagevec of extra references. * * pagevec_lookup_entries() returns the number of entries which were * found. */ unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_entries, pgoff_t *indices) { pvec->nr = find_get_entries(mapping, start, nr_entries, pvec->pages, indices); return pagevec_count(pvec); } /** * pagevec_remove_exceptionals - pagevec exceptionals pruning * @pvec: The pagevec to prune * * pagevec_lookup_entries() fills both pages and exceptional radix * tree entries into the pagevec. This function prunes all * exceptionals from @pvec without leaving holes, so that it can be * passed on to page-only pagevec operations. */ void pagevec_remove_exceptionals(struct pagevec *pvec) { int i, j; for (i = 0, j = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; if (!xa_is_value(page)) pvec->pages[j++] = page; } pvec->nr = j; } /** * pagevec_lookup_range - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search * @start: The starting page index * @end: The final page index * * pagevec_lookup_range() will search for & return a group of up to PAGEVEC_SIZE * pages in the mapping starting from index @start and upto index @end * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a * reference against the pages in @pvec. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. We * also update @start to index the next page for the traversal. * * pagevec_lookup_range() returns the number of pages which were found. If this * number is smaller than PAGEVEC_SIZE, the end of specified range has been * reached. */ unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end) { pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range); unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range_tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned max_pages) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range_nr_tag); /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ } #ifdef CONFIG_DEV_PAGEMAP_OPS void put_devmap_managed_page(struct page *page) { int count; if (WARN_ON_ONCE(!page_is_devmap_managed(page))) return; count = page_ref_dec_return(page); /* * devmap page refcounts are 1-based, rather than 0-based: if * refcount is 1, then the page is free and the refcount is * stable because nobody holds a reference on the page. */ if (count == 1) free_devmap_managed_page(page); else if (!count) __put_page(page); } EXPORT_SYMBOL(put_devmap_managed_page); #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MIN_HEAP_H #define _LINUX_MIN_HEAP_H #include <linux/bug.h> #include <linux/string.h> #include <linux/types.h> /** * struct min_heap - Data structure to hold a min-heap. * @data: Start of array holding the heap elements. * @nr: Number of elements currently in the heap. * @size: Maximum number of elements that can be held in current storage. */ struct min_heap { void *data; int nr; int size; }; /** * struct min_heap_callbacks - Data/functions to customise the min_heap. * @elem_size: The nr of each element in bytes. * @less: Partial order function for this heap. * @swp: Swap elements function. */ struct min_heap_callbacks { int elem_size; bool (*less)(const void *lhs, const void *rhs); void (*swp)(void *lhs, void *rhs); }; /* Sift the element at pos down the heap. */ static __always_inline void min_heapify(struct min_heap *heap, int pos, const struct min_heap_callbacks *func) { void *left, *right, *parent, *smallest; void *data = heap->data; for (;;) { if (pos * 2 + 1 >= heap->nr) break; left = data + ((pos * 2 + 1) * func->elem_size); parent = data + (pos * func->elem_size); smallest = parent; if (func->less(left, smallest)) smallest = left; if (pos * 2 + 2 < heap->nr) { right = data + ((pos * 2 + 2) * func->elem_size); if (func->less(right, smallest)) smallest = right; } if (smallest == parent) break; func->swp(smallest, parent); if (smallest == left) pos = (pos * 2) + 1; else pos = (pos * 2) + 2; } } /* Floyd's approach to heapification that is O(nr). */ static __always_inline void min_heapify_all(struct min_heap *heap, const struct min_heap_callbacks *func) { int i; for (i = heap->nr / 2; i >= 0; i--) min_heapify(heap, i, func); } /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline void min_heap_pop(struct min_heap *heap, const struct min_heap_callbacks *func) { void *data = heap->data; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) return; /* Place last element at the root (position 0) and then sift down. */ heap->nr--; memcpy(data, data + (heap->nr * func->elem_size), func->elem_size); min_heapify(heap, 0, func); } /* * Remove the minimum element and then push the given element. The * implementation performs 1 sift (O(log2(nr))) and is therefore more * efficient than a pop followed by a push that does 2. */ static __always_inline void min_heap_pop_push(struct min_heap *heap, const void *element, const struct min_heap_callbacks *func) { memcpy(heap->data, element, func->elem_size); min_heapify(heap, 0, func); } /* Push an element on to the heap, O(log2(nr)). */ static __always_inline void min_heap_push(struct min_heap *heap, const void *element, const struct min_heap_callbacks *func) { void *data = heap->data; void *child, *parent; int pos; if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap")) return; /* Place at the end of data. */ pos = heap->nr; memcpy(data + (pos * func->elem_size), element, func->elem_size); heap->nr++; /* Sift child at pos up. */ for (; pos > 0; pos = (pos - 1) / 2) { child = data + (pos * func->elem_size); parent = data + ((pos - 1) / 2) * func->elem_size; if (func->less(parent, child)) break; func->swp(parent, child); } } #endif /* _LINUX_MIN_HEAP_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 // SPDX-License-Identifier: GPL-2.0 /* * The class-specific portions of the driver model * * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2009 Novell Inc. * Copyright (c) 2012-2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> * Copyright (c) 2012-2019 Linux Foundation * * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_CLASS_H_ #define _DEVICE_CLASS_H_ #include <linux/kobject.h> #include <linux/klist.h> #include <linux/pm.h> #include <linux/device/bus.h> struct device; struct fwnode_handle; /** * struct class - device classes * @name: Name of the class. * @owner: The module owner. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. * @dev_kobj: The kobject that represents this class and links it into the hierarchy. * @dev_uevent: Called when a device is added, removed from this class, or a * few other things that generate uevents to add the environment * variables. * @devnode: Callback to provide the devtmpfs. * @class_release: Called to release this class. * @dev_release: Called to release the device. * @shutdown_pre: Called at shut-down time before driver shutdown. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. * @get_ownership: Allows class to specify uid/gid of the sysfs directories * for the devices belonging to the class. Usually tied to * device's namespace. * @pm: The default device power management operations of this class. * @p: The private data of the driver core, no one other than the * driver core can touch this. * * A class is a higher-level view of a device that abstracts out low-level * implementation details. Drivers may see a SCSI disk or an ATA disk, but, * at the class level, they are all simply disks. Classes allow user space * to work with devices based on what they do, rather than how they are * connected or how they work. */ struct class { const char *name; struct module *owner; const struct attribute_group **class_groups; const struct attribute_group **dev_groups; struct kobject *dev_kobj; int (*dev_uevent)(struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(struct device *dev, umode_t *mode); void (*class_release)(struct class *class); void (*dev_release)(struct device *dev); int (*shutdown_pre)(struct device *dev); const struct kobj_ns_type_operations *ns_type; const void *(*namespace)(struct device *dev); void (*get_ownership)(struct device *dev, kuid_t *uid, kgid_t *gid); const struct dev_pm_ops *pm; struct subsys_private *p; }; struct class_dev_iter { struct klist_iter ki; const struct device_type *type; }; extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; extern int __must_check __class_register(struct class *class, struct lock_class_key *key); extern void class_unregister(struct class *class); /* This is a #define to keep the compiler from merging different * instances of the __key variable */ #define class_register(class) \ ({ \ static struct lock_class_key __key; \ __class_register(class, &__key); \ }) struct class_compat; struct class_compat *class_compat_register(const char *name); void class_compat_unregister(struct class_compat *cls); int class_compat_create_link(struct class_compat *cls, struct device *dev, struct device *device_link); void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); extern void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, struct device *start, const struct device_type *type); extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); extern int class_for_each_device(struct class *class, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); extern struct device *class_find_device(struct class *class, struct device *start, const void *data, int (*match)(struct device *, const void *)); /** * class_find_device_by_name - device iterator for locating a particular device * of a specific name. * @class: class type * @name: name of the device to match */ static inline struct device *class_find_device_by_name(struct class *class, const char *name) { return class_find_device(class, NULL, name, device_match_name); } /** * class_find_device_by_of_node : device iterator for locating a particular device * matching the of_node. * @class: class type * @np: of_node of the device to match. */ static inline struct device * class_find_device_by_of_node(struct class *class, const struct device_node *np) { return class_find_device(class, NULL, np, device_match_of_node); } /** * class_find_device_by_fwnode : device iterator for locating a particular device * matching the fwnode. * @class: class type * @fwnode: fwnode of the device to match. */ static inline struct device * class_find_device_by_fwnode(struct class *class, const struct fwnode_handle *fwnode) { return class_find_device(class, NULL, fwnode, device_match_fwnode); } /** * class_find_device_by_devt : device iterator for locating a particular device * matching the device type. * @class: class type * @devt: device type of the device to match. */ static inline struct device *class_find_device_by_devt(struct class *class, dev_t devt) { return class_find_device(class, NULL, &devt, device_match_devt); } #ifdef CONFIG_ACPI struct acpi_device; /** * class_find_device_by_acpi_dev : device iterator for locating a particular * device matching the ACPI_COMPANION device. * @class: class type * @adev: ACPI_COMPANION device to match. */ static inline struct device * class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) { return class_find_device(class, NULL, adev, device_match_acpi_dev); } #else static inline struct device * class_find_device_by_acpi_dev(struct class *class, const void *adev) { return NULL; } #endif struct class_attribute { struct attribute attr; ssize_t (*show)(struct class *class, struct class_attribute *attr, char *buf); ssize_t (*store)(struct class *class, struct class_attribute *attr, const char *buf, size_t count); }; #define CLASS_ATTR_RW(_name) \ struct class_attribute class_attr_##_name = __ATTR_RW(_name) #define CLASS_ATTR_RO(_name) \ struct class_attribute class_attr_##_name = __ATTR_RO(_name) #define CLASS_ATTR_WO(_name) \ struct class_attribute class_attr_##_name = __ATTR_WO(_name) extern int __must_check class_create_file_ns(struct class *class, const struct class_attribute *attr, const void *ns); extern void class_remove_file_ns(struct class *class, const struct class_attribute *attr, const void *ns); static inline int __must_check class_create_file(struct class *class, const struct class_attribute *attr) { return class_create_file_ns(class, attr, NULL); } static inline void class_remove_file(struct class *class, const struct class_attribute *attr) { return class_remove_file_ns(class, attr, NULL); } /* Simple class attribute that is just a static string */ struct class_attribute_string { struct class_attribute attr; char *str; }; /* Currently read-only only */ #define _CLASS_ATTR_STRING(_name, _mode, _str) \ { __ATTR(_name, _mode, show_class_attr_string, NULL), _str } #define CLASS_ATTR_STRING(_name, _mode, _str) \ struct class_attribute_string class_attr_##_name = \ _CLASS_ATTR_STRING(_name, _mode, _str) extern ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, char *buf); struct class_interface { struct list_head node; struct class *class; int (*add_dev) (struct device *, struct class_interface *); void (*remove_dev) (struct device *, struct class_interface *); }; extern int __must_check class_interface_register(struct class_interface *); extern void class_interface_unregister(struct class_interface *); extern struct class * __must_check __class_create(struct module *owner, const char *name, struct lock_class_key *key); extern void class_destroy(struct class *cls); /* This is a #define to keep the compiler from merging different * instances of the __key variable */ #define class_create(owner, name) \ ({ \ static struct lock_class_key __key; \ __class_create(owner, name, &__key); \ }) #endif /* _DEVICE_CLASS_H_ */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> * * Architecture independence: * Copyright (c) 2005, Bull S.A. * Written by Pierre Peiffer <pierre.peiffer@bull.net> */ /* * Extents support for EXT4 * * TODO: * - ext4*_error() should be used in some situations * - analyze all BUG()/BUG_ON(), use -EIO where appropriate * - smart tree reduction */ #include <linux/fs.h> #include <linux/time.h> #include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fiemap.h> #include <linux/backing-dev.h> #include <linux/iomap.h> #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" #include <trace/events/ext4.h> /* * used by extent splitting. */ #define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \ due to ENOSPC */ #define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */ #define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */ #define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */ #define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */ static __le32 ext4_extent_block_csum(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)eh, EXT4_EXTENT_TAIL_OFFSET(eh)); return cpu_to_le32(csum); } static int ext4_extent_block_csum_verify(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); if (et->et_checksum != ext4_extent_block_csum(inode, eh)) return 0; return 1; } static void ext4_extent_block_csum_set(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); et->et_checksum = ext4_extent_block_csum(inode, eh); } static int ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, ext4_lblk_t split, int split_flag, int flags); static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) { /* * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; } /* * Make sure 'handle' has at least 'check_cred' credits. If not, restart * transaction with 'restart_cred' credits. The function drops i_data_sem * when restarting transaction and gets it after transaction is restarted. * * The function returns 0 on success, 1 if transaction had to be restarted, * and < 0 in case of fatal error. */ int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, int check_cred, int restart_cred, int revoke_cred) { int ret; int dropped = 0; ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred, revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped)); if (dropped) down_write(&EXT4_I(inode)->i_data_sem); return ret; } /* * could return: * - EROFS * - ENOMEM */ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err = 0; if (path->p_bh) { /* path points to block */ BUFFER_TRACE(path->p_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, path->p_bh); /* * The extent buffer's verified bit will be set again in * __ext4_ext_dirty(). We could leave an inconsistent * buffer if the extents updating procudure break off du * to some error happens, force to check it again. */ if (!err) clear_buffer_verified(path->p_bh); } /* path points to leaf/index in inode body */ /* we use in-core data, no need to protect them */ return err; } /* * could return: * - EROFS * - ENOMEM * - EIO */ static int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err; WARN_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (path->p_bh) { ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh)); /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); /* Extents updating done, re-set verified flag */ if (!err) set_buffer_verified(path->p_bh); } else { /* path points to leaf/index in inode body */ err = ext4_mark_inode_dirty(handle, inode); } return err; } #define ext4_ext_dirty(handle, inode, path) \ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { if (path) { int depth = path->p_depth; struct ext4_extent *ex; /* * Try to predict block placement assuming that we are * filling in a file which will eventually be * non-sparse --- i.e., in the case of libbfd writing * an ELF object sections out-of-order but in a way * the eventually results in a contiguous object or * executable file, or some database extending a table * space file. However, this is actually somewhat * non-ideal if we are writing a sparse file such as * qemu or KVM writing a raw image file that is going * to stay fairly sparse, since it will end up * fragmenting the file system's free space. Maybe we * should have some hueristics or some way to allow * userspace to pass a hint to file system, * especially if the latter case turns out to be * common. */ ex = path[depth].p_ext; if (ex) { ext4_fsblk_t ext_pblk = ext4_ext_pblock(ex); ext4_lblk_t ext_block = le32_to_cpu(ex->ee_block); if (block > ext_block) return ext_pblk + (block - ext_block); else return ext_pblk - (ext_block - block); } /* it looks like index is empty; * try to find starting block from index itself */ if (path[depth].p_bh) return path[depth].p_bh->b_blocknr; } /* OK. use inode's group */ return ext4_inode_to_goal_block(inode); } /* * Allocation for a meta data block */ static ext4_fsblk_t ext4_ext_new_meta_block(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex, int *err, unsigned int flags) { ext4_fsblk_t goal, newblock; goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block)); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, err); return newblock; } static inline int ext4_ext_space_block(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 6) size = 6; #endif return size; } static inline int ext4_ext_space_block_idx(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 5) size = 5; #endif return size; } static inline int ext4_ext_space_root(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 3) size = 3; #endif return size; } static inline int ext4_ext_space_root_idx(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 4) size = 4; #endif return size; } static inline int ext4_force_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, ext4_lblk_t lblk, int nofail) { struct ext4_ext_path *path = *ppath; int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext); int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO; if (nofail) flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL; return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ? EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0, flags); } static int ext4_ext_max_entries(struct inode *inode, int depth) { int max; if (depth == ext_depth(inode)) { if (depth == 0) max = ext4_ext_space_root(inode, 1); else max = ext4_ext_space_root_idx(inode, 1); } else { if (depth == 0) max = ext4_ext_space_block(inode, 1); else max = ext4_ext_space_block_idx(inode, 1); } return max; } static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); /* * We allow neither: * - zero length * - overflow/wrap-around */ if (lblock + len <= lblock) return 0; return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, struct ext4_extent_header *eh, ext4_lblk_t lblk, ext4_fsblk_t *pblk, int depth) { unsigned short entries; ext4_lblk_t lblock = 0; ext4_lblk_t prev = 0; if (eh->eh_entries == 0) return 1; entries = le16_to_cpu(eh->eh_entries); if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); /* * The logical block in the first entry should equal to * the number in the index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext->ee_block)) return 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); if ((lblock <= prev) && prev) { *pblk = ext4_ext_pblock(ext); return 0; } prev = lblock + ext4_ext_get_actual_len(ext) - 1; ext++; entries--; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); /* * The logical block in the first entry should equal to * the number in the parent index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext_idx->ei_block)) return 0; while (entries) { if (!ext4_valid_extent_idx(inode, ext_idx)) return 0; /* Check for overlapping index extents */ lblock = le32_to_cpu(ext_idx->ei_block); if ((lblock <= prev) && prev) { *pblk = ext4_idx_pblock(ext_idx); return 0; } ext_idx++; entries--; prev = lblock; } } return 1; } static int __ext4_ext_check(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_header *eh, int depth, ext4_fsblk_t pblk, ext4_lblk_t lblk) { const char *error_msg; int max = 0, err = -EFSCORRUPTED; if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { error_msg = "invalid magic"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_depth) != depth)) { error_msg = "unexpected eh_depth"; goto corrupted; } if (unlikely(eh->eh_max == 0)) { error_msg = "invalid eh_max"; goto corrupted; } max = ext4_ext_max_entries(inode, depth); if (unlikely(le16_to_cpu(eh->eh_max) > max)) { error_msg = "too large eh_max"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) { error_msg = "invalid eh_entries"; goto corrupted; } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } if (unlikely(depth > 32)) { error_msg = "too large eh_depth"; goto corrupted; } /* Verify checksum on non-root extent tree nodes */ if (ext_depth(inode) != depth && !ext4_extent_block_csum_verify(inode, eh)) { error_msg = "extent tree corrupted"; err = -EFSBADCRC; goto corrupted; } return 0; corrupted: ext4_error_inode_err(inode, function, line, 0, -err, "pblk %llu bad header/extent: %s - magic %x, " "entries %u, max %u(%u), depth %u(%u)", (unsigned long long) pblk, error_msg, le16_to_cpu(eh->eh_magic), le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), max, le16_to_cpu(eh->eh_depth), depth); return err; } #define ext4_ext_check(inode, eh, depth, pblk) \ __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk), 0) int ext4_ext_check_inode(struct inode *inode) { return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); } static void ext4_cache_extents(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); ext4_lblk_t prev = 0; int i; for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { unsigned int status = EXTENT_STATUS_WRITTEN; ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); int len = ext4_ext_get_actual_len(ex); if (prev && (prev != lblk)) ext4_es_cache_extent(inode, prev, lblk - prev, ~0, EXTENT_STATUS_HOLE); if (ext4_ext_is_unwritten(ex)) status = EXTENT_STATUS_UNWRITTEN; ext4_es_cache_extent(inode, lblk, len, ext4_ext_pblock(ex), status); prev = lblk + len; } } static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_idx *idx, int depth, int flags) { struct buffer_head *bh; int err; gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS; ext4_fsblk_t pblk; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; pblk = ext4_idx_pblock(idx); bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (!bh_uptodate_or_lock(bh)) { trace_ext4_ext_load_extent(inode, pblk, _RET_IP_); err = ext4_read_bh(bh, 0, NULL); if (err < 0) goto errout; } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; err = __ext4_ext_check(function, line, inode, ext_block_hdr(bh), depth, pblk, le32_to_cpu(idx->ei_block)); if (err) goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries */ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { struct ext4_extent_header *eh = ext_block_hdr(bh); ext4_cache_extents(inode, eh); } return bh; errout: put_bh(bh); return ERR_PTR(err); } #define read_extent_tree_block(inode, idx, depth, flags) \ __read_extent_tree_block(__func__, __LINE__, (inode), (idx), \ (depth), (flags)) /* * This function is called to cache a file's extent information in the * extent status tree */ int ext4_ext_precache(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_ext_path *path = NULL; struct buffer_head *bh; int i = 0, depth, ret = 0; if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return 0; /* not an extent-mapped inode */ down_read(&ei->i_data_sem); depth = ext_depth(inode); /* Don't cache anything if there are no external extent blocks */ if (!depth) { up_read(&ei->i_data_sem); return ret; } path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS); if (path == NULL) { up_read(&ei->i_data_sem); return -ENOMEM; } path[0].p_hdr = ext_inode_hdr(inode); ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0); if (ret) goto out; path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr); while (i >= 0) { /* * If this is a leaf block or we've reached the end of * the index block, go up */ if ((i == depth) || path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) { brelse(path[i].p_bh); path[i].p_bh = NULL; i--; continue; } bh = read_extent_tree_block(inode, path[i].p_idx++, depth - i - 1, EXT4_EX_FORCE_CACHE); if (IS_ERR(bh)) { ret = PTR_ERR(bh); break; } i++; path[i].p_bh = bh; path[i].p_hdr = ext_block_hdr(bh); path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr); } ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED); out: up_read(&ei->i_data_sem); ext4_ext_drop_refs(path); kfree(path); return ret; } #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { int k, l = path->p_depth; ext_debug(inode, "path:"); for (k = 0; k <= l; k++, path++) { if (path->p_idx) { ext_debug(inode, " %d->%llu", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { ext_debug(inode, " %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext4_ext_pblock(path->p_ext)); } else ext_debug(inode, " []"); } ext_debug(inode, "\n"); } static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) { int depth = ext_depth(inode); struct ext4_extent_header *eh; struct ext4_extent *ex; int i; if (!path) return; eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); ext_debug(inode, "Displaying leaf extents\n"); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); } ext_debug(inode, "\n"); } static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, ext4_fsblk_t newblock, int level) { int depth = ext_depth(inode); struct ext4_extent *ex; if (depth != level) { struct ext4_extent_idx *idx; idx = path[level].p_idx; while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) { ext_debug(inode, "%d: move %d:%llu in new index %llu\n", level, le32_to_cpu(idx->ei_block), ext4_idx_pblock(idx), newblock); idx++; } return; } ex = path[depth].p_ext; while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) { ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), newblock); ex++; } } #else #define ext4_ext_show_path(inode, path) #define ext4_ext_show_leaf(inode, path) #define ext4_ext_show_move(inode, path, newblock, level) #endif void ext4_ext_drop_refs(struct ext4_ext_path *path) { int depth, i; if (!path) return; depth = path->p_depth; for (i = 0; i <= depth; i++, path++) { brelse(path->p_bh); path->p_bh = NULL; } } /* * ext4_ext_binsearch_idx: * binary search for the closest index of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent_idx *r, *l, *m; ext_debug(inode, "binsearch for %u(idx): ", block); l = EXT_FIRST_INDEX(eh) + 1; r = EXT_LAST_INDEX(eh); while (l <= r) { m = l + (r - l) / 2; if (block < le32_to_cpu(m->ei_block)) r = m - 1; else l = m + 1; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), r, le32_to_cpu(r->ei_block)); } path->p_idx = l - 1; ext_debug(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH { struct ext4_extent_idx *chix, *ix; int k; chix = ix = EXT_FIRST_INDEX(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) { if (k != 0 && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) { printk(KERN_DEBUG "k=%d, ix=0x%p, " "first=0x%p\n", k, ix, EXT_FIRST_INDEX(eh)); printk(KERN_DEBUG "%u <= %u\n", le32_to_cpu(ix->ei_block), le32_to_cpu(ix[-1].ei_block)); } BUG_ON(k && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)); if (block < le32_to_cpu(ix->ei_block)) break; chix = ix; } BUG_ON(chix != path->p_idx); } #endif } /* * ext4_ext_binsearch: * binary search for closest extent of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent *r, *l, *m; if (eh->eh_entries == 0) { /* * this leaf is empty: * we get such a leaf in split/add case */ return; } ext_debug(inode, "binsearch for %u: ", block); l = EXT_FIRST_EXTENT(eh) + 1; r = EXT_LAST_EXTENT(eh); while (l <= r) { m = l + (r - l) / 2; if (block < le32_to_cpu(m->ee_block)) r = m - 1; else l = m + 1; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), r, le32_to_cpu(r->ee_block)); } path->p_ext = l - 1; ext_debug(inode, " -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_pblock(path->p_ext), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH { struct ext4_extent *chex, *ex; int k; chex = ex = EXT_FIRST_EXTENT(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) { BUG_ON(k && le32_to_cpu(ex->ee_block) <= le32_to_cpu(ex[-1].ee_block)); if (block < le32_to_cpu(ex->ee_block)) break; chex = ex; } BUG_ON(chex != path->p_ext); } #endif } void ext4_ext_tree_init(handle_t *handle, struct inode *inode) { struct ext4_extent_header *eh; eh = ext_inode_hdr(inode); eh->eh_depth = 0; eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); eh->eh_generation = 0; ext4_mark_inode_dirty(handle, inode); } struct ext4_ext_path * ext4_find_extent(struct inode *inode, ext4_lblk_t block, struct ext4_ext_path **orig_path, int flags) { struct ext4_extent_header *eh; struct buffer_head *bh; struct ext4_ext_path *path = orig_path ? *orig_path : NULL; short int depth, i, ppos = 0; int ret; gfp_t gfp_flags = GFP_NOFS; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; eh = ext_inode_hdr(inode); depth = ext_depth(inode); if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) { EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d", depth); ret = -EFSCORRUPTED; goto err; } if (path) { ext4_ext_drop_refs(path); if (depth > path[0].p_maxdepth) { kfree(path); *orig_path = path = NULL; } } if (!path) { /* account possible depth increase */ path = kcalloc(depth + 2, sizeof(struct ext4_ext_path), gfp_flags); if (unlikely(!path)) return ERR_PTR(-ENOMEM); path[0].p_maxdepth = depth + 1; } path[0].p_hdr = eh; path[0].p_bh = NULL; i = depth; if (!(flags & EXT4_EX_NOCACHE) && depth == 0) ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { ext_debug(inode, "depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_ext_binsearch_idx(inode, path + ppos, block); path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx); path[ppos].p_depth = i; path[ppos].p_ext = NULL; bh = read_extent_tree_block(inode, path[ppos].p_idx, --i, flags); if (IS_ERR(bh)) { ret = PTR_ERR(bh); goto err; } eh = ext_block_hdr(bh); ppos++; path[ppos].p_bh = bh; path[ppos].p_hdr = eh; } path[ppos].p_depth = i; path[ppos].p_ext = NULL; path[ppos].p_idx = NULL; /* find extent */ ext4_ext_binsearch(inode, path + ppos, block); /* if not an empty leaf */ if (path[ppos].p_ext) path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext); ext4_ext_show_path(inode, path); return path; err: ext4_ext_drop_refs(path); kfree(path); if (orig_path) *orig_path = NULL; return ERR_PTR(ret); } /* * ext4_ext_insert_index: * insert new index [@logical;@ptr] into the block at @curp; * check where to insert: before @curp or after @curp */ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, struct ext4_ext_path *curp, int logical, ext4_fsblk_t ptr) { struct ext4_extent_idx *ix; int len, err; err = ext4_ext_get_access(handle, inode, curp); if (err) return err; if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) { EXT4_ERROR_INODE(inode, "logical %d == ei_block %d!", logical, le32_to_cpu(curp->p_idx->ei_block)); return -EFSCORRUPTED; } if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries) >= le16_to_cpu(curp->p_hdr->eh_max))) { EXT4_ERROR_INODE(inode, "eh_entries %d >= eh_max %d!", le16_to_cpu(curp->p_hdr->eh_entries), le16_to_cpu(curp->p_hdr->eh_max)); return -EFSCORRUPTED; } if (logical > le32_to_cpu(curp->p_idx->ei_block)) { /* insert after */ ext_debug(inode, "insert new index %d after: %llu\n", logical, ptr); ix = curp->p_idx + 1; } else { /* insert before */ ext_debug(inode, "insert new index %d before: %llu\n", logical, ptr); ix = curp->p_idx; } len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { ext_debug(inode, "insert new index %d: " "move %d indices from 0x%p to 0x%p\n", logical, len, ix, ix + 1); memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); return -EFSCORRUPTED; } ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!"); return -EFSCORRUPTED; } err = ext4_ext_dirty(handle, inode, curp); ext4_std_error(inode->i_sb, err); return err; } /* * ext4_ext_split: * inserts new subtree into the path, using free index entry * at depth @at: * - allocates all needed blocks (new leaf and all intermediate index blocks) * - makes decision where to split * - moves remaining extents and index entries (right to the split point) * into the newly allocated blocks * - initializes subtree */ static int ext4_ext_split(handle_t *handle, struct inode *inode, unsigned int flags, struct ext4_ext_path *path, struct ext4_extent *newext, int at) { struct buffer_head *bh = NULL; int depth = ext_depth(inode); struct ext4_extent_header *neh; struct ext4_extent_idx *fidx; int i = at, k, m, a; ext4_fsblk_t newblock, oldblock; __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ gfp_t gfp_flags = GFP_NOFS; int err = 0; size_t ext_size = 0; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ /* if current leaf will be split, then we should use * border from split point */ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!"); return -EFSCORRUPTED; } if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { border = path[depth].p_ext[1].ee_block; ext_debug(inode, "leaf will be split." " next leaf starts at %d\n", le32_to_cpu(border)); } else { border = newext->ee_block; ext_debug(inode, "leaf will be added." " next leaf starts at %d\n", le32_to_cpu(border)); } /* * If error occurs, then we break processing * and mark filesystem read-only. index won't * be inserted and tree will be in consistent * state. Next mount will repair buffers too. */ /* * Get array to track all allocated blocks. * We need this to handle errors and free blocks * upon them. */ ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), gfp_flags); if (!ablocks) return -ENOMEM; /* allocate all needed blocks */ ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at); for (a = 0; a < depth - at; a++) { newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err, flags); if (newblock == 0) goto cleanup; ablocks[a] = newblock; } /* initialize new leaf */ newblock = ablocks[--a]; if (unlikely(newblock == 0)) { EXT4_ERROR_INODE(inode, "newblock == 0!"); err = -EFSCORRUPTED; goto cleanup; } bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, bh); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = 0; neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; neh->eh_generation = 0; /* move remainder of path[depth] to the new leaf */ if (unlikely(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max)) { EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!", path[depth].p_hdr->eh_entries, path[depth].p_hdr->eh_max); err = -EFSCORRUPTED; goto cleanup; } /* start copy from next extent */ m = EXT_MAX_EXTENT(path[depth].p_hdr) - path[depth].p_ext++; ext4_ext_show_move(inode, path, newblock, depth); if (m) { struct ext4_extent *ex; ex = EXT_FIRST_EXTENT(neh); memmove(ex, path[depth].p_ext, sizeof(struct ext4_extent) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old leaf */ if (m) { err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto cleanup; le16_add_cpu(&path[depth].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto cleanup; } /* create intermediate indexes */ k = depth - at - 1; if (unlikely(k < 0)) { EXT4_ERROR_INODE(inode, "k %d < 0!", k); err = -EFSCORRUPTED; goto cleanup; } if (k) ext_debug(inode, "create %d intermediate indices\n", k); /* insert new index into current index block */ /* current depth stored in i var */ i = depth - 1; while (k--) { oldblock = newblock; newblock = ablocks[--a]; bh = sb_getblk(inode->i_sb, newblock); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, bh); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = cpu_to_le16(1); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); neh->eh_generation = 0; fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n", i, newblock, le32_to_cpu(border), oldblock); /* move remainder of path[i] to the new index block */ if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) != EXT_LAST_INDEX(path[i].p_hdr))) { EXT4_ERROR_INODE(inode, "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!", le32_to_cpu(path[i].p_ext->ee_block)); err = -EFSCORRUPTED; goto cleanup; } /* start copy indexes */ m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++; ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx, EXT_MAX_INDEX(path[i].p_hdr)); ext4_ext_show_move(inode, path, newblock, i); if (m) { memmove(++fidx, path[i].p_idx, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old index */ if (m) { err = ext4_ext_get_access(handle, inode, path + i); if (err) goto cleanup; le16_add_cpu(&path[i].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + i); if (err) goto cleanup; } i--; } /* insert new index */ err = ext4_ext_insert_index(handle, inode, path + at, le32_to_cpu(border), newblock); cleanup: if (bh) { if (buffer_locked(bh)) unlock_buffer(bh); brelse(bh); } if (err) { /* free all allocated blocks in error case */ for (i = 0; i < depth; i++) { if (!ablocks[i]) continue; ext4_free_blocks(handle, inode, NULL, ablocks[i], 1, EXT4_FREE_BLOCKS_METADATA); } } kfree(ablocks); return err; } /* * ext4_ext_grow_indepth: * implements tree growing procedure: * - allocates new block * - moves top-level data (index block or leaf) into the new block * - initializes new top-level, creating index that points to the * just created block */ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, unsigned int flags) { struct ext4_extent_header *neh; struct buffer_head *bh; ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode))); if (goal > le32_to_cpu(es->s_first_data_block)) { flags |= EXT4_MB_HINT_TRY_GOAL; goal--; } else goal = ext4_inode_to_goal_block(inode); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, &err); if (newblock == 0) return err; bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) return -ENOMEM; lock_buffer(bh); err = ext4_journal_get_create_access(handle, bh); if (err) { unlock_buffer(bh); goto out; } ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); /* zero out unused area in the extent block */ memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); /* old root could have indexes or leaves * so calculate e_max right way */ if (ext_depth(inode)) neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); else neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto out; /* Update top-level index: num,max,pointer */ neh = ext_inode_hdr(inode); neh->eh_entries = cpu_to_le16(1); ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock); if (neh->eh_depth == 0) { /* Root extent block becomes index block */ neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0)); EXT_FIRST_INDEX(neh)->ei_block = EXT_FIRST_EXTENT(neh)->ee_block; } ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n", le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); le16_add_cpu(&neh->eh_depth, 1); err = ext4_mark_inode_dirty(handle, inode); out: brelse(bh); return err; } /* * ext4_ext_create_new_leaf: * finds empty index and adds new leaf. * if no free index is found, then it requests in-depth growing. */ static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, unsigned int mb_flags, unsigned int gb_flags, struct ext4_ext_path **ppath, struct ext4_extent *newext) { struct ext4_ext_path *path = *ppath; struct ext4_ext_path *curp; int depth, i, err = 0; repeat: i = depth = ext_depth(inode); /* walk up to the tree and look for free index entry */ curp = path + depth; while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) { i--; curp--; } /* we use already allocated block for index block, * so subsequent data blocks should be contiguous */ if (EXT_HAS_FREE_INDEX(curp)) { /* if we found index with free entry, then use that * entry: create all needed subtree and add new leaf */ err = ext4_ext_split(handle, inode, mb_flags, path, newext, i); if (err) goto out; /* refill path */ path = ext4_find_extent(inode, (ext4_lblk_t)le32_to_cpu(newext->ee_block), ppath, gb_flags); if (IS_ERR(path)) err = PTR_ERR(path); } else { /* tree is full, time to grow in depth */ err = ext4_ext_grow_indepth(handle, inode, mb_flags); if (err) goto out; /* refill path */ path = ext4_find_extent(inode, (ext4_lblk_t)le32_to_cpu(newext->ee_block), ppath, gb_flags); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; } /* * only first (depth 0 -> 1) produces free space; * in all other cases we have to split the grown tree */ depth = ext_depth(inode); if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) { /* now we need to split */ goto repeat; } } out: return err; } /* * search the closest allocated block to the left for *logical * and returns it at @logical + it's physical address at @phys * if *logical is the smallest allocated block, the function * returns 0 at @phys * return value contains 0 (success) or error code */ static int ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys) { struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth, ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!", *logical, le32_to_cpu(ex->ee_block)); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!", ix != NULL ? le32_to_cpu(ix->ei_block) : 0, EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ? le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0, depth); return -EFSCORRUPTED; } } return 0; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } *logical = le32_to_cpu(ex->ee_block) + ee_len - 1; *phys = ext4_ext_pblock(ex) + ee_len - 1; return 0; } /* * Search the closest allocated block to the right for *logical * and returns it at @logical + it's physical address at @phys. * If not exists, return 0 and @phys is set to 0. We will return * 1 which means we found an allocated block and ret_ex is valid. * Or return a (< 0) error code. */ static int ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys, struct ext4_extent *ret_ex) { struct buffer_head *bh = NULL; struct ext4_extent_header *eh; struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth; /* Note, NOT eh_depth; depth from top of tree */ int ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "first_extent(path[%d].p_hdr) != ex", depth); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix != EXT_FIRST_INDEX *logical %d!", *logical); return -EFSCORRUPTED; } } goto found_extent; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) { /* next allocated block in this leaf */ ex++; goto found_extent; } /* go up and search for index to the right */ while (--depth >= 0) { ix = path[depth].p_idx; if (ix != EXT_LAST_INDEX(path[depth].p_hdr)) goto got_index; } /* we've gone up to the root and found no index to the right */ return 0; got_index: /* we've found index to the right, let's * follow it and find the closest allocated * block to the right */ ix++; while (++depth < path->p_depth) { /* subtract from p_depth to get proper eh_depth */ bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ix = EXT_FIRST_INDEX(eh); put_bh(bh); } bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ex = EXT_FIRST_EXTENT(eh); found_extent: *logical = le32_to_cpu(ex->ee_block); *phys = ext4_ext_pblock(ex); if (ret_ex) *ret_ex = *ex; if (bh) put_bh(bh); return 1; } /* * ext4_ext_next_allocated_block: * returns allocated block in subsequent extent or EXT_MAX_BLOCKS. * NOTE: it considers block number from index entry as * allocated block. Thus, index entries have to be consistent * with leaves. */ ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; if (depth == 0 && path->p_ext == NULL) return EXT_MAX_BLOCKS; while (depth >= 0) { struct ext4_ext_path *p = &path[depth]; if (depth == path->p_depth) { /* leaf */ if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr)) return le32_to_cpu(p->p_ext[1].ee_block); } else { /* index */ if (p->p_idx != EXT_LAST_INDEX(p->p_hdr)) return le32_to_cpu(p->p_idx[1].ei_block); } depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_next_leaf_block: * returns first allocated block from next leaf or EXT_MAX_BLOCKS */ static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; /* zero-tree has no leaf blocks at all */ if (depth == 0) return EXT_MAX_BLOCKS; /* go to index block */ depth--; while (depth >= 0) { if (path[depth].p_idx != EXT_LAST_INDEX(path[depth].p_hdr)) return (ext4_lblk_t) le32_to_cpu(path[depth].p_idx[1].ei_block); depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_correct_indexes: * if leaf gets modified and modified extent is first in the leaf, * then we have to correct all indexes above. * TODO: do we need to correct tree in all cases? */ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { struct ext4_extent_header *eh; int depth = ext_depth(inode); struct ext4_extent *ex; __le32 border; int k, err = 0; eh = path[depth].p_hdr; ex = path[depth].p_ext; if (unlikely(ex == NULL || eh == NULL)) { EXT4_ERROR_INODE(inode, "ex %p == NULL or eh %p == NULL", ex, eh); return -EFSCORRUPTED; } if (depth == 0) { /* there is no tree at all */ return 0; } if (ex != EXT_FIRST_EXTENT(eh)) { /* we correct tree if first leaf got modified only */ return 0; } /* * TODO: we need correction if border is smaller than current one */ k = depth - 1; border = path[depth].p_ext->ee_block; err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) return err; while (k--) { /* change all left-side indexes */ if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr)) break; err = ext4_ext_get_access(handle, inode, path + k); if (err) break; path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) break; } return err; } static int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { unsigned short ext1_ee_len, ext2_ee_len; if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2)) return 0; ext1_ee_len = ext4_ext_get_actual_len(ex1); ext2_ee_len = ext4_ext_get_actual_len(ex2); if (le32_to_cpu(ex1->ee_block) + ext1_ee_len != le32_to_cpu(ex2->ee_block)) return 0; if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN) return 0; if (ext4_ext_is_unwritten(ex1) && ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN) return 0; #ifdef AGGRESSIVE_TEST if (ext1_ee_len >= 4) return 0; #endif if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_ext_pblock(ex2)) return 1; return 0; } /* * This function tries to merge the "ex" extent to the next extent in the tree. * It always tries to merge towards right. If you want to merge towards * left, pass "ex - 1" as argument instead of "ex". * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns * 1 if they got merged. */ static int ext4_ext_try_to_merge_right(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth, len; int merge_done = 0, unwritten; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; while (ex < EXT_LAST_EXTENT(eh)) { if (!ext4_can_extents_be_merged(inode, ex, ex + 1)) break; /* merge with next extent! */ unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(ex + 1)); if (unwritten) ext4_ext_mark_unwritten(ex); if (ex + 1 < EXT_LAST_EXTENT(eh)) { len = (EXT_LAST_EXTENT(eh) - ex - 1) * sizeof(struct ext4_extent); memmove(ex + 1, ex + 2, len); } le16_add_cpu(&eh->eh_entries, -1); merge_done = 1; WARN_ON(eh->eh_entries == 0); if (!eh->eh_entries) EXT4_ERROR_INODE(inode, "eh->eh_entries = 0!"); } return merge_done; } /* * This function does a very simple check to see if we can collapse * an extent tree with a single extent tree leaf block into the inode. */ static void ext4_ext_try_to_merge_up(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { size_t s; unsigned max_root = ext4_ext_space_root(inode, 0); ext4_fsblk_t blk; if ((path[0].p_depth != 1) || (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) || (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root)) return; /* * We need to modify the block allocation bitmap and the block * group descriptor to release the extent tree block. If we * can't get the journal credits, give up. */ if (ext4_journal_extend(handle, 2, ext4_free_metadata_revoke_credits(inode->i_sb, 1))) return; /* * Copy the extent data up to the inode */ blk = ext4_idx_pblock(path[0].p_idx); s = le16_to_cpu(path[1].p_hdr->eh_entries) * sizeof(struct ext4_extent_idx); s += sizeof(struct ext4_extent_header); path[1].p_maxdepth = path[0].p_maxdepth; memcpy(path[0].p_hdr, path[1].p_hdr, s); path[0].p_depth = 0; path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) + (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr)); path[0].p_hdr->eh_max = cpu_to_le16(max_root); brelse(path[1].p_bh); ext4_free_blocks(handle, inode, NULL, blk, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } /* * This function tries to merge the @ex extent to neighbours in the tree, then * tries to collapse the extent tree into the inode. */ static void ext4_ext_try_to_merge(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; if (ex > EXT_FIRST_EXTENT(eh)) merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1); if (!merge_done) (void) ext4_ext_try_to_merge_right(inode, path, ex); ext4_ext_try_to_merge_up(handle, inode, path); } /* * check if a portion of the "newext" extent overlaps with an * existing extent. * * If there is an overlap discovered, it updates the length of the newext * such that there will be no overlap, and then returns 1. * If there is no overlap found, it returns 0. */ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, struct inode *inode, struct ext4_extent *newext, struct ext4_ext_path *path) { ext4_lblk_t b1, b2; unsigned int depth, len1; unsigned int ret = 0; b1 = le32_to_cpu(newext->ee_block); len1 = ext4_ext_get_actual_len(newext); depth = ext_depth(inode); if (!path[depth].p_ext) goto out; b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block)); /* * get the next allocated block if the extent in the path * is before the requested block(s) */ if (b2 < b1) { b2 = ext4_ext_next_allocated_block(path); if (b2 == EXT_MAX_BLOCKS) goto out; b2 = EXT4_LBLK_CMASK(sbi, b2); } /* check for wrap through zero on extent logical start block*/ if (b1 + len1 < b1) { len1 = EXT_MAX_BLOCKS - b1; newext->ee_len = cpu_to_le16(len1); ret = 1; } /* check for overlap */ if (b1 + len1 > b2) { newext->ee_len = cpu_to_le16(b2 - b1); ret = 1; } out: return ret; } /* * ext4_ext_insert_extent: * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, struct ext4_extent *newext, int gb_flags) { struct ext4_ext_path *path = *ppath; struct ext4_extent_header *eh; struct ext4_extent *ex, *fex; struct ext4_extent *nearex; /* nearest extent */ struct ext4_ext_path *npath = NULL; int depth, len, err; ext4_lblk_t next; int mb_flags = 0, unwritten; if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) mb_flags |= EXT4_MB_DELALLOC_RESERVED; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); return -EFSCORRUPTED; } depth = ext_depth(inode); ex = path[depth].p_ext; eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EFSCORRUPTED; } /* try to insert block into found extent and return */ if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) { /* * Try to see whether we should rather test the extent on * right from ex, or from the left of ex. This is because * ext4_find_extent() can return either extent on the * left, or on the right from the searched position. This * will make merging more effective. */ if (ex < EXT_LAST_EXTENT(eh) && (le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex) < le32_to_cpu(newext->ee_block))) { ex += 1; goto prepend; } else if ((ex > EXT_FIRST_EXTENT(eh)) && (le32_to_cpu(newext->ee_block) + ext4_ext_get_actual_len(newext) < le32_to_cpu(ex->ee_block))) ex -= 1; /* Try to append newex to the ex */ if (ext4_can_extents_be_merged(inode, ex, newext)) { ext_debug(inode, "append [%d]%d block to %u:[%d]%d" "(from %llu)\n", ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; } prepend: /* Try to prepend newex to the ex */ if (ext4_can_extents_be_merged(inode, newext, ex)) { ext_debug(inode, "prepend %u[%d]%d block to %u:[%d]%d" "(from %llu)\n", le32_to_cpu(newext->ee_block), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; unwritten = ext4_ext_is_unwritten(ex); ex->ee_block = newext->ee_block; ext4_ext_store_pblock(ex, ext4_ext_pblock(newext)); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; } } depth = ext_depth(inode); eh = path[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) goto has_space; /* probably next leaf has space for us? */ fex = EXT_LAST_EXTENT(eh); next = EXT_MAX_BLOCKS; if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)) next = ext4_ext_next_leaf_block(path); if (next != EXT_MAX_BLOCKS) { ext_debug(inode, "next leaf block - %u\n", next); BUG_ON(npath != NULL); npath = ext4_find_extent(inode, next, NULL, gb_flags); if (IS_ERR(npath)) return PTR_ERR(npath); BUG_ON(npath->p_depth != path->p_depth); eh = npath[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) { ext_debug(inode, "next leaf isn't full(%d)\n", le16_to_cpu(eh->eh_entries)); path = npath; goto has_space; } ext_debug(inode, "next leaf has no free space(%d,%d)\n", le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); } /* * There is no free space in the found leaf. * We're gonna add a new leaf in the tree. */ if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) mb_flags |= EXT4_MB_USE_RESERVED; err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags, ppath, newext); if (err) goto cleanup; depth = ext_depth(inode); eh = path[depth].p_hdr; has_space: nearex = path[depth].p_ext; err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto cleanup; if (!nearex) { /* there is no extent in this leaf, create first one */ ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext)); nearex = EXT_FIRST_EXTENT(eh); } else { if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { /* Insert after */ ext_debug(inode, "insert %u:%llu:[%d]%d before: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); nearex++; } else { /* Insert before */ BUG_ON(newext->ee_block == nearex->ee_block); ext_debug(inode, "insert %u:%llu:[%d]%d after: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); } len = EXT_LAST_EXTENT(eh) - nearex + 1; if (len > 0) { ext_debug(inode, "insert %u:%llu:[%d]%d: " "move %d extents from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), len, nearex, nearex + 1); memmove(nearex + 1, nearex, len * sizeof(struct ext4_extent)); } } le16_add_cpu(&eh->eh_entries, 1); path[depth].p_ext = nearex; nearex->ee_block = newext->ee_block; ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext)); nearex->ee_len = newext->ee_len; merge: /* try to merge extents */ if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(handle, inode, path, nearex); /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); if (err) goto cleanup; err = ext4_ext_dirty(handle, inode, path + path->p_depth); cleanup: ext4_ext_drop_refs(npath); kfree(npath); return err; } static int ext4_fill_es_cache_info(struct inode *inode, ext4_lblk_t block, ext4_lblk_t num, struct fiemap_extent_info *fieinfo) { ext4_lblk_t next, end = block + num - 1; struct extent_status es; unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; unsigned int flags; int err; while (block <= end) { next = 0; flags = 0; if (!ext4_es_lookup_extent(inode, block, &next, &es)) break; if (ext4_es_is_unwritten(&es)) flags |= FIEMAP_EXTENT_UNWRITTEN; if (ext4_es_is_delayed(&es)) flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); if (ext4_es_is_hole(&es)) flags |= EXT4_FIEMAP_EXTENT_HOLE; if (next == 0) flags |= FIEMAP_EXTENT_LAST; if (flags & (FIEMAP_EXTENT_DELALLOC| EXT4_FIEMAP_EXTENT_HOLE)) es.es_pblk = 0; else es.es_pblk = ext4_es_pblock(&es); err = fiemap_fill_next_extent(fieinfo, (__u64)es.es_lblk << blksize_bits, (__u64)es.es_pblk << blksize_bits, (__u64)es.es_len << blksize_bits, flags); if (next == 0) break; block = next; if (err < 0) return err; if (err == 1) return 0; } return 0; } /* * ext4_ext_determine_hole - determine hole around given block * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole * * Determine hole length (and start if easily possible) around given logical * block. We don't try too hard to find the beginning of the hole but @path * actually points to extent before @lblk, we provide it. * * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; ext4_lblk_t len; ex = path[depth].p_ext; if (ex == NULL) { /* there is no extent yet, so gap is [0;-] */ *lblk = 0; len = EXT_MAX_BLOCKS; } else if (*lblk < le32_to_cpu(ex->ee_block)) { len = le32_to_cpu(ex->ee_block) - *lblk; } else if (*lblk >= le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)) { ext4_lblk_t next; *lblk = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); next = ext4_ext_next_allocated_block(path); BUG_ON(next == *lblk); len = next - *lblk; } else { BUG(); } return len; } /* * ext4_ext_put_gap_in_cache: * calculate boundaries of the gap that the requested block fits into * and cache this gap */ static void ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, ext4_lblk_t hole_len) { struct extent_status es; ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, hole_start + hole_len - 1, &es); if (es.es_len) { /* There's delayed extent containing lblock? */ if (es.es_lblk <= hole_start) return; hole_len = min(es.es_lblk - hole_start, hole_len); } ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); ext4_es_insert_extent(inode, hole_start, hole_len, ~0, EXTENT_STATUS_HOLE); } /* * ext4_ext_rm_idx: * removes index from the index block. */ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, int depth) { int err; ext4_fsblk_t leaf; /* free index block */ depth--; path = path + depth; leaf = ext4_idx_pblock(path->p_idx); if (unlikely(path->p_hdr->eh_entries == 0)) { EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0"); return -EFSCORRUPTED; } err = ext4_ext_get_access(handle, inode, path); if (err) return err; if (path->p_idx != EXT_LAST_INDEX(path->p_hdr)) { int len = EXT_LAST_INDEX(path->p_hdr) - path->p_idx; len *= sizeof(struct ext4_extent_idx); memmove(path->p_idx, path->p_idx + 1, len); } le16_add_cpu(&path->p_hdr->eh_entries, -1); err = ext4_ext_dirty(handle, inode, path); if (err) return err; ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf); trace_ext4_ext_rm_idx(inode, leaf); ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); while (--depth >= 0) { if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr)) break; path--; err = ext4_ext_get_access(handle, inode, path); if (err) break; path->p_idx->ei_block = (path+1)->p_idx->ei_block; err = ext4_ext_dirty(handle, inode, path); if (err) break; } return err; } /* * ext4_ext_calc_credits_for_single_extent: * This routine returns max. credits that needed to insert an extent * to the extent tree. * When pass the actual path, the caller should calculate credits * under i_data_sem. */ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, struct ext4_ext_path *path) { if (path) { int depth = ext_depth(inode); int ret = 0; /* probably there is space in leaf? */ if (le16_to_cpu(path[depth].p_hdr->eh_entries) < le16_to_cpu(path[depth].p_hdr->eh_max)) { /* * There are some space in the leaf tree, no * need to account for leaf block credit * * bitmaps and block group descriptor blocks * and other metadata blocks still need to be * accounted. */ /* 1 bitmap, 1 block group descriptor */ ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); return ret; } } return ext4_chunk_trans_blocks(inode, nrblocks); } /* * How many index/leaf blocks need to change/allocate to add @extents extents? * * If we add a single extent, then in the worse case, each tree level * index/leaf need to be changed in case of the tree split. * * If more extents are inserted, they could cause the whole tree split more * than once, but this is really rare. */ int ext4_ext_index_trans_blocks(struct inode *inode, int extents) { int index; int depth; /* If we are converting the inline data, only one is needed here. */ if (ext4_has_inline_data(inode)) return 1; depth = ext_depth(inode); if (extents <= 1) index = depth * 2; else index = depth * 3; return index; } static inline int get_default_free_blocks_flags(struct inode *inode) { if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; else if (ext4_should_journal_data(inode)) return EXT4_FREE_BLOCKS_FORGET; return 0; } /* * ext4_rereserve_cluster - increment the reserved cluster count when * freeing a cluster with a pending reservation * * @inode - file containing the cluster * @lblk - logical block in cluster to be reserved * * Increments the reserved cluster count and adjusts quota in a bigalloc * file system when freeing a partial cluster containing at least one * delayed and unwritten block. A partial cluster meeting that * requirement will have a pending reservation. If so, the * RERESERVE_CLUSTER flag is used when calling ext4_free_blocks() to * defer reserved and allocated space accounting to a subsequent call * to this function. */ static void ext4_rereserve_cluster(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); dquot_reclaim_block(inode, EXT4_C2B(sbi, 1)); spin_lock(&ei->i_block_reservation_lock); ei->i_reserved_data_blocks++; percpu_counter_add(&sbi->s_dirtyclusters_counter, 1); spin_unlock(&ei->i_block_reservation_lock); percpu_counter_add(&sbi->s_freeclusters_counter, 1); ext4_remove_pending(inode, lblk); } static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_extent *ex, struct partial_cluster *partial, ext4_lblk_t from, ext4_lblk_t to) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned short ee_len = ext4_ext_get_actual_len(ex); ext4_fsblk_t last_pblk, pblk; ext4_lblk_t num; int flags; /* only extent tail removal is allowed */ if (from < le32_to_cpu(ex->ee_block) || to != le32_to_cpu(ex->ee_block) + ee_len - 1) { ext4_error(sbi->s_sb, "strange request: removal(2) %u-%u from %u:%u", from, to, le32_to_cpu(ex->ee_block), ee_len); return 0; } #ifdef EXTENTS_STATS spin_lock(&sbi->s_ext_stats_lock); sbi->s_ext_blocks += ee_len; sbi->s_ext_extents++; if (ee_len < sbi->s_ext_min) sbi->s_ext_min = ee_len; if (ee_len > sbi->s_ext_max) sbi->s_ext_max = ee_len; if (ext_depth(inode) > sbi->s_depth_max) sbi->s_depth_max = ext_depth(inode); spin_unlock(&sbi->s_ext_stats_lock); #endif trace_ext4_remove_blocks(inode, ex, from, to, partial); /* * if we have a partial cluster, and it's different from the * cluster of the last block in the extent, we free it */ last_pblk = ext4_ext_pblock(ex) + ee_len - 1; if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, last_pblk)) { if (partial->state == tofree) { flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } num = le32_to_cpu(ex->ee_block) + ee_len - from; pblk = ext4_ext_pblock(ex) + ee_len - num; /* * We free the partial cluster at the end of the extent (if any), * unless the cluster is used by another extent (partial_cluster * state is nofree). If a partial cluster exists here, it must be * shared with the last block in the extent. */ flags = get_default_free_blocks_flags(inode); /* partial, left end cluster aligned, right end unaligned */ if ((EXT4_LBLK_COFF(sbi, to) != sbi->s_cluster_ratio - 1) && (EXT4_LBLK_CMASK(sbi, to) >= from) && (partial->state != nofree)) { if (ext4_is_pending(inode, to)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_PBLK_CMASK(sbi, last_pblk), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, to); partial->state = initial; flags = get_default_free_blocks_flags(inode); } flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER; /* * For bigalloc file systems, we never free a partial cluster * at the beginning of the extent. Instead, we check to see if we * need to free it on a subsequent call to ext4_remove_blocks, * or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space. */ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; ext4_free_blocks(handle, inode, NULL, pblk, num, flags); /* reset the partial cluster if we've freed past it */ if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, pblk)) partial->state = initial; /* * If we've freed the entire extent but the beginning is not left * cluster aligned and is not marked as ineligible for freeing we * record the partial cluster at the beginning of the extent. It * wasn't freed by the preceding ext4_free_blocks() call, and we * need to look farther to the left to determine if it's to be freed * (not shared with another extent). Else, reset the partial * cluster - we're either done freeing or the beginning of the * extent is left cluster aligned. */ if (EXT4_LBLK_COFF(sbi, from) && num == ee_len) { if (partial->state == initial) { partial->pclu = EXT4_B2C(sbi, pblk); partial->lblk = from; partial->state = tofree; } } else { partial->state = initial; } return 0; } /* * ext4_ext_rm_leaf() Removes the extents associated with the * blocks appearing between "start" and "end". Both "start" * and "end" must appear in the same extent or EIO is returned. * * @handle: The journal handle * @inode: The files inode * @path: The path to the leaf * @partial_cluster: The cluster which we'll have to free if all extents * has been released from it. However, if this value is * negative, it's a cluster just to the right of the * punched region and it must not be freed. * @start: The first block to remove * @end: The last block to remove */ static int ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct partial_cluster *partial, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int err = 0, correct_index = 0; int depth = ext_depth(inode), credits, revoke_credits; struct ext4_extent_header *eh; ext4_lblk_t a, b; unsigned num; ext4_lblk_t ex_ee_block; unsigned short ex_ee_len; unsigned unwritten = 0; struct ext4_extent *ex; ext4_fsblk_t pblk; /* the header must be checked already in ext4_ext_remove_space() */ ext_debug(inode, "truncate since %u in leaf to %u\n", start, end); if (!path[depth].p_hdr) path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EFSCORRUPTED; } /* find where to start removing */ ex = path[depth].p_ext; if (!ex) ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_rm_leaf(inode, start, ex, partial); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { if (ext4_ext_is_unwritten(ex)) unwritten = 1; else unwritten = 0; ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block, unwritten, ex_ee_len); path[depth].p_ext = ex; a = ex_ee_block > start ? ex_ee_block : start; b = ex_ee_block+ex_ee_len - 1 < end ? ex_ee_block+ex_ee_len - 1 : end; ext_debug(inode, " border %u:%u\n", a, b); /* If this extent is beyond the end of the hole, skip it */ if (end < ex_ee_block) { /* * We're going to skip this extent and move to another, * so note that its first cluster is in use to avoid * freeing it when removing blocks. Eventually, the * right edge of the truncated/punched region will * be just to the left. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex); partial->pclu = EXT4_B2C(sbi, pblk); partial->state = nofree; } ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); continue; } else if (b != ex_ee_block + ex_ee_len - 1) { EXT4_ERROR_INODE(inode, "can not handle truncate %u:%u " "on extent %u:%u", start, end, ex_ee_block, ex_ee_block + ex_ee_len - 1); err = -EFSCORRUPTED; goto out; } else if (a != ex_ee_block) { /* remove tail of the extent */ num = a - ex_ee_block; } else { /* remove whole extent: excellent! */ num = 0; } /* * 3 for leaf, sb, and inode plus 2 (bmap and group * descriptor) for each block group; assume two block * groups plus ex_ee_len/blocks_per_block_group for * the worst case */ credits = 7 + 2*(ex_ee_len/EXT4_BLOCKS_PER_GROUP(inode->i_sb)); if (ex == EXT_FIRST_EXTENT(eh)) { correct_index = 1; credits += (ext_depth(inode)) + 1; } credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); /* * We may end up freeing some index blocks and data from the * punched range. Note that partial clusters are accounted for * by ext4_free_data_revoke_credits(). */ revoke_credits = ext4_free_metadata_revoke_credits(inode->i_sb, ext_depth(inode)) + ext4_free_data_revoke_credits(inode, b - a + 1); err = ext4_datasem_ensure_credits(handle, inode, credits, credits, revoke_credits); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; err = ext4_remove_blocks(handle, inode, ex, partial, a, b); if (err) goto out; if (num == 0) /* this extent is removed; mark slot entirely unused */ ext4_ext_store_pblock(ex, 0); ex->ee_len = cpu_to_le16(num); /* * Do not mark unwritten if all the blocks in the * extent have been removed. */ if (unwritten && num) ext4_ext_mark_unwritten(ex); /* * If the extent was completely released, * we need to remove it from the leaf */ if (num == 0) { if (end != EXT_MAX_BLOCKS - 1) { /* * For hole punching, we need to scoot all the * extents up when an extent is removed so that * we dont have blank extents in the middle */ memmove(ex, ex+1, (EXT_LAST_EXTENT(eh) - ex) * sizeof(struct ext4_extent)); /* Now get rid of the one at the end */ memset(EXT_LAST_EXTENT(eh), 0, sizeof(struct ext4_extent)); } le16_add_cpu(&eh->eh_entries, -1); } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num, ext4_ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); } if (correct_index && eh->eh_entries) err = ext4_ext_correct_indexes(handle, inode, path); /* * If there's a partial cluster and at least one extent remains in * the leaf, free the partial cluster if it isn't shared with the * current extent. If it is shared with the current extent * we reset the partial cluster because we've reached the start of the * truncated/punched region and we're done removing blocks. */ if (partial->state == tofree && ex >= EXT_FIRST_EXTENT(eh)) { pblk = ext4_ext_pblock(ex) + ex_ee_len - 1; if (partial->pclu != EXT4_B2C(sbi, pblk)) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } /* if this leaf is free, then we should * remove it from index block above */ if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL) err = ext4_ext_rm_idx(handle, inode, path, depth); out: return err; } /* * ext4_ext_more_to_rm: * returns 1 if current index has to be freed (even partial) */ static int ext4_ext_more_to_rm(struct ext4_ext_path *path) { BUG_ON(path->p_idx == NULL); if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr)) return 0; /* * if truncate on deeper level happened, it wasn't partial, * so we have to consider current index for truncation */ if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block) return 0; return 1; } int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int depth = ext_depth(inode); struct ext4_ext_path *path = NULL; struct partial_cluster partial; handle_t *handle; int i = 0, err = 0; partial.pclu = 0; partial.lblk = 0; partial.state = initial; ext_debug(inode, "truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE, depth + 1, ext4_free_metadata_revoke_credits(inode->i_sb, depth)); if (IS_ERR(handle)) return PTR_ERR(handle); again: trace_ext4_ext_remove_space(inode, start, end, depth); /* * Check if we are removing extents inside the extent tree. If that * is the case, we are going to punch a hole inside the extent tree * so we have to check whether we need to split the extent covering * the last block to remove so we can easily remove the part of it * in ext4_ext_rm_leaf(). */ if (end < EXT_MAX_BLOCKS - 1) { struct ext4_extent *ex; ext4_lblk_t ee_block, ex_end, lblk; ext4_fsblk_t pblk; /* find extent for or closest extent to this block */ path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE | EXT4_EX_NOFAIL); if (IS_ERR(path)) { ext4_journal_stop(handle); return PTR_ERR(path); } depth = ext_depth(inode); /* Leaf not may not exist only if inode has no blocks at all */ ex = path[depth].p_ext; if (!ex) { if (depth) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); err = -EFSCORRUPTED; } goto out; } ee_block = le32_to_cpu(ex->ee_block); ex_end = ee_block + ext4_ext_get_actual_len(ex) - 1; /* * See if the last block is inside the extent, if so split * the extent at 'end' block so we can easily remove the * tail of the first part of the split extent in * ext4_ext_rm_leaf(). */ if (end >= ee_block && end < ex_end) { /* * If we're going to split the extent, note that * the cluster containing the block after 'end' is * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } /* * Split the extent in two so that 'end' is the last * block in the first new extent. Also we should not * fail removing space due to ENOSPC so try to use * reserved block if that happens. */ err = ext4_force_split_extent_at(handle, inode, &path, end + 1, 1); if (err < 0) goto out; } else if (sbi->s_cluster_ratio > 1 && end >= ex_end && partial.state == initial) { /* * If we're punching, there's an extent to the right. * If the partial cluster hasn't been set, set it to * that extent's first cluster and its state to nofree * so it won't be freed should it contain blocks to be * removed. If it's already set (tofree/nofree), we're * retrying and keep the original partial cluster info * so a cluster marked tofree as a result of earlier * extent removal is not lost. */ lblk = ex_end + 1; err = ext4_ext_search_right(inode, path, &lblk, &pblk, NULL); if (err < 0) goto out; if (pblk) { partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } } } /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. */ depth = ext_depth(inode); if (path) { int k = i = depth; while (--k > 0) path[k].p_block = le16_to_cpu(path[k].p_hdr->eh_entries)+1; } else { path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS | __GFP_NOFAIL); if (path == NULL) { ext4_journal_stop(handle); return -ENOMEM; } path[0].p_maxdepth = path[0].p_depth = depth; path[0].p_hdr = ext_inode_hdr(inode); i = 0; if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) { err = -EFSCORRUPTED; goto out; } } err = 0; while (i >= 0 && err == 0) { if (i == depth) { /* this is leaf block */ err = ext4_ext_rm_leaf(handle, inode, path, &partial, start, end); /* root level has p_bh == NULL, brelse() eats this */ brelse(path[i].p_bh); path[i].p_bh = NULL; i--; continue; } /* this is index block */ if (!path[i].p_hdr) { ext_debug(inode, "initialize header\n"); path[i].p_hdr = ext_block_hdr(path[i].p_bh); } if (!path[i].p_idx) { /* this level hasn't been touched yet */ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1; ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n", path[i].p_hdr, le16_to_cpu(path[i].p_hdr->eh_entries)); } else { /* we were already here, see at next index */ path[i].p_idx--; } ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n", i, EXT_FIRST_INDEX(path[i].p_hdr), path[i].p_idx); if (ext4_ext_more_to_rm(path + i)) { struct buffer_head *bh; /* go to the next level */ ext_debug(inode, "move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); bh = read_extent_tree_block(inode, path[i].p_idx, depth - i - 1, EXT4_EX_NOCACHE); if (IS_ERR(bh)) { /* should we reset i_size? */ err = PTR_ERR(bh); break; } /* Yield here to deal with large extent trees. * Should be a no-op if we did IO above. */ cond_resched(); if (WARN_ON(i + 1 > depth)) { err = -EFSCORRUPTED; break; } path[i + 1].p_bh = bh; /* save actual number of indexes since this * number is changed at the next iteration */ path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries); i++; } else { /* we finished processing this index, go up */ if (path[i].p_hdr->eh_entries == 0 && i > 0) { /* index is empty, remove it; * handle must be already prepared by the * truncatei_leaf() */ err = ext4_ext_rm_idx(handle, inode, path, i); } /* root level has p_bh == NULL, brelse() eats this */ brelse(path[i].p_bh); path[i].p_bh = NULL; i--; ext_debug(inode, "return to level %d\n", i); } } trace_ext4_ext_remove_space_done(inode, start, end, depth, &partial, path->p_hdr->eh_entries); /* * if there's a partial cluster and we have removed the first extent * in the file, then we also free the partial cluster, if any */ if (partial.state == tofree && err == 0) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial.lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial.pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial.lblk); partial.state = initial; } /* TODO: flexible tree reduction should be here */ if (path->p_hdr->eh_entries == 0) { /* * truncate to zero freed all the tree, * so we need to correct eh_depth */ err = ext4_ext_get_access(handle, inode, path); if (err == 0) { ext_inode_hdr(inode)->eh_depth = 0; ext_inode_hdr(inode)->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); err = ext4_ext_dirty(handle, inode, path); } } out: ext4_ext_drop_refs(path); kfree(path); path = NULL; if (err == -EAGAIN) goto again; ext4_journal_stop(handle); return err; } /* * called at mount time */ void ext4_ext_init(struct super_block *sb) { /* * possible initialization would be here */ if (ext4_has_feature_extents(sb)) { #if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS) printk(KERN_INFO "EXT4-fs: file extents enabled" #ifdef AGGRESSIVE_TEST ", aggressive tests" #endif #ifdef CHECK_BINSEARCH ", check binsearch" #endif #ifdef EXTENTS_STATS ", stats" #endif "\n"); #endif #ifdef EXTENTS_STATS spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock); EXT4_SB(sb)->s_ext_min = 1 << 30; EXT4_SB(sb)->s_ext_max = 0; #endif } } /* * called at umount time */ void ext4_ext_release(struct super_block *sb) { if (!ext4_has_feature_extents(sb)) return; #ifdef EXTENTS_STATS if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) { struct ext4_sb_info *sbi = EXT4_SB(sb); printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n", sbi->s_ext_blocks, sbi->s_ext_extents, sbi->s_ext_blocks / sbi->s_ext_extents); printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n", sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max); } #endif } static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) { ext4_lblk_t ee_block; ext4_fsblk_t ee_pblock; unsigned int ee_len; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); if (ee_len == 0) return 0; return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, EXTENT_STATUS_WRITTEN); } /* FIXME!! we need to try to merge to left or right after zero-out */ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock, ee_len); } /* * ext4_split_extent_at() splits an extent at given block. * * @handle: the journal handle * @inode: the file inode * @path: the path to the extent * @split: the logical block where the extent is splitted. * @split_flags: indicates if the extent could be zeroout if split fails, and * the states(init or unwritten) of new extents. * @flags: flags used to insert new extent to extent tree. * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states * of which are determined by split_flag. * * There are two cases: * a> the extent are splitted into two extent. * b> split is not needed, and just mark the extent. * * return 0 on success. */ static int ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, ext4_lblk_t split, int split_flag, int flags) { struct ext4_ext_path *path = *ppath; ext4_fsblk_t newblock; ext4_lblk_t ee_block; struct ext4_extent *ex, newex, orig_ex, zero_ex; struct ext4_extent *ex2 = NULL; unsigned int ee_len, depth; int err = 0; BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); ext_debug(inode, "logical block %llu\n", (unsigned long long)split); ext4_ext_show_leaf(inode, path); depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); newblock = split - ee_block + ext4_ext_pblock(ex); BUG_ON(split < ee_block || split >= (ee_block + ee_len)); BUG_ON(!ext4_ext_is_unwritten(ex) && split_flag & (EXT4_EXT_MAY_ZEROOUT | EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; if (split == ee_block) { /* * case b: block @split is the block that the extent begins with * then we just change the state of the extent, and splitting * is not needed. */ if (split_flag & EXT4_EXT_MARK_UNWRIT2) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); if (!(flags & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } /* case a */ memcpy(&orig_ex, ex, sizeof(orig_ex)); ex->ee_len = cpu_to_le16(split - ee_block); if (split_flag & EXT4_EXT_MARK_UNWRIT1) ext4_ext_mark_unwritten(ex); /* * path may lead to new leaf, not to original leaf any more * after ext4_ext_insert_extent() returns, */ err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto fix_extent_len; ex2 = &newex; ex2->ee_block = cpu_to_le32(split); ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block)); ext4_ext_store_pblock(ex2, newblock); if (split_flag & EXT4_EXT_MARK_UNWRIT2) ext4_ext_mark_unwritten(ex2); err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags); if (err != -ENOSPC && err != -EDQUOT) goto out; if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { if (split_flag & EXT4_EXT_DATA_VALID1) { err = ext4_ext_zeroout(inode, ex2); zero_ex.ee_block = ex2->ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(ex2)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex2)); } else { err = ext4_ext_zeroout(inode, ex); zero_ex.ee_block = ex->ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex)); } } else { err = ext4_ext_zeroout(inode, &orig_ex); zero_ex.ee_block = orig_ex.ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(&orig_ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(&orig_ex)); } if (!err) { /* update the extent length and mark as initialized */ ex->ee_len = cpu_to_le16(ee_len); ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (!err) /* update extent status tree */ err = ext4_zeroout_es(inode, &zero_ex); /* If we failed at this point, we don't know in which * state the extent tree exactly is so don't try to fix * length of the original extent as it may do even more * damage. */ goto out; } } fix_extent_len: ex->ee_len = orig_ex.ee_len; /* * Ignore ext4_ext_dirty return value since we are already in error path * and err is a non-zero error code. */ ext4_ext_dirty(handle, inode, path + path->p_depth); return err; out: ext4_ext_show_leaf(inode, path); return err; } /* * ext4_split_extents() splits an extent and mark extent which is covered * by @map as split_flags indicates * * It may result in splitting the extent into multiple extents (up to three) * There are three possibilities: * a> There is no split required * b> Splits in two extents: Split is happening at either end of the extent * c> Splits in three extents: Somone is splitting in middle of the extent * */ static int ext4_split_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, struct ext4_map_blocks *map, int split_flag, int flags) { struct ext4_ext_path *path = *ppath; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len, depth; int err = 0; int unwritten; int split_flag1, flags1; int allocated = map->m_len; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); unwritten = ext4_ext_is_unwritten(ex); if (map->m_lblk + map->m_len < ee_block + ee_len) { split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; if (unwritten) split_flag1 |= EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; if (split_flag & EXT4_EXT_DATA_VALID2) split_flag1 |= EXT4_EXT_DATA_VALID1; err = ext4_split_extent_at(handle, inode, ppath, map->m_lblk + map->m_len, split_flag1, flags1); if (err) goto out; } else { allocated = ee_len - (map->m_lblk - ee_block); } /* * Update path is required because previous ext4_split_extent_at() may * result in split of original leaf or extent zeroout. */ path = ext4_find_extent(inode, map->m_lblk, ppath, flags); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); return -EFSCORRUPTED; } unwritten = ext4_ext_is_unwritten(ex); split_flag1 = 0; if (map->m_lblk >= ee_block) { split_flag1 = split_flag & EXT4_EXT_DATA_VALID2; if (unwritten) { split_flag1 |= EXT4_EXT_MARK_UNWRIT1; split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT | EXT4_EXT_MARK_UNWRIT2); } err = ext4_split_extent_at(handle, inode, ppath, map->m_lblk, split_flag1, flags); if (err) goto out; } ext4_ext_show_leaf(inode, path); out: return err ? err : allocated; } /* * This function is called by ext4_ext_map_blocks() if someone tries to write * to an unwritten extent. It may result in splitting the unwritten * extent into multiple extents (up to three - one initialized and two * unwritten). * There are three possibilities: * a> There is no split required: Entire extent should be initialized * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * Pre-conditions: * - The extent pointed to by 'path' is unwritten. * - The extent pointed to by 'path' contains a superset * of the logical span [map->m_lblk, map->m_lblk + map->m_len). * * Post-conditions on success: * - the returned value is the number of blocks beyond map->l_lblk * that are allocated and initialized. * It is guaranteed to be >= map->m_len. */ static int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags) { struct ext4_ext_path *path = *ppath; struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex1, zero_ex2; struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth, map_len = map->m_len; int allocated = 0, max_zeroout = 0; int err = 0; int split_flag = EXT4_EXT_DATA_VALID2; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map_len) eof_block = map->m_lblk + map_len; depth = ext_depth(inode); eh = path[depth].p_hdr; ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); zero_ex1.ee_len = 0; zero_ex2.ee_len = 0; trace_ext4_ext_convert_to_initialized_enter(inode, map, ex); /* Pre-conditions */ BUG_ON(!ext4_ext_is_unwritten(ex)); BUG_ON(!in_range(map->m_lblk, ee_block, ee_len)); /* * Attempt to transfer newly initialized blocks from the currently * unwritten extent to its neighbor. This is much cheaper * than an insertion followed by a merge as those involve costly * memmove() calls. Transferring to the left is the common case in * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE) * followed by append writes. * * Limitations of the current logic: * - L1: we do not deal with writes covering the whole extent. * This would require removing the extent if the transfer * is possible. * - L2: we only attempt to merge with an extent stored in the * same extent tree node. */ if ((map->m_lblk == ee_block) && /* See if we can merge left */ (map_len < ee_len) && /*L1*/ (ex > EXT_FIRST_EXTENT(eh))) { /*L2*/ ext4_lblk_t prev_lblk; ext4_fsblk_t prev_pblk, ee_pblk; unsigned int prev_len; abut_ex = ex - 1; prev_lblk = le32_to_cpu(abut_ex->ee_block); prev_len = ext4_ext_get_actual_len(abut_ex); prev_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((prev_lblk + prev_len) == ee_block) && /*C2*/ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/ (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of ex by 'map_len' blocks */ ex->ee_block = cpu_to_le32(ee_block + map_len); ext4_ext_store_pblock(ex, ee_pblk + map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(prev_len + map_len); /* Result: number of initialized blocks past m_lblk */ allocated = map_len; } } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) && (map_len < ee_len) && /*L1*/ ex < EXT_LAST_EXTENT(eh)) { /*L2*/ /* See if we can merge right */ ext4_lblk_t next_lblk; ext4_fsblk_t next_pblk, ee_pblk; unsigned int next_len; abut_ex = ex + 1; next_lblk = le32_to_cpu(abut_ex->ee_block); next_len = ext4_ext_get_actual_len(abut_ex); next_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((map->m_lblk + map_len) == next_lblk) && /*C2*/ ((ee_pblk + ee_len) == next_pblk) && /*C3*/ (next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of abut_ex by 'map_len' blocks */ abut_ex->ee_block = cpu_to_le32(next_lblk - map_len); ext4_ext_store_pblock(abut_ex, next_pblk - map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(next_len + map_len); /* Result: number of initialized blocks past m_lblk */ allocated = map_len; } } if (allocated) { /* Mark the block containing both extents as dirty */ err = ext4_ext_dirty(handle, inode, path + depth); /* Update path to point to the right extent */ path[depth].p_ext = abut_ex; goto out; } else allocated = ee_len - (map->m_lblk - ee_block); WARN_ON(map->m_lblk < ee_block); /* * It is safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; if (EXT4_EXT_MAY_ZEROOUT & split_flag) max_zeroout = sbi->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); /* * five cases: * 1. split the extent into three extents. * 2. split the extent into two extents, zeroout the head of the first * extent. * 3. split the extent into two extents, zeroout the tail of the second * extent. * 4. split the extent into two extents with out zeroout. * 5. no splitting needed, just possibly zeroout the head and / or the * tail of the extent. */ split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; if (max_zeroout && (allocated > split_map.m_len)) { if (allocated <= max_zeroout) { /* case 3 or 5 */ zero_ex1.ee_block = cpu_to_le32(split_map.m_lblk + split_map.m_len); zero_ex1.ee_len = cpu_to_le16(allocated - split_map.m_len); ext4_ext_store_pblock(&zero_ex1, ext4_ext_pblock(ex) + split_map.m_lblk + split_map.m_len - ee_block); err = ext4_ext_zeroout(inode, &zero_ex1); if (err) goto out; split_map.m_len = allocated; } if (split_map.m_lblk - ee_block + split_map.m_len < max_zeroout) { /* case 2 or 5 */ if (split_map.m_lblk != ee_block) { zero_ex2.ee_block = ex->ee_block; zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk - ee_block); ext4_ext_store_pblock(&zero_ex2, ext4_ext_pblock(ex)); err = ext4_ext_zeroout(inode, &zero_ex2); if (err) goto out; } split_map.m_len += split_map.m_lblk - ee_block; split_map.m_lblk = ee_block; allocated = map->m_len; } } err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag, flags); if (err > 0) err = 0; out: /* If we have gotten a failure, don't zero out status tree */ if (!err) { err = ext4_zeroout_es(inode, &zero_ex1); if (!err) err = ext4_zeroout_es(inode, &zero_ex2); } return err ? err : allocated; } /* * This function is called by ext4_ext_map_blocks() from * ext4_get_blocks_dio_write() when DIO to write * to an unwritten extent. * * Writing to an unwritten extent may result in splitting the unwritten * extent into multiple initialized/unwritten extents (up to three) * There are three possibilities: * a> There is no split required: Entire extent should be unwritten * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * This works the same way in the case of initialized -> unwritten conversion. * * One of more index blocks maybe needed if the extent tree grow after * the unwritten extent split. To prevent ENOSPC occur at the IO * complete, we need to split the unwritten extent before DIO submit * the IO. The unwritten extent called at this time will be split * into three unwritten extent(at most). After IO complete, the part * being filled will be convert to initialized by the end_io callback function * via ext4_convert_unwritten_extents(). * * Returns the size of unwritten extent to be written on success. */ static int ext4_split_convert_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags) { struct ext4_ext_path *path = *ppath; ext4_lblk_t eof_block; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len; int split_flag = 0, depth; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map->m_len); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) eof_block = map->m_lblk + map->m_len; /* * It is safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); /* Convert to unwritten */ if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) { split_flag |= EXT4_EXT_DATA_VALID1; /* Convert to initialized */ } else if (flags & EXT4_GET_BLOCKS_CONVERT) { split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2); } flags |= EXT4_GET_BLOCKS_PRE_IO; return ext4_split_extent(handle, inode, ppath, map, split_flag, flags); } static int ext4_convert_unwritten_extents_endio(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath) { struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; int err = 0; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); /* If extent is larger than requested it is a clear sign that we still * have some extent state machine issues left. So extent_split is still * required. * TODO: Once all related issues will be fixed this situation should be * illegal. */ if (ee_block != map->m_lblk || ee_len > map->m_len) { #ifdef CONFIG_EXT4_DEBUG ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu," " len %u; IO logical block %llu, len %u", inode->i_ino, (unsigned long long)ee_block, ee_len, (unsigned long long)map->m_lblk, map->m_len); #endif err = ext4_split_convert_extents(handle, inode, map, ppath, EXT4_GET_BLOCKS_CONVERT); if (err < 0) return err; path = ext4_find_extent(inode, map->m_lblk, ppath, 0); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); ex = path[depth].p_ext; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; /* first mark the extent as initialized */ ext4_ext_mark_initialized(ex); /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: ext4_ext_show_leaf(inode, path); return err; } static int convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, unsigned int *allocated) { struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; int err = 0; /* * Make sure that the extent is no bigger than we support with * unwritten extent */ if (map->m_len > EXT_UNWRITTEN_MAX_LEN) map->m_len = EXT_UNWRITTEN_MAX_LEN / 2; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); if (ee_block != map->m_lblk || ee_len > map->m_len) { err = ext4_split_convert_extents(handle, inode, map, ppath, EXT4_GET_BLOCKS_CONVERT_UNWRITTEN); if (err < 0) return err; path = ext4_find_extent(inode, map->m_lblk, ppath, 0); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); return -EFSCORRUPTED; } } err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; /* first mark the extent as unwritten */ ext4_ext_mark_unwritten(ex); /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (err) return err; ext4_ext_show_leaf(inode, path); ext4_update_inode_fsync_trans(handle, inode, 1); map->m_flags |= EXT4_MAP_UNWRITTEN; if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; return 0; } static int ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags, unsigned int allocated, ext4_fsblk_t newblock) { struct ext4_ext_path __maybe_unused *path = *ppath; int ret = 0; int err = 0; ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n", (unsigned long long)map->m_lblk, map->m_len, flags, allocated); ext4_ext_show_leaf(inode, path); /* * When writing into unwritten space, we should not fail to * allocate metadata blocks for the new extent block if needed. */ flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL; trace_ext4_ext_handle_unwritten_extents(inode, map, flags, allocated, newblock); /* get_block() before submitting IO, split the extent */ if (flags & EXT4_GET_BLOCKS_PRE_IO) { ret = ext4_split_convert_extents(handle, inode, map, ppath, flags | EXT4_GET_BLOCKS_CONVERT); if (ret < 0) { err = ret; goto out2; } /* * shouldn't get a 0 return when splitting an extent unless * m_len is 0 (bug) or extent has been corrupted */ if (unlikely(ret == 0)) { EXT4_ERROR_INODE(inode, "unexpected ret == 0, m_len = %u", map->m_len); err = -EFSCORRUPTED; goto out2; } map->m_flags |= EXT4_MAP_UNWRITTEN; goto out; } /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { err = ext4_convert_unwritten_extents_endio(handle, inode, map, ppath); if (err < 0) goto out2; ext4_update_inode_fsync_trans(handle, inode, 1); goto map_out; } /* buffered IO cases */ /* * repeat fallocate creation request * we already have an unwritten extent */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { map->m_flags |= EXT4_MAP_UNWRITTEN; goto map_out; } /* buffered READ or buffered write_begin() lookup */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * We have blocks reserved already. We * return allocated blocks so that delalloc * won't do block reservation for us. But * the buffer head will be unmapped so that * a read from the block returns 0s. */ map->m_flags |= EXT4_MAP_UNWRITTEN; goto out1; } /* * Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1. * For buffered writes, at writepage time, etc. Convert a * discovered unwritten extent to written. */ ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags); if (ret < 0) { err = ret; goto out2; } ext4_update_inode_fsync_trans(handle, inode, 1); /* * shouldn't get a 0 return when converting an unwritten extent * unless m_len is 0 (bug) or extent has been corrupted */ if (unlikely(ret == 0)) { EXT4_ERROR_INODE(inode, "unexpected ret == 0, m_len = %u", map->m_len); err = -EFSCORRUPTED; goto out2; } out: allocated = ret; map->m_flags |= EXT4_MAP_NEW; map_out: map->m_flags |= EXT4_MAP_MAPPED; out1: map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; ext4_ext_show_leaf(inode, path); out2: return err ? err : allocated; } /* * get_implied_cluster_alloc - check to see if the requested * allocation (in the map structure) overlaps with a cluster already * allocated in an extent. * @sb The filesystem superblock structure * @map The requested lblk->pblk mapping * @ex The extent structure which might contain an implied * cluster allocation * * This function is called by ext4_ext_map_blocks() after we failed to * find blocks that were already in the inode's extent tree. Hence, * we know that the beginning of the requested region cannot overlap * the extent from the inode's extent tree. There are three cases we * want to catch. The first is this case: * * |--- cluster # N--| * |--- extent ---| |---- requested region ---| * |==========| * * The second case that we need to test for is this one: * * |--------- cluster # N ----------------| * |--- requested region --| |------- extent ----| * |=======================| * * The third case is when the requested region lies between two extents * within the same cluster: * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| * * In each of the above cases, we need to set the map->m_pblk and * map->m_len so it corresponds to the return the extent labelled as * "|====|" from cluster #N, since it is already in use for data in * cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to * signal to ext4_ext_map_blocks() that map->m_pblk should be treated * as a new "allocated" block region. Otherwise, we will return 0 and * ext4_ext_map_blocks() will then allocate one or more new clusters * by calling ext4_mb_new_blocks(). */ static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_map_blocks *map, struct ext4_extent *ex, struct ext4_ext_path *path) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start; ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len = ext4_ext_get_actual_len(ex); /* The extent passed in that we are trying to match */ ex_cluster_start = EXT4_B2C(sbi, ee_block); ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1); /* The requested region passed into ext4_map_blocks() */ rr_cluster_start = EXT4_B2C(sbi, map->m_lblk); if ((rr_cluster_start == ex_cluster_end) || (rr_cluster_start == ex_cluster_start)) { if (rr_cluster_start == ex_cluster_end) ee_start += ee_len - 1; map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset; map->m_len = min(map->m_len, (unsigned) sbi->s_cluster_ratio - c_offset); /* * Check for and handle this case: * * |--------- cluster # N-------------| * |------- extent ----| * |--- requested region ---| * |===========| */ if (map->m_lblk < ee_block) map->m_len = min(map->m_len, ee_block - map->m_lblk); /* * Check for the case where there is already another allocated * block to the right of 'ex' but before the end of the cluster. * * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| */ if (map->m_lblk > ee_block) { ext4_lblk_t next = ext4_ext_next_allocated_block(path); map->m_len = min(map->m_len, next - map->m_lblk); } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1); return 1; } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0); return 0; } /* * Block allocation/map/preallocation routine for extents based files * * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) * * return > 0, number of blocks already mapped/allocated * if create == 0 and these are pre-allocated blocks * buffer head is unmapped * otherwise blocks are mapped * * return = 0, if plain look up failed (blocks have not been allocated) * buffer head is unmapped * * return < 0, error case. */ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct ext4_ext_path *path = NULL; struct ext4_extent newex, *ex, ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0, pblk; int err = 0, depth, ret; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; ext4_lblk_t cluster_offset; ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len); trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ path = ext4_find_extent(inode, map->m_lblk, NULL, 0); if (IS_ERR(path)) { err = PTR_ERR(path); path = NULL; goto out; } depth = ext_depth(inode); /* * consistent leaf must not be empty; * this situation is possible, though, _during_ tree modification; * this is why assert can't be put in ext4_find_extent() */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address " "lblock: %lu, depth: %d pblock %lld", (unsigned long) map->m_lblk, depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } ex = path[depth].p_ext; if (ex) { ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len; /* * unwritten extents are treated as holes, except that * we split out initialized portions during a write. */ ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len); /* if found extent covers block, simply return it */ if (in_range(map->m_lblk, ee_block, ee_len)) { newblock = map->m_lblk - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (map->m_lblk - ee_block); ext_debug(inode, "%u fit into %u:%d -> %llu\n", map->m_lblk, ee_block, ee_len, newblock); /* * If the extent is initialized check whether the * caller wants to convert it to unwritten. */ if ((!ext4_ext_is_unwritten(ex)) && (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { err = convert_initialized_extent(handle, inode, map, &path, &allocated); goto out; } else if (!ext4_ext_is_unwritten(ex)) { map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; ext4_ext_show_leaf(inode, path); goto out; } ret = ext4_ext_handle_unwritten_extents( handle, inode, map, &path, flags, allocated, newblock); if (ret < 0) err = ret; else allocated = ret; goto out; } } /* * requested block isn't allocated yet; * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { ext4_lblk_t hole_start, hole_len; hole_start = map->m_lblk; hole_len = ext4_ext_determine_hole(inode, path, &hole_start); /* * put just found gap into cache to speed up * subsequent requests */ ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); /* Update hole_len to reflect hole size after map->m_lblk */ if (hole_start != map->m_lblk) hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; map->m_len = min_t(unsigned int, map->m_len, hole_len); goto out; } /* * Okay, we need to do block allocation. */ newex.ee_block = cpu_to_le32(map->m_lblk); cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); /* * If we are doing bigalloc, check to see if the extent returned * by ext4_find_extent() implies a cluster we can use. */ if (cluster_offset && ex && get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; goto got_allocated_blocks; } /* find neighbour allocated blocks */ ar.lleft = map->m_lblk; err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft); if (err) goto out; ar.lright = map->m_lblk; err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2); if (err < 0) goto out; /* Check if the extent after searching to the right implies a * cluster we can use. */ if ((sbi->s_cluster_ratio > 1) && err && get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; goto got_allocated_blocks; } /* * See if request is beyond maximum number of blocks we can have in * a single extent. For an initialized extent this limit is * EXT_INIT_MAX_LEN and for an unwritten extent this limit is * EXT_UNWRITTEN_MAX_LEN. */ if (map->m_len > EXT_INIT_MAX_LEN && !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_INIT_MAX_LEN; else if (map->m_len > EXT_UNWRITTEN_MAX_LEN && (flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_UNWRITTEN_MAX_LEN; /* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */ newex.ee_len = cpu_to_le16(map->m_len); err = ext4_ext_check_overlap(sbi, inode, &newex, path); if (err) allocated = ext4_ext_get_actual_len(&newex); else allocated = map->m_len; /* allocate new block */ ar.inode = inode; ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk); ar.logical = map->m_lblk; /* * We calculate the offset from the beginning of the cluster * for the logical block number, since when we allocate a * physical cluster, the physical block should start at the * same offset from the beginning of the cluster. This is * needed so that future calls to get_implied_cluster_alloc() * work correctly. */ offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ar.len = EXT4_NUM_B2C(sbi, offset+allocated); ar.goal -= offset; ar.logical -= offset; if (S_ISREG(inode->i_mode)) ar.flags = EXT4_MB_HINT_DATA; else /* disable in-core preallocation for non-regular files */ ar.flags = 0; if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE) ar.flags |= EXT4_MB_HINT_NOPREALLOC; if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) ar.flags |= EXT4_MB_DELALLOC_RESERVED; if (flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) ar.flags |= EXT4_MB_USE_RESERVED; newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) goto out; allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n", ar.goal, newblock, ar.len, allocated); if (ar.len > allocated) ar.len = allocated; got_allocated_blocks: /* try to insert new extent into found leaf and return */ pblk = newblock + offset; ext4_ext_store_pblock(&newex, pblk); newex.ee_len = cpu_to_le16(ar.len); /* Mark unwritten */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { ext4_ext_mark_unwritten(&newex); map->m_flags |= EXT4_MAP_UNWRITTEN; } err = ext4_ext_insert_extent(handle, inode, &path, &newex, flags); if (err) { if (allocated_clusters) { int fb_flags = 0; /* * free data blocks we just allocated. * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ ext4_discard_preallocations(inode, 0); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, EXT4_C2B(sbi, allocated_clusters), fb_flags); } goto out; } /* * Reduce the reserved cluster count to reflect successful deferred * allocation of delayed allocated clusters or direct allocation of * clusters discovered to be delayed allocated. Once allocated, a * cluster is not included in the reserved count. */ if (test_opt(inode->i_sb, DELALLOC) && allocated_clusters) { if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { /* * When allocating delayed allocated clusters, simply * reduce the reserved cluster count and claim quota */ ext4_da_update_reserve_space(inode, allocated_clusters, 1); } else { ext4_lblk_t lblk, len; unsigned int n; /* * When allocating non-delayed allocated clusters * (from fallocate, filemap, DIO, or clusters * allocated when delalloc has been disabled by * ext4_nonda_switch), reduce the reserved cluster * count by the number of allocated clusters that * have previously been delayed allocated. Quota * has been claimed by ext4_mb_new_blocks() above, * so release the quota reservations made for any * previously delayed allocated clusters. */ lblk = EXT4_LBLK_CMASK(sbi, map->m_lblk); len = allocated_clusters << sbi->s_cluster_bits; n = ext4_es_delayed_clu(inode, lblk, len); if (n > 0) ext4_da_update_reserve_space(inode, (int) n, 0); } } /* * Cache the extent and update transaction to commit on fdatasync only * when it is _not_ an unwritten extent. */ if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0) ext4_update_inode_fsync_trans(handle, inode, 1); else ext4_update_inode_fsync_trans(handle, inode, 0); map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED); map->m_pblk = pblk; map->m_len = ar.len; allocated = map->m_len; ext4_ext_show_leaf(inode, path); out: ext4_ext_drop_refs(path); kfree(path); trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); return err ? err : allocated; } int ext4_ext_truncate(handle_t *handle, struct inode *inode) { struct super_block *sb = inode->i_sb; ext4_lblk_t last_block; int err = 0; /* * TODO: optimization is possible here. * Probably we need not scan at all, * because page truncation is enough. */ /* we have to know where to truncate from in crash case */ EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_mark_inode_dirty(handle, inode); if (err) return err; last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); retry: err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); if (err == -ENOMEM) { cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } if (err) return err; retry_remove_space: err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry_remove_space; } return err; } static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, ext4_lblk_t len, loff_t new_size, int flags) { struct inode *inode = file_inode(file); handle_t *handle; int ret = 0; int ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; unsigned int credits; loff_t epos; BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)); map.m_lblk = offset; map.m_len = len; /* * Don't normalize the request if it can fit in one extent so * that it doesn't get unnecessarily split into multiple * extents. */ if (len <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, len); depth = ext_depth(inode); retry: while (ret >= 0 && len) { /* * Recalculate credits when extent tree depth changes. */ if (depth != ext_depth(inode)) { credits = ext4_chunk_trans_blocks(inode, len); depth = ext_depth(inode); } handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } ret = ext4_map_blocks(handle, inode, &map, flags); if (ret <= 0) { ext4_debug("inode #%lu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ext4_mark_inode_dirty(handle, inode); ret2 = ext4_journal_stop(handle); break; } map.m_lblk += ret; map.m_len = len = len - ret; epos = (loff_t)map.m_lblk << inode->i_blkbits; inode->i_ctime = current_time(inode); if (new_size) { if (epos > new_size) epos = new_size; if (ext4_update_inode_size(inode, epos) & 0x1) inode->i_mtime = inode->i_ctime; } ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); ret3 = ext4_journal_stop(handle); ret2 = ret3 ? ret3 : ret2; if (unlikely(ret2)) break; } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) { ret = 0; goto retry; } return ret > 0 ? ret2 : ret; } static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); handle_t *handle = NULL; unsigned int max_blocks; loff_t new_size = 0; int ret = 0; int flags; int credits; int partial_begin, partial_end; loff_t start, end; ext4_lblk_t lblk; unsigned int blkbits = inode->i_blkbits; trace_ext4_zero_range(inode, offset, len, mode); /* Call ext4_force_commit to flush all data in case of data=journal. */ if (ext4_should_journal_data(inode)) { ret = ext4_force_commit(inode->i_sb); if (ret) return ret; } /* * Round up offset. This is not fallocate, we need to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the * range. */ start = round_up(offset, 1 << blkbits); end = round_down((offset + len), 1 << blkbits); if (start < offset || end > offset + len) return -EINVAL; partial_begin = offset & ((1 << blkbits) - 1); partial_end = (offset + len) & ((1 << blkbits) - 1); lblk = start >> blkbits; max_blocks = (end >> blkbits); if (max_blocks < lblk) max_blocks = 0; else max_blocks -= lblk; inode_lock(inode); /* * Indirect files do not support unwritten extents */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { ret = -EOPNOTSUPP; goto out_mutex; } if (!(mode & FALLOC_FL_KEEP_SIZE) && (offset + len > inode->i_size || offset + len > EXT4_I(inode)->i_disksize)) { new_size = offset + len; ret = inode_newsize_ok(inode, new_size); if (ret) goto out_mutex; } flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode); /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, round_down(offset, 1 << blkbits) >> blkbits, (round_up((offset + len), 1 << blkbits) - round_down(offset, 1 << blkbits)) >> blkbits, new_size, flags); if (ret) goto out_mutex; } /* Zero range excluding the unaligned edges */ if (max_blocks > 0) { flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); /* * Prevent page faults from reinstantiating pages we have * released from page cache. */ down_write(&EXT4_I(inode)->i_mmap_sem); ret = ext4_break_layouts(inode); if (ret) { up_write(&EXT4_I(inode)->i_mmap_sem); goto out_mutex; } ret = ext4_update_disksize_before_punch(inode, offset, len); if (ret) { up_write(&EXT4_I(inode)->i_mmap_sem); goto out_mutex; } /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); up_write(&EXT4_I(inode)->i_mmap_sem); if (ret) goto out_mutex; } if (!partial_begin && !partial_end) goto out_mutex; /* * In worst case we have to writeout two nonadjacent unwritten * blocks and update the inode */ credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1; if (ext4_should_journal_data(inode)) credits += 2; handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(inode->i_sb, ret); goto out_mutex; } inode->i_mtime = inode->i_ctime = current_time(inode); if (new_size) ext4_update_inode_size(inode, new_size); ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits, (offset + len - 1) >> inode->i_sb->s_blocksize_bits); /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); if (file->f_flags & O_SYNC) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); out_mutex: inode_unlock(inode); return ret; } /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. * For block-mapped files, posix_fallocate should fall back to the method * of writing zeroes to the required new blocks (the same behavior which is * expected for file systems which do not support fallocate() system call). */ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); loff_t new_size = 0; unsigned int max_blocks; int ret = 0; int flags; ext4_lblk_t lblk; unsigned int blkbits = inode->i_blkbits; /* * Encrypted inodes can't handle collapse range or insert * range since we would need to re-encrypt blocks with a * different IV or XTS tweak (which are based on the logical * block number). */ if (IS_ENCRYPTED(inode) && (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; ext4_fc_start_update(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { ret = ext4_punch_hole(inode, offset, len); goto exit; } ret = ext4_convert_inline_data(inode); if (ret) goto exit; if (mode & FALLOC_FL_COLLAPSE_RANGE) { ret = ext4_collapse_range(inode, offset, len); goto exit; } if (mode & FALLOC_FL_INSERT_RANGE) { ret = ext4_insert_range(inode, offset, len); goto exit; } if (mode & FALLOC_FL_ZERO_RANGE) { ret = ext4_zero_range(file, offset, len, mode); goto exit; } trace_ext4_fallocate_enter(inode, offset, len, mode); lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; inode_lock(inode); /* * We only support preallocation for extent-based files only */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { ret = -EOPNOTSUPP; goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE) && (offset + len > inode->i_size || offset + len > EXT4_I(inode)->i_disksize)) { new_size = offset + len; ret = inode_newsize_ok(inode, new_size); if (ret) goto out; } /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) { ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, EXT4_I(inode)->i_sync_tid); } out: inode_unlock(inode); trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); exit: ext4_fc_stop_update(inode); return ret; } /* * This function convert a range of blocks to written extents * The caller of this function will pass the start offset and the size. * all unwritten extents within this range will be converted to * written extents. * * This function is called from the direct IO end io call back * function, to convert the fallocated extents after IO is completed. * Returns 0 on success. */ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; unsigned int credits = 0; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); if (!handle) { /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, max_blocks); } while (ret >= 0 && ret < max_blocks) { map.m_lblk += ret; map.m_len = (max_blocks -= ret); if (credits) { handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } } ret = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_IO_CONVERT_EXT); if (ret <= 0) ext4_warning(inode->i_sb, "inode #%lu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ret2 = ext4_mark_inode_dirty(handle, inode); if (credits) { ret3 = ext4_journal_stop(handle); if (unlikely(ret3)) ret2 = ret3; } if (ret <= 0 || ret2) break; } return ret > 0 ? ret2 : ret; } int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end) { int ret = 0, err = 0; struct ext4_io_end_vec *io_end_vec; /* * This is somewhat ugly but the idea is clear: When transaction is * reserved, everything goes into it. Otherwise we rather start several * smaller transactions for conversion of each extent separately. */ if (handle) { handle = ext4_journal_start_reserved(handle, EXT4_HT_EXT_CONVERT); if (IS_ERR(handle)) return PTR_ERR(handle); } list_for_each_entry(io_end_vec, &io_end->list_vec, list) { ret = ext4_convert_unwritten_extents(handle, io_end->inode, io_end_vec->offset, io_end_vec->size); if (ret) break; } if (handle) err = ext4_journal_stop(handle); return ret < 0 ? ret : err; } static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap) { __u64 physical = 0; __u64 length = 0; int blockbits = inode->i_sb->s_blocksize_bits; int error = 0; u16 iomap_type; /* in-inode? */ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { struct ext4_iloc iloc; int offset; /* offset of xattr in inode */ error = ext4_get_inode_loc(inode, &iloc); if (error) return error; physical = (__u64)iloc.bh->b_blocknr << blockbits; offset = EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize; physical += offset; length = EXT4_SB(inode->i_sb)->s_inode_size - offset; brelse(iloc.bh); iomap_type = IOMAP_INLINE; } else if (EXT4_I(inode)->i_file_acl) { /* external block */ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits; length = inode->i_sb->s_blocksize; iomap_type = IOMAP_MAPPED; } else { /* no in-inode or external block for xattr, so return -ENOENT */ error = -ENOENT; goto out; } iomap->addr = physical; iomap->offset = 0; iomap->length = length; iomap->type = iomap_type; iomap->flags = 0; out: return error; } static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { int error; error = ext4_iomap_xattr_fiemap(inode, iomap); if (error == 0 && (offset >= iomap->length)) error = -ENOENT; return error; } static const struct iomap_ops ext4_iomap_xattr_ops = { .iomap_begin = ext4_iomap_xattr_begin, }; static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len) { u64 maxbytes; if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) maxbytes = inode->i_sb->s_maxbytes; else maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; if (*len == 0) return -EINVAL; if (start > maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; return 0; } int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { int error = 0; if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) return error; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } /* * For bitmap files the maximum size limit could be smaller than * s_maxbytes, so check len here manually instead of just relying on the * generic check. */ error = ext4_fiemap_check_ranges(inode, start, &len); if (error) return error; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_xattr_ops); } return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops); } int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { ext4_lblk_t start_blk, len_blks; __u64 last_blk; int error = 0; if (ext4_has_inline_data(inode)) { int has_inline; down_read(&EXT4_I(inode)->xattr_sem); has_inline = ext4_has_inline_data(inode); up_read(&EXT4_I(inode)->xattr_sem); if (has_inline) return 0; } if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) return error; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } error = fiemap_prep(inode, fieinfo, start, &len, 0); if (error) return error; error = ext4_fiemap_check_ranges(inode, start, &len); if (error) return error; start_blk = start >> inode->i_sb->s_blocksize_bits; last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; if (last_blk >= EXT_MAX_BLOCKS) last_blk = EXT_MAX_BLOCKS-1; len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; /* * Walk the extent tree gathering extent information * and pushing extents back to the user. */ return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo); } /* * ext4_ext_shift_path_extents: * Shift the extents of a path structure lying between path[depth].p_ext * and EXT_LAST_EXTENT(path[depth].p_hdr), by @shift blocks. @SHIFT tells * if it is right shift or left shift operation. */ static int ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, struct inode *inode, handle_t *handle, enum SHIFT_DIRECTION SHIFT) { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; bool update = false; int credits, restart_credits; depth = path->p_depth; while (depth >= 0) { if (depth == path->p_depth) { ex_start = path[depth].p_ext; if (!ex_start) return -EFSCORRUPTED; ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); /* leaf + sb + inode */ credits = 3; if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) { update = true; /* extent tree + sb + inode */ credits = depth + 2; } restart_credits = ext4_writepage_trans_blocks(inode); err = ext4_datasem_ensure_credits(handle, inode, credits, restart_credits, 0); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { le32_add_cpu(&ex_start->ee_block, -shift); /* Try to merge to the left. */ if ((ex_start > EXT_FIRST_EXTENT(path[depth].p_hdr)) && ext4_ext_try_to_merge_right(inode, path, ex_start - 1)) ex_last--; else ex_start++; } else { le32_add_cpu(&ex_last->ee_block, shift); ext4_ext_try_to_merge_right(inode, path, ex_last); ex_last--; } } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; if (--depth < 0 || !update) break; } /* Update index too */ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; if (SHIFT == SHIFT_LEFT) le32_add_cpu(&path[depth].p_idx->ei_block, -shift); else le32_add_cpu(&path[depth].p_idx->ei_block, shift); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; /* we are done if current index is not a starting index */ if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr)) break; depth--; } out: return err; } /* * ext4_ext_shift_extents: * All the extents which lies in the range from @start to the last allocated * block for the @inode are shifted either towards left or right (depending * upon @SHIFT) by @shift blocks. * On success, 0 is returned, error otherwise. */ static int ext4_ext_shift_extents(struct inode *inode, handle_t *handle, ext4_lblk_t start, ext4_lblk_t shift, enum SHIFT_DIRECTION SHIFT) { struct ext4_ext_path *path; int ret = 0, depth; struct ext4_extent *extent; ext4_lblk_t stop, *iterator, ex_start, ex_end; ext4_lblk_t tmp = EXT_MAX_BLOCKS; /* Let path point to the last extent */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) goto out; stop = le32_to_cpu(extent->ee_block); /* * For left shifts, make sure the hole on the left is big enough to * accommodate the shift. For right shifts, make sure the last extent * won't be shifted beyond EXT_MAX_BLOCKS. */ if (SHIFT == SHIFT_LEFT) { path = ext4_find_extent(inode, start - 1, &path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (extent) { ex_start = le32_to_cpu(extent->ee_block); ex_end = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { ex_start = 0; ex_end = 0; } if ((start == ex_start && shift > ex_start) || (shift > start - ex_end)) { ret = -EINVAL; goto out; } } else { if (shift > EXT_MAX_BLOCKS - (stop + ext4_ext_get_actual_len(extent))) { ret = -EINVAL; goto out; } } /* * In case of left shift, iterator points to start and it is increased * till we reach stop. In case of right shift, iterator points to stop * and it is decreased till we reach start. */ again: if (SHIFT == SHIFT_LEFT) iterator = &start; else iterator = &stop; if (tmp != EXT_MAX_BLOCKS) *iterator = tmp; /* * Its safe to start updating extents. Start and stop are unsigned, so * in case of right shift if extent with 0 block is reached, iterator * becomes NULL to indicate the end of the loop. */ while (iterator && start <= stop) { path = ext4_find_extent(inode, *iterator, &path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) *iterator); return -EFSCORRUPTED; } if (SHIFT == SHIFT_LEFT && *iterator > le32_to_cpu(extent->ee_block)) { /* Hole, move to the next extent */ if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) { path[depth].p_ext++; } else { *iterator = ext4_ext_next_allocated_block(path); continue; } } tmp = *iterator; if (SHIFT == SHIFT_LEFT) { extent = EXT_LAST_EXTENT(path[depth].p_hdr); *iterator = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); if (le32_to_cpu(extent->ee_block) > 0) *iterator = le32_to_cpu(extent->ee_block) - 1; else /* Beginning is reached, end of the loop */ iterator = NULL; /* Update path extent in case we need to stop */ while (le32_to_cpu(extent->ee_block) < start) extent++; path[depth].p_ext = extent; } ret = ext4_ext_shift_path_extents(path, shift, inode, handle, SHIFT); /* iterator can be NULL which means we should break */ if (ret == -EAGAIN) goto again; if (ret) break; } out: ext4_ext_drop_refs(path); kfree(path); return ret; } /* * ext4_collapse_range: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) { struct super_block *sb = inode->i_sb; ext4_lblk_t punch_start, punch_stop; handle_t *handle; unsigned int credits; loff_t new_size, ioffset; int ret; /* * We need to test this early because xfstests assumes that a * collapse range of (0, 1) will return EOPNOTSUPP if the file * system does not support collapse range. */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Collapse range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; trace_ext4_collapse_range(inode, offset, len); punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb); punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb); /* Call ext4_force_commit to flush all data in case of data=journal. */ if (ext4_should_journal_data(inode)) { ret = ext4_force_commit(inode->i_sb); if (ret) return ret; } inode_lock(inode); /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation */ if (offset + len >= inode->i_size) { ret = -EINVAL; goto out_mutex; } /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; goto out_mutex; } /* Wait for existing dio to complete */ inode_dio_wait(inode); /* * Prevent page faults from reinstantiating pages we have released from * page cache. */ down_write(&EXT4_I(inode)->i_mmap_sem); ret = ext4_break_layouts(inode); if (ret) goto out_mmap; /* * Need to round down offset to be aligned with page size boundary * for page size > block size. */ ioffset = round_down(offset, PAGE_SIZE); /* * Write tail of the last page before removed range since it will get * removed from the page cache below. */ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset); if (ret) goto out_mmap; /* * Write data that will be shifted to preserve them when discarding * page cache below. We are also protected from pages becoming dirty * by i_mmap_sem. */ ret = filemap_write_and_wait_range(inode->i_mapping, offset + len, LLONG_MAX); if (ret) goto out_mmap; truncate_pagecache(inode, ioffset); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_mmap; } ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } ext4_discard_preallocations(inode, 0); ret = ext4_ext_shift_extents(inode, handle, punch_stop, punch_stop - punch_start, SHIFT_LEFT); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } new_size = inode->i_size - len; i_size_write(inode, new_size); EXT4_I(inode)->i_disksize = new_size; up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); ext4_fc_stop_ineligible(sb); out_mmap: up_write(&EXT4_I(inode)->i_mmap_sem); out_mutex: inode_unlock(inode); return ret; } /* * ext4_insert_range: * This function implements the FALLOC_FL_INSERT_RANGE flag of fallocate. * The data blocks starting from @offset to the EOF are shifted by @len * towards right to create a hole in the @inode. Inode size is increased * by len bytes. * Returns 0 on success, error otherwise. */ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) { struct super_block *sb = inode->i_sb; handle_t *handle; struct ext4_ext_path *path; struct ext4_extent *extent; ext4_lblk_t offset_lblk, len_lblk, ee_start_lblk = 0; unsigned int credits, ee_len; int ret = 0, depth, split_flag = 0; loff_t ioffset; /* * We need to test this early because xfstests assumes that an * insert range of (0, 1) will return EOPNOTSUPP if the file * system does not support insert range. */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Insert range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; trace_ext4_insert_range(inode, offset, len); offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb); len_lblk = len >> EXT4_BLOCK_SIZE_BITS(sb); /* Call ext4_force_commit to flush all data in case of data=journal */ if (ext4_should_journal_data(inode)) { ret = ext4_force_commit(inode->i_sb); if (ret) return ret; } inode_lock(inode); /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; goto out_mutex; } /* Check whether the maximum file size would be exceeded */ if (len > inode->i_sb->s_maxbytes - inode->i_size) { ret = -EFBIG; goto out_mutex; } /* Offset must be less than i_size */ if (offset >= inode->i_size) { ret = -EINVAL; goto out_mutex; } /* Wait for existing dio to complete */ inode_dio_wait(inode); /* * Prevent page faults from reinstantiating pages we have released from * page cache. */ down_write(&EXT4_I(inode)->i_mmap_sem); ret = ext4_break_layouts(inode); if (ret) goto out_mmap; /* * Need to round down to align start offset to page size boundary * for page size > block size. */ ioffset = round_down(offset, PAGE_SIZE); /* Write out all dirty pages */ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, LLONG_MAX); if (ret) goto out_mmap; truncate_pagecache(inode, ioffset); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_mmap; } ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; EXT4_I(inode)->i_disksize += len; inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); path = ext4_find_extent(inode, offset_lblk, NULL, 0); if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } depth = ext_depth(inode); extent = path[depth].p_ext; if (extent) { ee_start_lblk = le32_to_cpu(extent->ee_block); ee_len = ext4_ext_get_actual_len(extent); /* * If offset_lblk is not the starting block of extent, split * the extent @offset_lblk */ if ((offset_lblk > ee_start_lblk) && (offset_lblk < (ee_start_lblk + ee_len))) { if (ext4_ext_is_unwritten(extent)) split_flag = EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; ret = ext4_split_extent_at(handle, inode, &path, offset_lblk, split_flag, EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_METADATA_NOFAIL); } ext4_ext_drop_refs(path); kfree(path); if (ret < 0) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } } else { ext4_ext_drop_refs(path); kfree(path); } ret = ext4_es_remove_extent(inode, offset_lblk, EXT_MAX_BLOCKS - offset_lblk); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } /* * if offset_lblk lies in a hole which is at start of file, use * ee_start_lblk to shift extents */ ret = ext4_ext_shift_extents(inode, handle, ee_start_lblk > offset_lblk ? ee_start_lblk : offset_lblk, len_lblk, SHIFT_RIGHT); up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); ext4_fc_stop_ineligible(sb); out_mmap: up_write(&EXT4_I(inode)->i_mmap_sem); out_mutex: inode_unlock(inode); return ret; } /** * ext4_swap_extents() - Swap extents between two inodes * @handle: handle for this transaction * @inode1: First inode * @inode2: Second inode * @lblk1: Start block for first inode * @lblk2: Start block for second inode * @count: Number of blocks to swap * @unwritten: Mark second inode's extents as unwritten after swap * @erp: Pointer to save error value * * This helper routine does exactly what is promise "swap extents". All other * stuff such as page-cache locking consistency, bh mapping consistency or * extent's data copying must be performed by caller. * Locking: * i_mutex is held for both inodes * i_data_sem is locked for write for both inodes * Assumptions: * All pages from requested range are locked for both inodes */ int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int unwritten, int *erp) { struct ext4_ext_path *path1 = NULL; struct ext4_ext_path *path2 = NULL; int replaced_count = 0; BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem)); BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem)); BUG_ON(!inode_is_locked(inode1)); BUG_ON(!inode_is_locked(inode2)); *erp = ext4_es_remove_extent(inode1, lblk1, count); if (unlikely(*erp)) return 0; *erp = ext4_es_remove_extent(inode2, lblk2, count); if (unlikely(*erp)) return 0; while (count) { struct ext4_extent *ex1, *ex2, tmp_ex; ext4_lblk_t e1_blk, e2_blk; int e1_len, e2_len, len; int split = 0; path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); path1 = NULL; finish: count = 0; goto repeat; } path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); path2 = NULL; goto finish; } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) goto finish; e1_blk = le32_to_cpu(ex1->ee_block); e2_blk = le32_to_cpu(ex2->ee_block); e1_len = ext4_ext_get_actual_len(ex1); e2_len = ext4_ext_get_actual_len(ex2); /* Hole handling */ if (!in_range(lblk1, e1_blk, e1_len) || !in_range(lblk2, e2_blk, e2_len)) { ext4_lblk_t next1, next2; /* if hole after extent, then go to next extent */ next1 = ext4_ext_next_allocated_block(path1); next2 = ext4_ext_next_allocated_block(path2); /* If hole before extent, then shift to that extent */ if (e1_blk > lblk1) next1 = e1_blk; if (e2_blk > lblk2) next2 = e2_blk; /* Do we have something to swap */ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS) goto finish; /* Move to the rightest boundary */ len = next1 - lblk1; if (len < next2 - lblk2) len = next2 - lblk2; if (len > count) len = count; lblk1 += len; lblk2 += len; count -= len; goto repeat; } /* Prepare left boundary */ if (e1_blk < lblk1) { split = 1; *erp = ext4_force_split_extent_at(handle, inode1, &path1, lblk1, 0); if (unlikely(*erp)) goto finish; } if (e2_blk < lblk2) { split = 1; *erp = ext4_force_split_extent_at(handle, inode2, &path2, lblk2, 0); if (unlikely(*erp)) goto finish; } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) goto repeat; /* Prepare right boundary */ len = count; if (len > e1_blk + e1_len - lblk1) len = e1_blk + e1_len - lblk1; if (len > e2_blk + e2_len - lblk2) len = e2_blk + e2_len - lblk2; if (len != e1_len) { split = 1; *erp = ext4_force_split_extent_at(handle, inode1, &path1, lblk1 + len, 0); if (unlikely(*erp)) goto finish; } if (len != e2_len) { split = 1; *erp = ext4_force_split_extent_at(handle, inode2, &path2, lblk2 + len, 0); if (*erp) goto finish; } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) goto repeat; BUG_ON(e2_len != e1_len); *erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth); if (unlikely(*erp)) goto finish; *erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto finish; /* Both extents are fully inside boundaries. Swap it now */ tmp_ex = *ex1; ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2)); ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex)); ex1->ee_len = cpu_to_le16(e2_len); ex2->ee_len = cpu_to_le16(e1_len); if (unwritten) ext4_ext_mark_unwritten(ex2); if (ext4_ext_is_unwritten(&tmp_ex)) ext4_ext_mark_unwritten(ex1); ext4_ext_try_to_merge(handle, inode2, path2, ex2); ext4_ext_try_to_merge(handle, inode1, path1, ex1); *erp = ext4_ext_dirty(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto finish; *erp = ext4_ext_dirty(handle, inode1, path1 + path1->p_depth); /* * Looks scarry ah..? second inode already points to new blocks, * and it was successfully dirtied. But luckily error may happen * only due to journal error, so full transaction will be * aborted anyway. */ if (unlikely(*erp)) goto finish; lblk1 += len; lblk2 += len; replaced_count += len; count -= len; repeat: ext4_ext_drop_refs(path1); kfree(path1); ext4_ext_drop_refs(path2); kfree(path2); path1 = path2 = NULL; } return replaced_count; } /* * ext4_clu_mapped - determine whether any block in a logical cluster has * been mapped to a physical cluster * * @inode - file containing the logical cluster * @lclu - logical cluster of interest * * Returns 1 if any block in the logical cluster is mapped, signifying * that a physical cluster has been allocated for it. Otherwise, * returns 0. Can also return negative error codes. Derived from * ext4_ext_map_blocks(). */ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_ext_path *path; int depth, mapped = 0, err = 0; struct ext4_extent *extent; ext4_lblk_t first_lblk, first_lclu, last_lclu; /* search for the extent closest to the first block in the cluster */ path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0); if (IS_ERR(path)) { err = PTR_ERR(path); path = NULL; goto out; } depth = ext_depth(inode); /* * A consistent leaf must not be empty. This situation is possible, * though, _during_ tree modification, and it's why an assert can't * be put in ext4_find_extent(). */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address - lblock: %lu, depth: %d, pblock: %lld", (unsigned long) EXT4_C2B(sbi, lclu), depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } extent = path[depth].p_ext; /* can't be mapped if the extent tree is empty */ if (extent == NULL) goto out; first_lblk = le32_to_cpu(extent->ee_block); first_lclu = EXT4_B2C(sbi, first_lblk); /* * Three possible outcomes at this point - found extent spanning * the target cluster, to the left of the target cluster, or to the * right of the target cluster. The first two cases are handled here. * The last case indicates the target cluster is not mapped. */ if (lclu >= first_lclu) { last_lclu = EXT4_B2C(sbi, first_lblk + ext4_ext_get_actual_len(extent) - 1); if (lclu <= last_lclu) { mapped = 1; } else { first_lblk = ext4_ext_next_allocated_block(path); first_lclu = EXT4_B2C(sbi, first_lblk); if (lclu == first_lclu) mapped = 1; } } out: ext4_ext_drop_refs(path); kfree(path); return err ? err : mapped; } /* * Updates physical block address and unwritten status of extent * starting at lblk start and of len. If such an extent doesn't exist, * this function splits the extent tree appropriately to create an * extent like this. This function is called in the fast commit * replay path. Returns 0 on success and error on failure. */ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, int len, int unwritten, ext4_fsblk_t pblk) { struct ext4_ext_path *path = NULL, *ppath; struct ext4_extent *ex; int ret; path = ext4_find_extent(inode, start, NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ret = -EFSCORRUPTED; goto out; } if (le32_to_cpu(ex->ee_block) != start || ext4_ext_get_actual_len(ex) != len) { /* We need to split this extent to match our extent first */ ppath = path; down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_force_split_extent_at(NULL, inode, &ppath, start, 1); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out; kfree(path); path = ext4_find_extent(inode, start, NULL, 0); if (IS_ERR(path)) return -1; ppath = path; ex = path[path->p_depth].p_ext; WARN_ON(le32_to_cpu(ex->ee_block) != start); if (ext4_ext_get_actual_len(ex) != len) { down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_force_split_extent_at(NULL, inode, &ppath, start + len, 1); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out; kfree(path); path = ext4_find_extent(inode, start, NULL, 0); if (IS_ERR(path)) return -EINVAL; ex = path[path->p_depth].p_ext; } } if (unwritten) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); ext4_ext_store_pblock(ex, pblk); down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); out: ext4_ext_drop_refs(path); kfree(path); ext4_mark_inode_dirty(NULL, inode); return ret; } /* Try to shrink the extent tree */ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t old_cur, cur = 0; while (cur < end) { path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) return; ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); ext4_mark_inode_dirty(NULL, inode); return; } old_cur = cur; cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); if (cur <= old_cur) cur = old_cur + 1; ext4_ext_try_to_merge(NULL, inode, path, ex); down_write(&EXT4_I(inode)->i_data_sem); ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); ext4_mark_inode_dirty(NULL, inode); ext4_ext_drop_refs(path); kfree(path); } } /* Check if *cur is a hole and if it is, skip it */ static int skip_hole(struct inode *inode, ext4_lblk_t *cur) { int ret; struct ext4_map_blocks map; map.m_lblk = *cur; map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; if (ret != 0) return 0; *cur = *cur + map.m_len; return 0; } /* Count number of blocks used by this inode and update i_blocks */ int ext4_ext_replay_set_iblocks(struct inode *inode) { struct ext4_ext_path *path = NULL, *path2 = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int numblks = 0, i, ret = 0; ext4_fsblk_t cmp1, cmp2; struct ext4_map_blocks map; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); goto out; } end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); ext4_ext_drop_refs(path); kfree(path); /* Count the number of data blocks */ cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) numblks += ret; cur = cur + map.m_len; } /* * Count the number of extent tree blocks. We do it by looking up * two successive extents and determining the difference between * their paths. When path is different for 2 successive extents * we compare the blocks in the path at each level and increment * iblocks by total number of differences found. */ cur = 0; ret = skip_hole(inode, &cur); if (ret < 0) goto out; path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) goto out; numblks += path->p_depth; ext4_ext_drop_refs(path); kfree(path); while (cur < end) { path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) break; ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); return 0; } cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); ret = skip_hole(inode, &cur); if (ret < 0) { ext4_ext_drop_refs(path); kfree(path); break; } path2 = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path2)) { ext4_ext_drop_refs(path); kfree(path); break; } ex = path2[path2->p_depth].p_ext; for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) { cmp1 = cmp2 = 0; if (i <= path->p_depth) cmp1 = path[i].p_bh ? path[i].p_bh->b_blocknr : 0; if (i <= path2->p_depth) cmp2 = path2[i].p_bh ? path2[i].p_bh->b_blocknr : 0; if (cmp1 != cmp2 && cmp2 != 0) numblks++; } ext4_ext_drop_refs(path); ext4_ext_drop_refs(path2); kfree(path); kfree(path2); } out: inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9); ext4_mark_inode_dirty(NULL, inode); return 0; } int ext4_ext_clear_bb(struct inode *inode) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int j, ret = 0; struct ext4_map_blocks map; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); return 0; } end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); ext4_ext_drop_refs(path); kfree(path); cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, NULL, 0); if (!IS_ERR_OR_NULL(path)) { for (j = 0; j < path->p_depth; j++) { ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 0); } ext4_ext_drop_refs(path); kfree(path); } ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); } cur = cur + map.m_len; } return 0; }
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 /* * Copyright (c) 1982, 1986 Regents of the University of California. * All rights reserved. * * This code is derived from software contributed to Berkeley by * Robert Elz at The University of Melbourne. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #ifndef _LINUX_QUOTA_ #define _LINUX_QUOTA_ #include <linux/list.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/spinlock.h> #include <linux/wait.h> #include <linux/percpu_counter.h> #include <linux/dqblk_xfs.h> #include <linux/dqblk_v1.h> #include <linux/dqblk_v2.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/projid.h> #include <uapi/linux/quota.h> #undef USRQUOTA #undef GRPQUOTA #undef PRJQUOTA enum quota_type { USRQUOTA = 0, /* element used for user quotas */ GRPQUOTA = 1, /* element used for group quotas */ PRJQUOTA = 2, /* element used for project quotas */ }; /* Masks for quota types when used as a bitmask */ #define QTYPE_MASK_USR (1 << USRQUOTA) #define QTYPE_MASK_GRP (1 << GRPQUOTA) #define QTYPE_MASK_PRJ (1 << PRJQUOTA) typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */ typedef long long qsize_t; /* Type in which we store sizes */ struct kqid { /* Type in which we store the quota identifier */ union { kuid_t uid; kgid_t gid; kprojid_t projid; }; enum quota_type type; /* USRQUOTA (uid) or GRPQUOTA (gid) or PRJQUOTA (projid) */ }; extern bool qid_eq(struct kqid left, struct kqid right); extern bool qid_lt(struct kqid left, struct kqid right); extern qid_t from_kqid(struct user_namespace *to, struct kqid qid); extern qid_t from_kqid_munged(struct user_namespace *to, struct kqid qid); extern bool qid_valid(struct kqid qid); /** * make_kqid - Map a user-namespace, type, qid tuple into a kqid. * @from: User namespace that the qid is in * @type: The type of quota * @qid: Quota identifier * * Maps a user-namespace, type qid tuple into a kernel internal * kqid, and returns that kqid. * * When there is no mapping defined for the user-namespace, type, * qid tuple an invalid kqid is returned. Callers are expected to * test for and handle handle invalid kqids being returned. * Invalid kqids may be tested for using qid_valid(). */ static inline struct kqid make_kqid(struct user_namespace *from, enum quota_type type, qid_t qid) { struct kqid kqid; kqid.type = type; switch (type) { case USRQUOTA: kqid.uid = make_kuid(from, qid); break; case GRPQUOTA: kqid.gid = make_kgid(from, qid); break; case PRJQUOTA: kqid.projid = make_kprojid(from, qid); break; default: BUG(); } return kqid; } /** * make_kqid_invalid - Explicitly make an invalid kqid * @type: The type of quota identifier * * Returns an invalid kqid with the specified type. */ static inline struct kqid make_kqid_invalid(enum quota_type type) { struct kqid kqid; kqid.type = type; switch (type) { case USRQUOTA: kqid.uid = INVALID_UID; break; case GRPQUOTA: kqid.gid = INVALID_GID; break; case PRJQUOTA: kqid.projid = INVALID_PROJID; break; default: BUG(); } return kqid; } /** * make_kqid_uid - Make a kqid from a kuid * @uid: The kuid to make the quota identifier from */ static inline struct kqid make_kqid_uid(kuid_t uid) { struct kqid kqid; kqid.type = USRQUOTA; kqid.uid = uid; return kqid; } /** * make_kqid_gid - Make a kqid from a kgid * @gid: The kgid to make the quota identifier from */ static inline struct kqid make_kqid_gid(kgid_t gid) { struct kqid kqid; kqid.type = GRPQUOTA; kqid.gid = gid; return kqid; } /** * make_kqid_projid - Make a kqid from a projid * @projid: The kprojid to make the quota identifier from */ static inline struct kqid make_kqid_projid(kprojid_t projid) { struct kqid kqid; kqid.type = PRJQUOTA; kqid.projid = projid; return kqid; } /** * qid_has_mapping - Report if a qid maps into a user namespace. * @ns: The user namespace to see if a value maps into. * @qid: The kernel internal quota identifier to test. */ static inline bool qid_has_mapping(struct user_namespace *ns, struct kqid qid) { return from_kqid(ns, qid) != (qid_t) -1; } extern spinlock_t dq_data_lock; /* Maximal numbers of writes for quota operation (insert/delete/update) * (over VFS all formats) */ #define DQUOT_INIT_ALLOC max(V1_INIT_ALLOC, V2_INIT_ALLOC) #define DQUOT_INIT_REWRITE max(V1_INIT_REWRITE, V2_INIT_REWRITE) #define DQUOT_DEL_ALLOC max(V1_DEL_ALLOC, V2_DEL_ALLOC) #define DQUOT_DEL_REWRITE max(V1_DEL_REWRITE, V2_DEL_REWRITE) /* * Data for one user/group kept in memory */ struct mem_dqblk { qsize_t dqb_bhardlimit; /* absolute limit on disk blks alloc */ qsize_t dqb_bsoftlimit; /* preferred limit on disk blks */ qsize_t dqb_curspace; /* current used space */ qsize_t dqb_rsvspace; /* current reserved space for delalloc*/ qsize_t dqb_ihardlimit; /* absolute limit on allocated inodes */ qsize_t dqb_isoftlimit; /* preferred inode limit */ qsize_t dqb_curinodes; /* current # allocated inodes */ time64_t dqb_btime; /* time limit for excessive disk use */ time64_t dqb_itime; /* time limit for excessive inode use */ }; /* * Data for one quotafile kept in memory */ struct quota_format_type; struct mem_dqinfo { struct quota_format_type *dqi_format; int dqi_fmt_id; /* Id of the dqi_format - used when turning * quotas on after remount RW */ struct list_head dqi_dirty_list; /* List of dirty dquots [dq_list_lock] */ unsigned long dqi_flags; /* DFQ_ flags [dq_data_lock] */ unsigned int dqi_bgrace; /* Space grace time [dq_data_lock] */ unsigned int dqi_igrace; /* Inode grace time [dq_data_lock] */ qsize_t dqi_max_spc_limit; /* Maximum space limit [static] */ qsize_t dqi_max_ino_limit; /* Maximum inode limit [static] */ void *dqi_priv; }; struct super_block; /* Mask for flags passed to userspace */ #define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE) /* Mask for flags modifiable from userspace */ #define DQF_SETINFO_MASK DQF_ROOT_SQUASH enum { DQF_INFO_DIRTY_B = DQF_PRIVATE, }; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); static inline int info_dirty(struct mem_dqinfo *info) { return test_bit(DQF_INFO_DIRTY_B, &info->dqi_flags); } enum { DQST_LOOKUPS, DQST_DROPS, DQST_READS, DQST_WRITES, DQST_CACHE_HITS, DQST_ALLOC_DQUOTS, DQST_FREE_DQUOTS, DQST_SYNCS, _DQST_DQSTAT_LAST }; struct dqstats { unsigned long stat[_DQST_DQSTAT_LAST]; struct percpu_counter counter[_DQST_DQSTAT_LAST]; }; extern struct dqstats dqstats; static inline void dqstats_inc(unsigned int type) { percpu_counter_inc(&dqstats.counter[type]); } static inline void dqstats_dec(unsigned int type) { percpu_counter_dec(&dqstats.counter[type]); } #define DQ_MOD_B 0 /* dquot modified since read */ #define DQ_BLKS_B 1 /* uid/gid has been warned about blk limit */ #define DQ_INODES_B 2 /* uid/gid has been warned about inode limit */ #define DQ_FAKE_B 3 /* no limits only usage */ #define DQ_READ_B 4 /* dquot was read into memory */ #define DQ_ACTIVE_B 5 /* dquot is active (dquot_release not called) */ #define DQ_LASTSET_B 6 /* Following 6 bits (see QIF_) are reserved\ * for the mask of entries set via SETQUOTA\ * quotactl. They are set under dq_data_lock\ * and the quota format handling dquot can\ * clear them when it sees fit. */ struct dquot { struct hlist_node dq_hash; /* Hash list in memory [dq_list_lock] */ struct list_head dq_inuse; /* List of all quotas [dq_list_lock] */ struct list_head dq_free; /* Free list element [dq_list_lock] */ struct list_head dq_dirty; /* List of dirty dquots [dq_list_lock] */ struct mutex dq_lock; /* dquot IO lock */ spinlock_t dq_dqb_lock; /* Lock protecting dq_dqb changes */ atomic_t dq_count; /* Use count */ struct super_block *dq_sb; /* superblock this applies to */ struct kqid dq_id; /* ID this applies to (uid, gid, projid) */ loff_t dq_off; /* Offset of dquot on disk [dq_lock, stable once set] */ unsigned long dq_flags; /* See DQ_* */ struct mem_dqblk dq_dqb; /* Diskquota usage [dq_dqb_lock] */ }; /* Operations which must be implemented by each quota format */ struct quota_format_ops { int (*check_quota_file)(struct super_block *sb, int type); /* Detect whether file is in our format */ int (*read_file_info)(struct super_block *sb, int type); /* Read main info about file - called on quotaon() */ int (*write_file_info)(struct super_block *sb, int type); /* Write main info about file */ int (*free_file_info)(struct super_block *sb, int type); /* Called on quotaoff() */ int (*read_dqblk)(struct dquot *dquot); /* Read structure for one user */ int (*commit_dqblk)(struct dquot *dquot); /* Write structure for one user */ int (*release_dqblk)(struct dquot *dquot); /* Called when last reference to dquot is being dropped */ int (*get_next_id)(struct super_block *sb, struct kqid *qid); /* Get next ID with existing structure in the quota file */ }; /* Operations working with dquots */ struct dquot_operations { int (*write_dquot) (struct dquot *); /* Ordinary dquot write */ struct dquot *(*alloc_dquot)(struct super_block *, int); /* Allocate memory for new dquot */ void (*destroy_dquot)(struct dquot *); /* Free memory for dquot */ int (*acquire_dquot) (struct dquot *); /* Quota is going to be created on disk */ int (*release_dquot) (struct dquot *); /* Quota is going to be deleted from disk */ int (*mark_dirty) (struct dquot *); /* Dquot is marked dirty */ int (*write_info) (struct super_block *, int); /* Write of quota "superblock" */ /* get reserved quota for delayed alloc, value returned is managed by * quota code only */ qsize_t *(*get_reserved_space) (struct inode *); int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */ /* Get number of inodes that were charged for a given inode */ int (*get_inode_usage) (struct inode *, qsize_t *); /* Get next ID with active quota structure */ int (*get_next_id) (struct super_block *sb, struct kqid *qid); }; struct path; /* Structure for communicating via ->get_dqblk() & ->set_dqblk() */ struct qc_dqblk { int d_fieldmask; /* mask of fields to change in ->set_dqblk() */ u64 d_spc_hardlimit; /* absolute limit on used space */ u64 d_spc_softlimit; /* preferred limit on used space */ u64 d_ino_hardlimit; /* maximum # allocated inodes */ u64 d_ino_softlimit; /* preferred inode limit */ u64 d_space; /* Space owned by the user */ u64 d_ino_count; /* # inodes owned by the user */ s64 d_ino_timer; /* zero if within inode limits */ /* if not, we refuse service */ s64 d_spc_timer; /* similar to above; for space */ int d_ino_warns; /* # warnings issued wrt num inodes */ int d_spc_warns; /* # warnings issued wrt used space */ u64 d_rt_spc_hardlimit; /* absolute limit on realtime space */ u64 d_rt_spc_softlimit; /* preferred limit on RT space */ u64 d_rt_space; /* realtime space owned */ s64 d_rt_spc_timer; /* similar to above; for RT space */ int d_rt_spc_warns; /* # warnings issued wrt RT space */ }; /* * Field specifiers for ->set_dqblk() in struct qc_dqblk and also for * ->set_info() in struct qc_info */ #define QC_INO_SOFT (1<<0) #define QC_INO_HARD (1<<1) #define QC_SPC_SOFT (1<<2) #define QC_SPC_HARD (1<<3) #define QC_RT_SPC_SOFT (1<<4) #define QC_RT_SPC_HARD (1<<5) #define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \ QC_RT_SPC_SOFT | QC_RT_SPC_HARD) #define QC_SPC_TIMER (1<<6) #define QC_INO_TIMER (1<<7) #define QC_RT_SPC_TIMER (1<<8) #define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER) #define QC_SPC_WARNS (1<<9) #define QC_INO_WARNS (1<<10) #define QC_RT_SPC_WARNS (1<<11) #define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS) #define QC_SPACE (1<<12) #define QC_INO_COUNT (1<<13) #define QC_RT_SPACE (1<<14) #define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE) #define QC_FLAGS (1<<15) #define QCI_SYSFILE (1 << 0) /* Quota file is hidden from userspace */ #define QCI_ROOT_SQUASH (1 << 1) /* Root squash turned on */ #define QCI_ACCT_ENABLED (1 << 2) /* Quota accounting enabled */ #define QCI_LIMITS_ENFORCED (1 << 3) /* Quota limits enforced */ /* Structures for communicating via ->get_state */ struct qc_type_state { unsigned int flags; /* Flags QCI_* */ unsigned int spc_timelimit; /* Time after which space softlimit is * enforced */ unsigned int ino_timelimit; /* Ditto for inode softlimit */ unsigned int rt_spc_timelimit; /* Ditto for real-time space */ unsigned int spc_warnlimit; /* Limit for number of space warnings */ unsigned int ino_warnlimit; /* Ditto for inodes */ unsigned int rt_spc_warnlimit; /* Ditto for real-time space */ unsigned long long ino; /* Inode number of quota file */ blkcnt_t blocks; /* Number of 512-byte blocks in the file */ blkcnt_t nextents; /* Number of extents in the file */ }; struct qc_state { unsigned int s_incoredqs; /* Number of dquots in core */ struct qc_type_state s_state[MAXQUOTAS]; /* Per quota type information */ }; /* Structure for communicating via ->set_info */ struct qc_info { int i_fieldmask; /* mask of fields to change in ->set_info() */ unsigned int i_flags; /* Flags QCI_* */ unsigned int i_spc_timelimit; /* Time after which space softlimit is * enforced */ unsigned int i_ino_timelimit; /* Ditto for inode softlimit */ unsigned int i_rt_spc_timelimit;/* Ditto for real-time space */ unsigned int i_spc_warnlimit; /* Limit for number of space warnings */ unsigned int i_ino_warnlimit; /* Limit for number of inode warnings */ unsigned int i_rt_spc_warnlimit; /* Ditto for real-time space */ }; /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, const struct path *); int (*quota_off)(struct super_block *, int); int (*quota_enable)(struct super_block *, unsigned int); int (*quota_disable)(struct super_block *, unsigned int); int (*quota_sync)(struct super_block *, int); int (*set_info)(struct super_block *, int, struct qc_info *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_nextdqblk)(struct super_block *, struct kqid *, struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_state)(struct super_block *, struct qc_state *); int (*rm_xquota)(struct super_block *, unsigned int); }; struct quota_format_type { int qf_fmt_id; /* Quota format id */ const struct quota_format_ops *qf_ops; /* Operations of format */ struct module *qf_owner; /* Module implementing quota format */ struct quota_format_type *qf_next; }; /** * Quota state flags - they actually come in two flavors - for users and groups. * * Actual typed flags layout: * USRQUOTA GRPQUOTA * DQUOT_USAGE_ENABLED 0x0001 0x0002 * DQUOT_LIMITS_ENABLED 0x0004 0x0008 * DQUOT_SUSPENDED 0x0010 0x0020 * * Following bits are used for non-typed flags: * DQUOT_QUOTA_SYS_FILE 0x0040 * DQUOT_NEGATIVE_USAGE 0x0080 */ enum { _DQUOT_USAGE_ENABLED = 0, /* Track disk usage for users */ _DQUOT_LIMITS_ENABLED, /* Enforce quota limits for users */ _DQUOT_SUSPENDED, /* User diskquotas are off, but * we have necessary info in * memory to turn them on */ _DQUOT_STATE_FLAGS }; #define DQUOT_USAGE_ENABLED (1 << _DQUOT_USAGE_ENABLED * MAXQUOTAS) #define DQUOT_LIMITS_ENABLED (1 << _DQUOT_LIMITS_ENABLED * MAXQUOTAS) #define DQUOT_SUSPENDED (1 << _DQUOT_SUSPENDED * MAXQUOTAS) #define DQUOT_STATE_FLAGS (DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED | \ DQUOT_SUSPENDED) /* Other quota flags */ #define DQUOT_STATE_LAST (_DQUOT_STATE_FLAGS * MAXQUOTAS) #define DQUOT_QUOTA_SYS_FILE (1 << DQUOT_STATE_LAST) /* Quota file is a special * system file and user cannot * touch it. Filesystem is * responsible for setting * S_NOQUOTA, S_NOATIME flags */ #define DQUOT_NEGATIVE_USAGE (1 << (DQUOT_STATE_LAST + 1)) /* Allow negative quota usage */ /* Do not track dirty dquots in a list */ #define DQUOT_NOLIST_DIRTY (1 << (DQUOT_STATE_LAST + 2)) static inline unsigned int dquot_state_flag(unsigned int flags, int type) { return flags << type; } static inline unsigned int dquot_generic_flag(unsigned int flags, int type) { return (flags >> type) & DQUOT_STATE_FLAGS; } /* Bitmap of quota types where flag is set in flags */ static __always_inline unsigned dquot_state_types(unsigned flags, unsigned flag) { BUILD_BUG_ON_NOT_POWER_OF_2(flag); return (flags / flag) & ((1 << MAXQUOTAS) - 1); } #ifdef CONFIG_QUOTA_NETLINK_INTERFACE extern void quota_send_warning(struct kqid qid, dev_t dev, const char warntype); #else static inline void quota_send_warning(struct kqid qid, dev_t dev, const char warntype) { return; } #endif /* CONFIG_QUOTA_NETLINK_INTERFACE */ struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ struct rw_semaphore dqio_sem; /* Lock quota file while I/O in progress */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; int register_quota_format(struct quota_format_type *fmt); void unregister_quota_format(struct quota_format_type *fmt); struct quota_module_name { int qm_fmt_id; char *qm_mod_name; }; #define INIT_QUOTA_MODULE_NAMES {\ {QFMT_VFS_OLD, "quota_v1"},\ {QFMT_VFS_V0, "quota_v2"},\ {QFMT_VFS_V1, "quota_v2"},\ {0, NULL}} #endif /* _QUOTA_ */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H #ifdef __KERNEL__ #include <asm/nops.h> #include <asm/processor-flags.h> #include <linux/irqflags.h> #include <linux/jump_label.h> /* * The compiler should not reorder volatile asm statements with respect to each * other: they should execute in program order. However GCC 4.9.x and 5.x have * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder * volatile asm. The write functions are not affected since they have memory * clobbers preventing reordering. To prevent reads from being reordered with * respect to writes, use a dummy memory operand. */ #define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL) void native_write_cr0(unsigned long val); static inline unsigned long native_read_cr0(void) { unsigned long val; asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline unsigned long native_read_cr2(void) { unsigned long val; asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline void native_write_cr2(unsigned long val) { asm volatile("mov %0,%%cr2": : "r" (val) : "memory"); } static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static inline void native_write_cr3(unsigned long val) { asm volatile("mov %0,%%cr3": : "r" (val) : "memory"); } static inline unsigned long native_read_cr4(void) { unsigned long val; #ifdef CONFIG_X86_32 /* * This could fault if CR4 does not exist. Non-existent CR4 * is functionally equivalent to CR4 == 0. Keep it simple and pretend * that CR4 == 0 on CPUs that don't have CR4. */ asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) : "=r" (val) : "0" (0), __FORCE_ORDER); #else /* CR4 always exists on x86_64. */ asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER); #endif return val; } void native_write_cr4(unsigned long val); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline u32 rdpkru(void) { u32 ecx = 0; u32 edx, pkru; /* * "rdpkru" instruction. Places PKRU contents in to EAX, * clears EDX and requires that ecx=0. */ asm volatile(".byte 0x0f,0x01,0xee\n\t" : "=a" (pkru), "=d" (edx) : "c" (ecx)); return pkru; } static inline void wrpkru(u32 pkru) { u32 ecx = 0, edx = 0; /* * "wrpkru" instruction. Loads contents in EAX to PKRU, * requires that ecx = edx = 0. */ asm volatile(".byte 0x0f,0x01,0xef\n\t" : : "a" (pkru), "c"(ecx), "d"(edx)); } static inline void __write_pkru(u32 pkru) { /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru == rdpkru()) return; wrpkru(pkru); } #else static inline u32 rdpkru(void) { return 0; } static inline void __write_pkru(u32 pkru) { } #endif static inline void native_wbinvd(void) { asm volatile("wbinvd": : :"memory"); } extern asmlinkage void asm_load_gs_index(unsigned int selector); static inline void native_load_gs_index(unsigned int selector) { unsigned long flags; local_irq_save(flags); asm_load_gs_index(selector); local_irq_restore(flags); } static inline unsigned long __read_cr4(void) { return native_read_cr4(); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else static inline unsigned long read_cr0(void) { return native_read_cr0(); } static inline void write_cr0(unsigned long x) { native_write_cr0(x); } static __always_inline unsigned long read_cr2(void) { return native_read_cr2(); } static __always_inline void write_cr2(unsigned long x) { native_write_cr2(x); } /* * Careful! CR3 contains more than just an address. You probably want * read_cr3_pa() instead. */ static inline unsigned long __read_cr3(void) { return __native_read_cr3(); } static inline void write_cr3(unsigned long x) { native_write_cr3(x); } static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } static inline void wbinvd(void) { native_wbinvd(); } #ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int selector) { native_load_gs_index(selector); } #endif #endif /* CONFIG_PARAVIRT_XXL */ static inline void clflush(volatile void *__p) { asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); } static inline void clflushopt(volatile void *__p) { alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0", ".byte 0x66; clflush %P0", X86_FEATURE_CLFLUSHOPT, "+m" (*(volatile char __force *)__p)); } static inline void clwb(volatile void *__p) { volatile struct { char x[64]; } *p = __p; asm volatile(ALTERNATIVE_2( ".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])", ".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */ X86_FEATURE_CLFLUSHOPT, ".byte 0x66, 0x0f, 0xae, 0x30", /* clwb (%%rax) */ X86_FEATURE_CLWB) : [p] "+m" (*p) : [pax] "a" (p)); } #define nop() asm volatile ("nop") static inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); } /* The dst parameter must be 64-bytes aligned */ static inline void movdir64b(void *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. * * Both __src and __dst must be memory constraints in order to tell the * compiler that no other memory accesses should be reordered around * this one. * * Also, both must be supplied as lvalues because this tells * the compiler what the object is (its size) the instruction accesses. * I.e., not the pointers but what they point to, thus the deref'ing '*'. */ asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" : "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); } /** * enqcmds - Enqueue a command in supervisor (CPL0) mode * @dst: destination, in MMIO space (must be 512-bit aligned) * @src: 512 bits memory operand * * The ENQCMDS instruction allows software to write a 512-bit command to * a 512-bit-aligned special MMIO region that supports the instruction. * A return status is loaded into the ZF flag in the RFLAGS register. * ZF = 0 equates to success, and ZF = 1 indicates retry or error. * * This function issues the ENQCMDS instruction to submit data from * kernel space to MMIO space, in a unit of 512 bits. Order of data access * is not guaranteed, nor is a memory barrier performed afterwards. It * returns 0 on success and -EAGAIN on failure. * * Warning: Do not use this helper unless your driver has checked that the * ENQCMDS instruction is supported on the platform and the device accepts * ENQCMDS. */ static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } __iomem *__dst = dst; bool zf; /* * ENQCMDS %(rdx), rax * * See movdir64b()'s comment on operand specification. */ asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90" CC_SET(z) : CC_OUT(z) (zf), "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); /* Submission failure is indicated via EFLAGS.ZF=1 */ if (zf) return -EAGAIN; return 0; } #endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/mballoc.h * * Written by: Alex Tomas <alex@clusterfs.com> * */ #ifndef _EXT4_MBALLOC_H #define _EXT4_MBALLOC_H #include <linux/time.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include <linux/module.h> #include <linux/swap.h> #include <linux/proc_fs.h> #include <linux/pagemap.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include <linux/mutex.h> #include "ext4_jbd2.h" #include "ext4.h" /* * mb_debug() dynamic printk msgs could be used to debug mballoc code. */ #ifdef CONFIG_EXT4_DEBUG #define mb_debug(sb, fmt, ...) \ pr_debug("[%s/%d] EXT4-fs (%s): (%s, %d): %s: " fmt, \ current->comm, task_pid_nr(current), sb->s_id, \ __FILE__, __LINE__, __func__, ##__VA_ARGS__) #else #define mb_debug(sb, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif #define EXT4_MB_HISTORY_ALLOC 1 /* allocation */ #define EXT4_MB_HISTORY_PREALLOC 2 /* preallocated blocks used */ /* * How long mballoc can look for a best extent (in found extents) */ #define MB_DEFAULT_MAX_TO_SCAN 200 /* * How long mballoc must look for a best extent */ #define MB_DEFAULT_MIN_TO_SCAN 10 /* * with 'ext4_mb_stats' allocator will collect stats that will be * shown at umount. The collecting costs though! */ #define MB_DEFAULT_STATS 0 /* * files smaller than MB_DEFAULT_STREAM_THRESHOLD are served * by the stream allocator, which purpose is to pack requests * as close each to other as possible to produce smooth I/O traffic * We use locality group prealloc space for stream request. * We can tune the same via /proc/fs/ext4/<parition>/stream_req */ #define MB_DEFAULT_STREAM_THRESHOLD 16 /* 64K */ /* * for which requests use 2^N search using buddies */ #define MB_DEFAULT_ORDER2_REQS 2 /* * default group prealloc size 512 blocks */ #define MB_DEFAULT_GROUP_PREALLOC 512 /* * maximum length of inode prealloc list */ #define MB_DEFAULT_MAX_INODE_PREALLOC 512 struct ext4_free_data { /* this links the free block information from sb_info */ struct list_head efd_list; /* this links the free block information from group_info */ struct rb_node efd_node; /* group which free block extent belongs */ ext4_group_t efd_group; /* free block extent */ ext4_grpblk_t efd_start_cluster; ext4_grpblk_t efd_count; /* transaction which freed this extent */ tid_t efd_tid; }; struct ext4_prealloc_space { struct list_head pa_inode_list; struct list_head pa_group_list; union { struct list_head pa_tmp_list; struct rcu_head pa_rcu; } u; spinlock_t pa_lock; atomic_t pa_count; unsigned pa_deleted; ext4_fsblk_t pa_pstart; /* phys. block */ ext4_lblk_t pa_lstart; /* log. block */ ext4_grpblk_t pa_len; /* len of preallocated chunk */ ext4_grpblk_t pa_free; /* how many blocks are free */ unsigned short pa_type; /* pa type. inode or group */ spinlock_t *pa_obj_lock; struct inode *pa_inode; /* hack, for history only */ }; enum { MB_INODE_PA = 0, MB_GROUP_PA = 1 }; struct ext4_free_extent { ext4_lblk_t fe_logical; ext4_grpblk_t fe_start; /* In cluster units */ ext4_group_t fe_group; ext4_grpblk_t fe_len; /* In cluster units */ }; /* * Locality group: * we try to group all related changes together * so that writeback can flush/allocate them together as well * Size of lg_prealloc_list hash is determined by MB_DEFAULT_GROUP_PREALLOC * (512). We store prealloc space into the hash based on the pa_free blocks * order value.ie, fls(pa_free)-1; */ #define PREALLOC_TB_SIZE 10 struct ext4_locality_group { /* for allocator */ /* to serialize allocates */ struct mutex lg_mutex; /* list of preallocations */ struct list_head lg_prealloc_list[PREALLOC_TB_SIZE]; spinlock_t lg_prealloc_lock; }; struct ext4_allocation_context { struct inode *ac_inode; struct super_block *ac_sb; /* original request */ struct ext4_free_extent ac_o_ex; /* goal request (normalized ac_o_ex) */ struct ext4_free_extent ac_g_ex; /* the best found extent */ struct ext4_free_extent ac_b_ex; /* copy of the best found extent taken before preallocation efforts */ struct ext4_free_extent ac_f_ex; __u16 ac_groups_scanned; __u16 ac_found; __u16 ac_tail; __u16 ac_buddy; __u16 ac_flags; /* allocation hints */ __u8 ac_status; __u8 ac_criteria; __u8 ac_2order; /* if request is to allocate 2^N blocks and * N > 0, the field stores N, otherwise 0 */ __u8 ac_op; /* operation, for history only */ struct page *ac_bitmap_page; struct page *ac_buddy_page; struct ext4_prealloc_space *ac_pa; struct ext4_locality_group *ac_lg; }; #define AC_STATUS_CONTINUE 1 #define AC_STATUS_FOUND 2 #define AC_STATUS_BREAK 3 struct ext4_buddy { struct page *bd_buddy_page; void *bd_buddy; struct page *bd_bitmap_page; void *bd_bitmap; struct ext4_group_info *bd_info; struct super_block *bd_sb; __u16 bd_blkbits; ext4_group_t bd_group; }; static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb, struct ext4_free_extent *fex) { return ext4_group_first_block_no(sb, fex->fe_group) + (fex->fe_start << EXT4_SB(sb)->s_cluster_bits); } typedef int (*ext4_mballoc_query_range_fn)( struct super_block *sb, ext4_group_t agno, ext4_grpblk_t start, ext4_grpblk_t len, void *priv); int ext4_mballoc_query_range( struct super_block *sb, ext4_group_t agno, ext4_grpblk_t start, ext4_grpblk_t end, ext4_mballoc_query_range_fn formatter, void *priv); #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TLB_H #define _ASM_X86_TLB_H #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> static inline void tlb_flush(struct mmu_gather *tlb) { unsigned long start = 0UL, end = TLB_FLUSH_ALL; unsigned int stride_shift = tlb_get_unmap_shift(tlb); if (!tlb->fullmm && !tlb->need_flush_all) { start = tlb->start; end = tlb->end; } flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); } /* * While x86 architecture in general requires an IPI to perform TLB * shootdown, enablement code for several hypervisors overrides * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing * a hypercall. To keep software pagetable walkers safe in this case we * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h * for more details. */ static inline void __tlb_remove_table(void *table) { free_page_and_swap_cache(table); } #endif /* _ASM_X86_TLB_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ICMPV6_H #define _LINUX_ICMPV6_H #include <linux/skbuff.h> #include <linux/ipv6.h> #include <uapi/linux/icmpv6.h> static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) { return (struct icmp6hdr *)skb_transport_header(skb); } #include <linux/netdevice.h> #if IS_ENABLED(CONFIG_IPV6) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct inet6_skb_parm *parm) { icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { BUILD_BUG_ON(fn != icmp6_send); return 0; } static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) { BUILD_BUG_ON(fn != icmp6_send); return 0; } #else extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { __icmpv6_send(skb, type, code, info, IP6CB(skb)); } int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { struct inet6_skb_parm parm = { 0 }; __icmpv6_send(skb_in, type, code, info, &parm); } #endif #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } static inline void icmpv6_ndo_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } #endif extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); extern void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos); struct flowi6; struct in6_addr; extern void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif); static inline bool icmpv6_is_err(int type) { switch (type) { case ICMPV6_DEST_UNREACH: case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: return true; } return false; } #endif
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 // SPDX-License-Identifier: GPL-2.0+ /* * linux/fs/jbd2/revoke.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 2000 * * Copyright 2000 Red Hat corp --- All Rights Reserved * * Journal revoke routines for the generic filesystem journaling code; * part of the ext2fs journaling system. * * Revoke is the mechanism used to prevent old log records for deleted * metadata from being replayed on top of newer data using the same * blocks. The revoke mechanism is used in two separate places: * * + Commit: during commit we write the entire list of the current * transaction's revoked blocks to the journal * * + Recovery: during recovery we record the transaction ID of all * revoked blocks. If there are multiple revoke records in the log * for a single block, only the last one counts, and if there is a log * entry for a block beyond the last revoke, then that log entry still * gets replayed. * * We can get interactions between revokes and new log data within a * single transaction: * * Block is revoked and then journaled: * The desired end result is the journaling of the new block, so we * cancel the revoke before the transaction commits. * * Block is journaled and then revoked: * The revoke must take precedence over the write of the block, so we * need either to cancel the journal entry or to write the revoke * later in the log than the log block. In this case, we choose the * latter: journaling a block cancels any revoke record for that block * in the current transaction, so any revoke for that block in the * transaction must have happened after the block was journaled and so * the revoke must take precedence. * * Block is revoked and then written as data: * The data write is allowed to succeed, but the revoke is _not_ * cancelled. We still need to prevent old log records from * overwriting the new data. We don't even need to clear the revoke * bit here. * * We cache revoke status of a buffer in the current transaction in b_states * bits. As the name says, revokevalid flag indicates that the cached revoke * status of a buffer is valid and we can rely on the cached status. * * Revoke information on buffers is a tri-state value: * * RevokeValid clear: no cached revoke status, need to look it up * RevokeValid set, Revoked clear: * buffer has not been revoked, and cancel_revoke * need do nothing. * RevokeValid set, Revoked set: * buffer has been revoked. * * Locking rules: * We keep two hash tables of revoke records. One hashtable belongs to the * running transaction (is pointed to by journal->j_revoke), the other one * belongs to the committing transaction. Accesses to the second hash table * happen only from the kjournald and no other thread touches this table. Also * journal_switch_revoke_table() which switches which hashtable belongs to the * running and which to the committing transaction is called only from * kjournald. Therefore we need no locks when accessing the hashtable belonging * to the committing transaction. * * All users operating on the hash table belonging to the running transaction * have a handle to the transaction. Therefore they are safe from kjournald * switching hash tables under them. For operations on the lists of entries in * the hash table j_revoke_lock is used. * * Finally, also replay code uses the hash tables but at this moment no one else * can touch them (filesystem isn't mounted yet) and hence no locking is * needed. */ #ifndef __KERNEL__ #include "jfs_user.h" #else #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/log2.h> #include <linux/hash.h> #endif static struct kmem_cache *jbd2_revoke_record_cache; static struct kmem_cache *jbd2_revoke_table_cache; /* Each revoke record represents one single revoked block. During journal replay, this involves recording the transaction ID of the last transaction to revoke this block. */ struct jbd2_revoke_record_s { struct list_head hash; tid_t sequence; /* Used for recovery only */ unsigned long long blocknr; }; /* The revoke table is just a simple hash table of revoke records. */ struct jbd2_revoke_table_s { /* It is conceivable that we might want a larger hash table * for recovery. Must be a power of two. */ int hash_size; int hash_shift; struct list_head *hash_table; }; #ifdef __KERNEL__ static void write_one_revoke_record(transaction_t *, struct list_head *, struct buffer_head **, int *, struct jbd2_revoke_record_s *); static void flush_descriptor(journal_t *, struct buffer_head *, int); #endif /* Utility functions to maintain the revoke table */ static inline int hash(journal_t *journal, unsigned long long block) { return hash_64(block, journal->j_revoke->hash_shift); } static int insert_revoke_hash(journal_t *journal, unsigned long long blocknr, tid_t seq) { struct list_head *hash_list; struct jbd2_revoke_record_s *record; gfp_t gfp_mask = GFP_NOFS; if (journal_oom_retry) gfp_mask |= __GFP_NOFAIL; record = kmem_cache_alloc(jbd2_revoke_record_cache, gfp_mask); if (!record) return -ENOMEM; record->sequence = seq; record->blocknr = blocknr; hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)]; spin_lock(&journal->j_revoke_lock); list_add(&record->hash, hash_list); spin_unlock(&journal->j_revoke_lock); return 0; } /* Find a revoke record in the journal's hash table. */ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal, unsigned long long blocknr) { struct list_head *hash_list; struct jbd2_revoke_record_s *record; hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)]; spin_lock(&journal->j_revoke_lock); record = (struct jbd2_revoke_record_s *) hash_list->next; while (&(record->hash) != hash_list) { if (record->blocknr == blocknr) { spin_unlock(&journal->j_revoke_lock); return record; } record = (struct jbd2_revoke_record_s *) record->hash.next; } spin_unlock(&journal->j_revoke_lock); return NULL; } void jbd2_journal_destroy_revoke_record_cache(void) { kmem_cache_destroy(jbd2_revoke_record_cache); jbd2_revoke_record_cache = NULL; } void jbd2_journal_destroy_revoke_table_cache(void) { kmem_cache_destroy(jbd2_revoke_table_cache); jbd2_revoke_table_cache = NULL; } int __init jbd2_journal_init_revoke_record_cache(void) { J_ASSERT(!jbd2_revoke_record_cache); jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s, SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY); if (!jbd2_revoke_record_cache) { pr_emerg("JBD2: failed to create revoke_record cache\n"); return -ENOMEM; } return 0; } int __init jbd2_journal_init_revoke_table_cache(void) { J_ASSERT(!jbd2_revoke_table_cache); jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s, SLAB_TEMPORARY); if (!jbd2_revoke_table_cache) { pr_emerg("JBD2: failed to create revoke_table cache\n"); return -ENOMEM; } return 0; } static struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size) { int shift = 0; int tmp = hash_size; struct jbd2_revoke_table_s *table; table = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL); if (!table) goto out; while((tmp >>= 1UL) != 0UL) shift++; table->hash_size = hash_size; table->hash_shift = shift; table->hash_table = kmalloc_array(hash_size, sizeof(struct list_head), GFP_KERNEL); if (!table->hash_table) { kmem_cache_free(jbd2_revoke_table_cache, table); table = NULL; goto out; } for (tmp = 0; tmp < hash_size; tmp++) INIT_LIST_HEAD(&table->hash_table[tmp]); out: return table; } static void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table) { int i; struct list_head *hash_list; for (i = 0; i < table->hash_size; i++) { hash_list = &table->hash_table[i]; J_ASSERT(list_empty(hash_list)); } kfree(table->hash_table); kmem_cache_free(jbd2_revoke_table_cache, table); } /* Initialise the revoke table for a given journal to a given size. */ int jbd2_journal_init_revoke(journal_t *journal, int hash_size) { J_ASSERT(journal->j_revoke_table[0] == NULL); J_ASSERT(is_power_of_2(hash_size)); journal->j_revoke_table[0] = jbd2_journal_init_revoke_table(hash_size); if (!journal->j_revoke_table[0]) goto fail0; journal->j_revoke_table[1] = jbd2_journal_init_revoke_table(hash_size); if (!journal->j_revoke_table[1]) goto fail1; journal->j_revoke = journal->j_revoke_table[1]; spin_lock_init(&journal->j_revoke_lock); return 0; fail1: jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]); journal->j_revoke_table[0] = NULL; fail0: return -ENOMEM; } /* Destroy a journal's revoke table. The table must already be empty! */ void jbd2_journal_destroy_revoke(journal_t *journal) { journal->j_revoke = NULL; if (journal->j_revoke_table[0]) jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]); if (journal->j_revoke_table[1]) jbd2_journal_destroy_revoke_table(journal->j_revoke_table[1]); } #ifdef __KERNEL__ /* * jbd2_journal_revoke: revoke a given buffer_head from the journal. This * prevents the block from being replayed during recovery if we take a * crash after this current transaction commits. Any subsequent * metadata writes of the buffer in this transaction cancel the * revoke. * * Note that this call may block --- it is up to the caller to make * sure that there are no further calls to journal_write_metadata * before the revoke is complete. In ext3, this implies calling the * revoke before clearing the block bitmap when we are deleting * metadata. * * Revoke performs a jbd2_journal_forget on any buffer_head passed in as a * parameter, but does _not_ forget the buffer_head if the bh was only * found implicitly. * * bh_in may not be a journalled buffer - it may have come off * the hash tables without an attached journal_head. * * If bh_in is non-zero, jbd2_journal_revoke() will decrement its b_count * by one. */ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, struct buffer_head *bh_in) { struct buffer_head *bh = NULL; journal_t *journal; struct block_device *bdev; int err; might_sleep(); if (bh_in) BUFFER_TRACE(bh_in, "enter"); journal = handle->h_transaction->t_journal; if (!jbd2_journal_set_features(journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)){ J_ASSERT (!"Cannot set revoke feature!"); return -EINVAL; } bdev = journal->j_fs_dev; bh = bh_in; if (!bh) { bh = __find_get_block(bdev, blocknr, journal->j_blocksize); if (bh) BUFFER_TRACE(bh, "found on hash"); } #ifdef JBD2_EXPENSIVE_CHECKING else { struct buffer_head *bh2; /* If there is a different buffer_head lying around in * memory anywhere... */ bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize); if (bh2) { /* ... and it has RevokeValid status... */ if (bh2 != bh && buffer_revokevalid(bh2)) /* ...then it better be revoked too, * since it's illegal to create a revoke * record against a buffer_head which is * not marked revoked --- that would * risk missing a subsequent revoke * cancel. */ J_ASSERT_BH(bh2, buffer_revoked(bh2)); put_bh(bh2); } } #endif if (WARN_ON_ONCE(handle->h_revoke_credits <= 0)) { if (!bh_in) brelse(bh); return -EIO; } /* We really ought not ever to revoke twice in a row without first having the revoke cancelled: it's illegal to free a block twice without allocating it in between! */ if (bh) { if (!J_EXPECT_BH(bh, !buffer_revoked(bh), "inconsistent data on disk")) { if (!bh_in) brelse(bh); return -EIO; } set_buffer_revoked(bh); set_buffer_revokevalid(bh); if (bh_in) { BUFFER_TRACE(bh_in, "call jbd2_journal_forget"); jbd2_journal_forget(handle, bh_in); } else { BUFFER_TRACE(bh, "call brelse"); __brelse(bh); } } handle->h_revoke_credits--; jbd_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in); err = insert_revoke_hash(journal, blocknr, handle->h_transaction->t_tid); BUFFER_TRACE(bh_in, "exit"); return err; } /* * Cancel an outstanding revoke. For use only internally by the * journaling code (called from jbd2_journal_get_write_access). * * We trust buffer_revoked() on the buffer if the buffer is already * being journaled: if there is no revoke pending on the buffer, then we * don't do anything here. * * This would break if it were possible for a buffer to be revoked and * discarded, and then reallocated within the same transaction. In such * a case we would have lost the revoked bit, but when we arrived here * the second time we would still have a pending revoke to cancel. So, * do not trust the Revoked bit on buffers unless RevokeValid is also * set. */ int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh) { struct jbd2_revoke_record_s *record; journal_t *journal = handle->h_transaction->t_journal; int need_cancel; int did_revoke = 0; /* akpm: debug */ struct buffer_head *bh = jh2bh(jh); jbd_debug(4, "journal_head %p, cancelling revoke\n", jh); /* Is the existing Revoke bit valid? If so, we trust it, and * only perform the full cancel if the revoke bit is set. If * not, we can't trust the revoke bit, and we need to do the * full search for a revoke record. */ if (test_set_buffer_revokevalid(bh)) { need_cancel = test_clear_buffer_revoked(bh); } else { need_cancel = 1; clear_buffer_revoked(bh); } if (need_cancel) { record = find_revoke_record(journal, bh->b_blocknr); if (record) { jbd_debug(4, "cancelled existing revoke on " "blocknr %llu\n", (unsigned long long)bh->b_blocknr); spin_lock(&journal->j_revoke_lock); list_del(&record->hash); spin_unlock(&journal->j_revoke_lock); kmem_cache_free(jbd2_revoke_record_cache, record); did_revoke = 1; } } #ifdef JBD2_EXPENSIVE_CHECKING /* There better not be one left behind by now! */ record = find_revoke_record(journal, bh->b_blocknr); J_ASSERT_JH(jh, record == NULL); #endif /* Finally, have we just cleared revoke on an unhashed * buffer_head? If so, we'd better make sure we clear the * revoked status on any hashed alias too, otherwise the revoke * state machine will get very upset later on. */ if (need_cancel) { struct buffer_head *bh2; bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size); if (bh2) { if (bh2 != bh) clear_buffer_revoked(bh2); __brelse(bh2); } } return did_revoke; } /* * journal_clear_revoked_flag clears revoked flag of buffers in * revoke table to reflect there is no revoked buffers in the next * transaction which is going to be started. */ void jbd2_clear_buffer_revoked_flags(journal_t *journal) { struct jbd2_revoke_table_s *revoke = journal->j_revoke; int i = 0; for (i = 0; i < revoke->hash_size; i++) { struct list_head *hash_list; struct list_head *list_entry; hash_list = &revoke->hash_table[i]; list_for_each(list_entry, hash_list) { struct jbd2_revoke_record_s *record; struct buffer_head *bh; record = (struct jbd2_revoke_record_s *)list_entry; bh = __find_get_block(journal->j_fs_dev, record->blocknr, journal->j_blocksize); if (bh) { clear_buffer_revoked(bh); __brelse(bh); } } } } /* journal_switch_revoke table select j_revoke for next transaction * we do not want to suspend any processing until all revokes are * written -bzzz */ void jbd2_journal_switch_revoke_table(journal_t *journal) { int i; if (journal->j_revoke == journal->j_revoke_table[0]) journal->j_revoke = journal->j_revoke_table[1]; else journal->j_revoke = journal->j_revoke_table[0]; for (i = 0; i < journal->j_revoke->hash_size; i++) INIT_LIST_HEAD(&journal->j_revoke->hash_table[i]); } /* * Write revoke records to the journal for all entries in the current * revoke hash, deleting the entries as we go. */ void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs) { journal_t *journal = transaction->t_journal; struct buffer_head *descriptor; struct jbd2_revoke_record_s *record; struct jbd2_revoke_table_s *revoke; struct list_head *hash_list; int i, offset, count; descriptor = NULL; offset = 0; count = 0; /* select revoke table for committing transaction */ revoke = journal->j_revoke == journal->j_revoke_table[0] ? journal->j_revoke_table[1] : journal->j_revoke_table[0]; for (i = 0; i < revoke->hash_size; i++) { hash_list = &revoke->hash_table[i]; while (!list_empty(hash_list)) { record = (struct jbd2_revoke_record_s *) hash_list->next; write_one_revoke_record(transaction, log_bufs, &descriptor, &offset, record); count++; list_del(&record->hash); kmem_cache_free(jbd2_revoke_record_cache, record); } } if (descriptor) flush_descriptor(journal, descriptor, offset); jbd_debug(1, "Wrote %d revoke records\n", count); } /* * Write out one revoke record. We need to create a new descriptor * block if the old one is full or if we have not already created one. */ static void write_one_revoke_record(transaction_t *transaction, struct list_head *log_bufs, struct buffer_head **descriptorp, int *offsetp, struct jbd2_revoke_record_s *record) { journal_t *journal = transaction->t_journal; int csum_size = 0; struct buffer_head *descriptor; int sz, offset; /* If we are already aborting, this all becomes a noop. We still need to go round the loop in jbd2_journal_write_revoke_records in order to free all of the revoke records: only the IO to the journal is omitted. */ if (is_journal_aborted(journal)) return; descriptor = *descriptorp; offset = *offsetp; /* Do we need to leave space at the end for a checksum? */ if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_block_tail); if (jbd2_has_feature_64bit(journal)) sz = 8; else sz = 4; /* Make sure we have a descriptor with space left for the record */ if (descriptor) { if (offset + sz > journal->j_blocksize - csum_size) { flush_descriptor(journal, descriptor, offset); descriptor = NULL; } } if (!descriptor) { descriptor = jbd2_journal_get_descriptor_buffer(transaction, JBD2_REVOKE_BLOCK); if (!descriptor) return; /* Record it so that we can wait for IO completion later */ BUFFER_TRACE(descriptor, "file in log_bufs"); jbd2_file_log_bh(log_bufs, descriptor); offset = sizeof(jbd2_journal_revoke_header_t); *descriptorp = descriptor; } if (jbd2_has_feature_64bit(journal)) * ((__be64 *)(&descriptor->b_data[offset])) = cpu_to_be64(record->blocknr); else * ((__be32 *)(&descriptor->b_data[offset])) = cpu_to_be32(record->blocknr); offset += sz; *offsetp = offset; } /* * Flush a revoke descriptor out to the journal. If we are aborting, * this is a noop; otherwise we are generating a buffer which needs to * be waited for during commit, so it has to go onto the appropriate * journal buffer list. */ static void flush_descriptor(journal_t *journal, struct buffer_head *descriptor, int offset) { jbd2_journal_revoke_header_t *header; if (is_journal_aborted(journal)) return; header = (jbd2_journal_revoke_header_t *)descriptor->b_data; header->r_count = cpu_to_be32(offset); jbd2_descriptor_block_csum_set(journal, descriptor); set_buffer_jwrite(descriptor); BUFFER_TRACE(descriptor, "write"); set_buffer_dirty(descriptor); write_dirty_buffer(descriptor, REQ_SYNC); } #endif /* * Revoke support for recovery. * * Recovery needs to be able to: * * record all revoke records, including the tid of the latest instance * of each revoke in the journal * * check whether a given block in a given transaction should be replayed * (ie. has not been revoked by a revoke record in that or a subsequent * transaction) * * empty the revoke table after recovery. */ /* * First, setting revoke records. We create a new revoke record for * every block ever revoked in the log as we scan it for recovery, and * we update the existing records if we find multiple revokes for a * single block. */ int jbd2_journal_set_revoke(journal_t *journal, unsigned long long blocknr, tid_t sequence) { struct jbd2_revoke_record_s *record; record = find_revoke_record(journal, blocknr); if (record) { /* If we have multiple occurrences, only record the * latest sequence number in the hashed record */ if (tid_gt(sequence, record->sequence)) record->sequence = sequence; return 0; } return insert_revoke_hash(journal, blocknr, sequence); } /* * Test revoke records. For a given block referenced in the log, has * that block been revoked? A revoke record with a given transaction * sequence number revokes all blocks in that transaction and earlier * ones, but later transactions still need replayed. */ int jbd2_journal_test_revoke(journal_t *journal, unsigned long long blocknr, tid_t sequence) { struct jbd2_revoke_record_s *record; record = find_revoke_record(journal, blocknr); if (!record) return 0; if (tid_gt(sequence, record->sequence)) return 0; return 1; } /* * Finally, once recovery is over, we need to clear the revoke table so * that it can be reused by the running filesystem. */ void jbd2_journal_clear_revoke(journal_t *journal) { int i; struct list_head *hash_list; struct jbd2_revoke_record_s *record; struct jbd2_revoke_table_s *revoke; revoke = journal->j_revoke; for (i = 0; i < revoke->hash_size; i++) { hash_list = &revoke->hash_table[i]; while (!list_empty(hash_list)) { record = (struct jbd2_revoke_record_s*) hash_list->next; list_del(&record->hash); kmem_cache_free(jbd2_revoke_record_cache, record); } } }
1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 // SPDX-License-Identifier: GPL-2.0 /* * Functions related to io context handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/sched/task.h> #include "blk.h" /* * For io context allocations */ static struct kmem_cache *iocontext_cachep; /** * get_io_context - increment reference count to io_context * @ioc: io_context to get * * Increment reference count to @ioc. */ void get_io_context(struct io_context *ioc) { BUG_ON(atomic_long_read(&ioc->refcount) <= 0); atomic_long_inc(&ioc->refcount); } static void icq_free_icq_rcu(struct rcu_head *head) { struct io_cq *icq = container_of(head, struct io_cq, __rcu_head); kmem_cache_free(icq->__rcu_icq_cache, icq); } /* * Exit an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_exit_icq(struct io_cq *icq) { struct elevator_type *et = icq->q->elevator->type; if (icq->flags & ICQ_EXITED) return; if (et->ops.exit_icq) et->ops.exit_icq(icq); icq->flags |= ICQ_EXITED; } /* * Release an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_destroy_icq(struct io_cq *icq) { struct io_context *ioc = icq->ioc; struct request_queue *q = icq->q; struct elevator_type *et = q->elevator->type; lockdep_assert_held(&ioc->lock); radix_tree_delete(&ioc->icq_tree, icq->q->id); hlist_del_init(&icq->ioc_node); list_del_init(&icq->q_node); /* * Both setting lookup hint to and clearing it from @icq are done * under queue_lock. If it's not pointing to @icq now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(ioc->icq_hint) == icq) rcu_assign_pointer(ioc->icq_hint, NULL); ioc_exit_icq(icq); /* * @icq->q might have gone away by the time RCU callback runs * making it impossible to determine icq_cache. Record it in @icq. */ icq->__rcu_icq_cache = et->icq_cache; icq->flags |= ICQ_DESTROYED; call_rcu(&icq->__rcu_head, icq_free_icq_rcu); } /* * Slow path for ioc release in put_io_context(). Performs double-lock * dancing to unlink all icq's and then frees ioc. */ static void ioc_release_fn(struct work_struct *work) { struct io_context *ioc = container_of(work, struct io_context, release_work); spin_lock_irq(&ioc->lock); while (!hlist_empty(&ioc->icq_list)) { struct io_cq *icq = hlist_entry(ioc->icq_list.first, struct io_cq, ioc_node); struct request_queue *q = icq->q; if (spin_trylock(&q->queue_lock)) { ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); } else { /* Make sure q and icq cannot be freed. */ rcu_read_lock(); /* Re-acquire the locks in the correct order. */ spin_unlock(&ioc->lock); spin_lock(&q->queue_lock); spin_lock(&ioc->lock); /* * The icq may have been destroyed when the ioc lock * was released. */ if (!(icq->flags & ICQ_DESTROYED)) ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); rcu_read_unlock(); } } spin_unlock_irq(&ioc->lock); kmem_cache_free(iocontext_cachep, ioc); } /** * put_io_context - put a reference of io_context * @ioc: io_context to put * * Decrement reference count of @ioc and release it if the count reaches * zero. */ void put_io_context(struct io_context *ioc) { unsigned long flags; bool free_ioc = false; if (ioc == NULL) return; BUG_ON(atomic_long_read(&ioc->refcount) <= 0); /* * Releasing ioc requires reverse order double locking and we may * already be holding a queue_lock. Do it asynchronously from wq. */ if (atomic_long_dec_and_test(&ioc->refcount)) { spin_lock_irqsave(&ioc->lock, flags); if (!hlist_empty(&ioc->icq_list)) queue_work(system_power_efficient_wq, &ioc->release_work); else free_ioc = true; spin_unlock_irqrestore(&ioc->lock, flags); } if (free_ioc) kmem_cache_free(iocontext_cachep, ioc); } /** * put_io_context_active - put active reference on ioc * @ioc: ioc of interest * * Undo get_io_context_active(). If active reference reaches zero after * put, @ioc can never issue further IOs and ioscheds are notified. */ void put_io_context_active(struct io_context *ioc) { struct io_cq *icq; if (!atomic_dec_and_test(&ioc->active_ref)) { put_io_context(ioc); return; } spin_lock_irq(&ioc->lock); hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) { if (icq->flags & ICQ_EXITED) continue; ioc_exit_icq(icq); } spin_unlock_irq(&ioc->lock); put_io_context(ioc); } /* Called by the exiting task */ void exit_io_context(struct task_struct *task) { struct io_context *ioc; task_lock(task); ioc = task->io_context; task->io_context = NULL; task_unlock(task); atomic_dec(&ioc->nr_tasks); put_io_context_active(ioc); } static void __ioc_clear_queue(struct list_head *icq_list) { unsigned long flags; rcu_read_lock(); while (!list_empty(icq_list)) { struct io_cq *icq = list_entry(icq_list->next, struct io_cq, q_node); struct io_context *ioc = icq->ioc; spin_lock_irqsave(&ioc->lock, flags); if (icq->flags & ICQ_DESTROYED) { spin_unlock_irqrestore(&ioc->lock, flags); continue; } ioc_destroy_icq(icq); spin_unlock_irqrestore(&ioc->lock, flags); } rcu_read_unlock(); } /** * ioc_clear_queue - break any ioc association with the specified queue * @q: request_queue being cleared * * Walk @q->icq_list and exit all io_cq's. */ void ioc_clear_queue(struct request_queue *q) { LIST_HEAD(icq_list); spin_lock_irq(&q->queue_lock); list_splice_init(&q->icq_list, &icq_list); spin_unlock_irq(&q->queue_lock); __ioc_clear_queue(&icq_list); } int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node) { struct io_context *ioc; int ret; ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO, node); if (unlikely(!ioc)) return -ENOMEM; /* initialize */ atomic_long_set(&ioc->refcount, 1); atomic_set(&ioc->nr_tasks, 1); atomic_set(&ioc->active_ref, 1); spin_lock_init(&ioc->lock); INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&ioc->icq_list); INIT_WORK(&ioc->release_work, ioc_release_fn); /* * Try to install. ioc shouldn't be installed if someone else * already did or @task, which isn't %current, is exiting. Note * that we need to allow ioc creation on exiting %current as exit * path may issue IOs from e.g. exit_files(). The exit path is * responsible for not issuing IO after exit_io_context(). */ task_lock(task); if (!task->io_context && (task == current || !(task->flags & PF_EXITING))) task->io_context = ioc; else kmem_cache_free(iocontext_cachep, ioc); ret = task->io_context ? 0 : -EBUSY; task_unlock(task); return ret; } /** * get_task_io_context - get io_context of a task * @task: task of interest * @gfp_flags: allocation flags, used if allocation is necessary * @node: allocation node, used if allocation is necessary * * Return io_context of @task. If it doesn't exist, it is created with * @gfp_flags and @node. The returned io_context has its reference count * incremented. * * This function always goes through task_lock() and it's better to use * %current->io_context + get_io_context() for %current. */ struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node) { struct io_context *ioc; might_sleep_if(gfpflags_allow_blocking(gfp_flags)); do { task_lock(task); ioc = task->io_context; if (likely(ioc)) { get_io_context(ioc); task_unlock(task); return ioc; } task_unlock(task); } while (!create_task_io_context(task, gfp_flags, node)); return NULL; } /** * ioc_lookup_icq - lookup io_cq from ioc * @ioc: the associated io_context * @q: the associated request_queue * * Look up io_cq associated with @ioc - @q pair from @ioc. Must be called * with @q->queue_lock held. */ struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q) { struct io_cq *icq; lockdep_assert_held(&q->queue_lock); /* * icq's are indexed from @ioc using radix tree and hint pointer, * both of which are protected with RCU. All removals are done * holding both q and ioc locks, and we're holding q lock - if we * find a icq which points to us, it's guaranteed to be valid. */ rcu_read_lock(); icq = rcu_dereference(ioc->icq_hint); if (icq && icq->q == q) goto out; icq = radix_tree_lookup(&ioc->icq_tree, q->id); if (icq && icq->q == q) rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */ else icq = NULL; out: rcu_read_unlock(); return icq; } EXPORT_SYMBOL(ioc_lookup_icq); /** * ioc_create_icq - create and link io_cq * @ioc: io_context of interest * @q: request_queue of interest * @gfp_mask: allocation mask * * Make sure io_cq linking @ioc and @q exists. If icq doesn't exist, they * will be created using @gfp_mask. * * The caller is responsible for ensuring @ioc won't go away and @q is * alive and will stay alive until this function returns. */ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, gfp_t gfp_mask) { struct elevator_type *et = q->elevator->type; struct io_cq *icq; /* allocate stuff */ icq = kmem_cache_alloc_node(et->icq_cache, gfp_mask | __GFP_ZERO, q->node); if (!icq) return NULL; if (radix_tree_maybe_preload(gfp_mask) < 0) { kmem_cache_free(et->icq_cache, icq); return NULL; } icq->ioc = ioc; icq->q = q; INIT_LIST_HEAD(&icq->q_node); INIT_HLIST_NODE(&icq->ioc_node); /* lock both q and ioc and try to link @icq */ spin_lock_irq(&q->queue_lock); spin_lock(&ioc->lock); if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { hlist_add_head(&icq->ioc_node, &ioc->icq_list); list_add(&icq->q_node, &q->icq_list); if (et->ops.init_icq) et->ops.init_icq(icq); } else { kmem_cache_free(et->icq_cache, icq); icq = ioc_lookup_icq(ioc, q); if (!icq) printk(KERN_ERR "cfq: icq link failed!\n"); } spin_unlock(&ioc->lock); spin_unlock_irq(&q->queue_lock); radix_tree_preload_end(); return icq; } static int __init blk_ioc_init(void) { iocontext_cachep = kmem_cache_create("blkdev_ioc", sizeof(struct io_context), 0, SLAB_PANIC, NULL); return 0; } subsys_initcall(blk_ioc_init);
1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 /* SPDX-License-Identifier: GPL-2.0-only */ /* * NSA Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <sds@tycho.nsa.gov> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include "flask.h" #include "avc.h" struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ } __randomize_layout; enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { struct super_block *sb; /* back pointer to sb object */ u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct *selinux_inode( const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct *selinux_msg_msg( const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct *selinux_ipc( const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } #endif /* _SELINUX_OBJSEC_H_ */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/file.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/file.c * * Copyright (C) 1991, 1992 Linus Torvalds * * ext4 fs regular file handling primitives * * 64-bit file support on 64-bit platforms by Jakub Jelinek * (jj@sunsite.ms.mff.cuni.cz) */ #include <linux/time.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mount.h> #include <linux/path.h> #include <linux/dax.h> #include <linux/quotaops.h> #include <linux/pagevec.h> #include <linux/uio.h> #include <linux/mman.h> #include <linux/backing-dev.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "truncate.h" static bool ext4_dio_supported(struct inode *inode) { if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode)) return false; if (fsverity_active(inode)) return false; if (ext4_should_journal_data(inode)) return false; if (ext4_has_inline_data(inode)) return false; return true; } static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) { ssize_t ret; struct inode *inode = file_inode(iocb->ki_filp); if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock_shared(inode)) return -EAGAIN; } else { inode_lock_shared(inode); } if (!ext4_dio_supported(inode)) { inode_unlock_shared(inode); /* * Fallback to buffered I/O if the operation being performed on * the inode is not supported by direct I/O. The IOCB_DIRECT * flag needs to be cleared here in order to ensure that the * direct I/O path within generic_file_read_iter() is not * taken. */ iocb->ki_flags &= ~IOCB_DIRECT; return generic_file_read_iter(iocb, to); } ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, is_sync_kiocb(iocb)); inode_unlock_shared(inode); file_accessed(iocb->ki_filp); return ret; } #ifdef CONFIG_FS_DAX static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock_shared(inode)) return -EAGAIN; } else { inode_lock_shared(inode); } /* * Recheck under inode lock - at this point we are sure it cannot * change anymore */ if (!IS_DAX(inode)) { inode_unlock_shared(inode); /* Fallback to buffered IO in case we cannot support DAX */ return generic_file_read_iter(iocb, to); } ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops); inode_unlock_shared(inode); file_accessed(iocb->ki_filp); return ret; } #endif static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; if (!iov_iter_count(to)) return 0; /* skip atime */ #ifdef CONFIG_FS_DAX if (IS_DAX(inode)) return ext4_dax_read_iter(iocb, to); #endif if (iocb->ki_flags & IOCB_DIRECT) return ext4_dio_read_iter(iocb, to); return generic_file_read_iter(iocb, to); } /* * Called when an inode is released. Note that this is different * from ext4_file_open: open gets called at every open, but release * gets called only when /all/ the files are closed. */ static int ext4_release_file(struct inode *inode, struct file *filp) { if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) { ext4_alloc_da_blocks(inode); ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); } /* if we are the last writer on the inode, drop the block reservation */ if ((filp->f_mode & FMODE_WRITE) && (atomic_read(&inode->i_writecount) == 1) && !EXT4_I(inode)->i_reserved_data_blocks) { down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); } if (is_dx(inode) && filp->private_data) ext4_htree_free_dir_info(filp->private_data); return 0; } /* * This tests whether the IO in question is block-aligned or not. * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they * are converted to written only after the IO is complete. Until they are * mapped, these blocks appear as holes, so dio_zero_block() will assume that * it needs to zero out portions of the start and/or end block. If 2 AIO * threads are at work on the same unwritten block, they must be synchronized * or one thread will zero the other's data, causing corruption. */ static bool ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos) { struct super_block *sb = inode->i_sb; unsigned long blockmask = sb->s_blocksize - 1; if ((pos | iov_iter_alignment(from)) & blockmask) return true; return false; } static bool ext4_extending_io(struct inode *inode, loff_t offset, size_t len) { if (offset + len > i_size_read(inode) || offset + len > EXT4_I(inode)->i_disksize) return true; return false; } /* Is IO overwriting allocated and initialized blocks? */ static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len) { struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; int err, blklen; if (pos + len > i_size_read(inode)) return false; map.m_lblk = pos >> blkbits; map.m_len = EXT4_MAX_BLOCKS(len, pos, blkbits); blklen = map.m_len; err = ext4_map_blocks(NULL, inode, &map, 0); /* * 'err==len' means that all of the blocks have been preallocated, * regardless of whether they have been initialized or not. To exclude * unwritten extents, we need to check m_flags. */ return err == blklen && (map.m_flags & EXT4_MAP_MAPPED); } static ssize_t ext4_generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; ret = generic_write_checks(iocb, from); if (ret <= 0) return ret; /* * If we have encountered a bitmap-format file, the size limit * is smaller than s_maxbytes, which is for extent-mapped files. */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (iocb->ki_pos >= sbi->s_bitmap_maxbytes) return -EFBIG; iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos); } return iov_iter_count(from); } static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from) { ssize_t ret, count; count = ext4_generic_write_checks(iocb, from); if (count <= 0) return count; ret = file_modified(iocb->ki_filp); if (ret) return ret; return count; } static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, struct iov_iter *from) { ssize_t ret; struct inode *inode = file_inode(iocb->ki_filp); if (iocb->ki_flags & IOCB_NOWAIT) return -EOPNOTSUPP; ext4_fc_start_update(inode); inode_lock(inode); ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; current->backing_dev_info = inode_to_bdi(inode); ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos); current->backing_dev_info = NULL; out: inode_unlock(inode); ext4_fc_stop_update(inode); if (likely(ret > 0)) { iocb->ki_pos += ret; ret = generic_write_sync(iocb, ret); } return ret; } static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, ssize_t written, size_t count) { handle_t *handle; bool truncate = false; u8 blkbits = inode->i_blkbits; ext4_lblk_t written_blk, end_blk; int ret; /* * Note that EXT4_I(inode)->i_disksize can get extended up to * inode->i_size while the I/O was running due to writeback of delalloc * blocks. But, the code in ext4_iomap_alloc() is careful to use * zeroed/unwritten extents if this is possible; thus we won't leave * uninitialized blocks in a file even if we didn't succeed in writing * as much as we intended. */ WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize); if (offset + count <= EXT4_I(inode)->i_disksize) { /* * We need to ensure that the inode is removed from the orphan * list if it has been added prematurely, due to writeback of * delalloc blocks. */ if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) { ext4_orphan_del(NULL, inode); return PTR_ERR(handle); } ext4_orphan_del(handle, inode); ext4_journal_stop(handle); } return written; } if (written < 0) goto truncate; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) { written = PTR_ERR(handle); goto truncate; } if (ext4_update_inode_size(inode, offset + written)) { ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) { written = ret; ext4_journal_stop(handle); goto truncate; } } /* * We may need to truncate allocated but not written blocks beyond EOF. */ written_blk = ALIGN(offset + written, 1 << blkbits); end_blk = ALIGN(offset + count, 1 << blkbits); if (written_blk < end_blk && ext4_can_truncate(inode)) truncate = true; /* * Remove the inode from the orphan list if it has been extended and * everything went OK. */ if (!truncate && inode->i_nlink) ext4_orphan_del(handle, inode); ext4_journal_stop(handle); if (truncate) { truncate: ext4_truncate_failed_write(inode); /* * If the truncate operation failed early, then the inode may * still be on the orphan list. In that case, we need to try * remove the inode from the in-memory linked list. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return written; } static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error, unsigned int flags) { loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(iocb->ki_filp); if (error) return error; if (size && flags & IOMAP_DIO_UNWRITTEN) { error = ext4_convert_unwritten_extents(NULL, inode, pos, size); if (error < 0) return error; } /* * If we are extending the file, we have to update i_size here before * page cache gets invalidated in iomap_dio_rw(). Otherwise racing * buffered reads could zero out too much from page cache pages. Update * of on-disk size will happen later in ext4_dio_write_iter() where * we have enough information to also perform orphan list handling etc. * Note that we perform all extending writes synchronously under * i_rwsem held exclusively so i_size update is safe here in that case. * If the write was not extending, we cannot see pos > i_size here * because operations reducing i_size like truncate wait for all * outstanding DIO before updating i_size. */ pos += size; if (pos > i_size_read(inode)) i_size_write(inode, pos); return 0; } static const struct iomap_dio_ops ext4_dio_write_ops = { .end_io = ext4_dio_write_end_io, }; /* * The intention here is to start with shared lock acquired then see if any * condition requires an exclusive inode lock. If yes, then we restart the * whole operation by releasing the shared lock and acquiring exclusive lock. * * - For unaligned_io we never take shared lock as it may cause data corruption * when two unaligned IO tries to modify the same block e.g. while zeroing. * * - For extending writes case we don't take the shared lock, since it requires * updating inode i_disksize and/or orphan handling with exclusive lock. * * - shared locking will only be true mostly with overwrites. Otherwise we will * switch to exclusive i_rwsem lock. */ static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from, bool *ilock_shared, bool *extend) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); loff_t offset; size_t count; ssize_t ret; restart: ret = ext4_generic_write_checks(iocb, from); if (ret <= 0) goto out; offset = iocb->ki_pos; count = ret; if (ext4_extending_io(inode, offset, count)) *extend = true; /* * Determine whether the IO operation will overwrite allocated * and initialized blocks. * We need exclusive i_rwsem for changing security info * in file_modified(). */ if (*ilock_shared && (!IS_NOSEC(inode) || *extend || !ext4_overwrite_io(inode, offset, count))) { if (iocb->ki_flags & IOCB_NOWAIT) { ret = -EAGAIN; goto out; } inode_unlock_shared(inode); *ilock_shared = false; inode_lock(inode); goto restart; } ret = file_modified(file); if (ret < 0) goto out; return count; out: if (*ilock_shared) inode_unlock_shared(inode); else inode_unlock(inode); return ret; } static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) { ssize_t ret; handle_t *handle; struct inode *inode = file_inode(iocb->ki_filp); loff_t offset = iocb->ki_pos; size_t count = iov_iter_count(from); const struct iomap_ops *iomap_ops = &ext4_iomap_ops; bool extend = false, unaligned_io = false; bool ilock_shared = true; /* * We initially start with shared inode lock unless it is * unaligned IO which needs exclusive lock anyways. */ if (ext4_unaligned_io(inode, from, offset)) { unaligned_io = true; ilock_shared = false; } /* * Quick check here without any i_rwsem lock to see if it is extending * IO. A more reliable check is done in ext4_dio_write_checks() with * proper locking in place. */ if (offset + count > i_size_read(inode)) ilock_shared = false; if (iocb->ki_flags & IOCB_NOWAIT) { if (ilock_shared) { if (!inode_trylock_shared(inode)) return -EAGAIN; } else { if (!inode_trylock(inode)) return -EAGAIN; } } else { if (ilock_shared) inode_lock_shared(inode); else inode_lock(inode); } /* Fallback to buffered I/O if the inode does not support direct I/O. */ if (!ext4_dio_supported(inode)) { if (ilock_shared) inode_unlock_shared(inode); else inode_unlock(inode); return ext4_buffered_write_iter(iocb, from); } ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend); if (ret <= 0) return ret; /* if we're going to block and IOCB_NOWAIT is set, return -EAGAIN */ if ((iocb->ki_flags & IOCB_NOWAIT) && (unaligned_io || extend)) { ret = -EAGAIN; goto out; } offset = iocb->ki_pos; count = ret; /* * Unaligned direct IO must be serialized among each other as zeroing * of partial blocks of two competing unaligned IOs can result in data * corruption. * * So we make sure we don't allow any unaligned IO in flight. * For IOs where we need not wait (like unaligned non-AIO DIO), * below inode_dio_wait() may anyway become a no-op, since we start * with exclusive lock. */ if (unaligned_io) inode_dio_wait(inode); if (extend) { handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; } ext4_fc_start_update(inode); ret = ext4_orphan_add(handle, inode); ext4_fc_stop_update(inode); if (ret) { ext4_journal_stop(handle); goto out; } ext4_journal_stop(handle); } if (ilock_shared) iomap_ops = &ext4_iomap_overwrite_ops; ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops, is_sync_kiocb(iocb) || unaligned_io || extend); if (ret == -ENOTBLK) ret = 0; if (extend) ret = ext4_handle_inode_extension(inode, offset, ret, count); out: if (ilock_shared) inode_unlock_shared(inode); else inode_unlock(inode); if (ret >= 0 && iov_iter_count(from)) { ssize_t err; loff_t endbyte; offset = iocb->ki_pos; err = ext4_buffered_write_iter(iocb, from); if (err < 0) return err; /* * We need to ensure that the pages within the page cache for * the range covered by this I/O are written to disk and * invalidated. This is in attempt to preserve the expected * direct I/O semantics in the case we fallback to buffered I/O * to complete off the I/O request. */ ret += err; endbyte = offset + err - 1; err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping, offset, endbyte); if (!err) invalidate_mapping_pages(iocb->ki_filp->f_mapping, offset >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); } return ret; } #ifdef CONFIG_FS_DAX static ssize_t ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) { ssize_t ret; size_t count; loff_t offset; handle_t *handle; bool extend = false; struct inode *inode = file_inode(iocb->ki_filp); if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock(inode)) return -EAGAIN; } else { inode_lock(inode); } ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; offset = iocb->ki_pos; count = iov_iter_count(from); if (offset + count > EXT4_I(inode)->i_disksize) { handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; } ret = ext4_orphan_add(handle, inode); if (ret) { ext4_journal_stop(handle); goto out; } extend = true; ext4_journal_stop(handle); } ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops); if (extend) ret = ext4_handle_inode_extension(inode, offset, ret, count); out: inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } #endif static ssize_t ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; #ifdef CONFIG_FS_DAX if (IS_DAX(inode)) return ext4_dax_write_iter(iocb, from); #endif if (iocb->ki_flags & IOCB_DIRECT) return ext4_dio_write_iter(iocb, from); else return ext4_buffered_write_iter(iocb, from); } #ifdef CONFIG_FS_DAX static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf, enum page_entry_size pe_size) { int error = 0; vm_fault_t result; int retries = 0; handle_t *handle = NULL; struct inode *inode = file_inode(vmf->vma->vm_file); struct super_block *sb = inode->i_sb; /* * We have to distinguish real writes from writes which will result in a * COW page; COW writes should *not* poke the journal (the file will not * be changed). Doing so would cause unintended failures when mounted * read-only. * * We check for VM_SHARED rather than vmf->cow_page since the latter is * unset for pe_size != PE_SIZE_PTE (i.e. only in do_cow_fault); for * other sizes, dax_iomap_fault will handle splitting / fallback so that * we eventually come back with a COW page. */ bool write = (vmf->flags & FAULT_FLAG_WRITE) && (vmf->vma->vm_flags & VM_SHARED); pfn_t pfn; if (write) { sb_start_pagefault(sb); file_update_time(vmf->vma->vm_file); down_read(&EXT4_I(inode)->i_mmap_sem); retry: handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, EXT4_DATA_TRANS_BLOCKS(sb)); if (IS_ERR(handle)) { up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); return VM_FAULT_SIGBUS; } } else { down_read(&EXT4_I(inode)->i_mmap_sem); } result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops); if (write) { ext4_journal_stop(handle); if ((result & VM_FAULT_ERROR) && error == -ENOSPC && ext4_should_retry_alloc(sb, &retries)) goto retry; /* Handling synchronous page fault? */ if (result & VM_FAULT_NEEDDSYNC) result = dax_finish_sync_fault(vmf, pe_size, pfn); up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); } else { up_read(&EXT4_I(inode)->i_mmap_sem); } return result; } static vm_fault_t ext4_dax_fault(struct vm_fault *vmf) { return ext4_dax_huge_fault(vmf, PE_SIZE_PTE); } static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .huge_fault = ext4_dax_huge_fault, .page_mkwrite = ext4_dax_fault, .pfn_mkwrite = ext4_dax_fault, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops #endif static const struct vm_operations_struct ext4_file_vm_ops = { .fault = ext4_filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file->f_mapping->host; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct dax_device *dax_dev = sbi->s_daxdev; if (unlikely(ext4_forced_shutdown(sbi))) return -EIO; /* * We don't support synchronous mappings for non-DAX files and * for DAX files if underneath dax_device is not synchronous. */ if (!daxdev_mapping_supported(vma, dax_dev)) return -EOPNOTSUPP; file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; vma->vm_flags |= VM_HUGEPAGE; } else { vma->vm_ops = &ext4_file_vm_ops; } return 0; } static int ext4_sample_last_mounted(struct super_block *sb, struct vfsmount *mnt) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct path path; char buf[64], *cp; handle_t *handle; int err; if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED))) return 0; if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb)) return 0; ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED); /* * Sample where the filesystem has been mounted and * store it in the superblock for sysadmin convenience * when trying to sort through large numbers of block * devices or filesystem images. */ memset(buf, 0, sizeof(buf)); path.mnt = mnt; path.dentry = mnt->mnt_root; cp = d_path(&path, buf, sizeof(buf)); err = 0; if (IS_ERR(cp)) goto out; handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); err = PTR_ERR(handle); if (IS_ERR(handle)) goto out; BUFFER_TRACE(sbi->s_sbh, "get_write_access"); err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto out_journal; strncpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); ext4_handle_dirty_super(handle, sb); out_journal: ext4_journal_stop(handle); out: sb_end_intwrite(sb); return err; } static int ext4_file_open(struct inode *inode, struct file *filp) { int ret; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt); if (ret) return ret; ret = fscrypt_file_open(inode, filp); if (ret) return ret; ret = fsverity_file_open(inode, filp); if (ret) return ret; /* * Set up the jbd2_inode if we are opening the inode for * writing and the journal is present */ if (filp->f_mode & FMODE_WRITE) { ret = ext4_inode_attach_jinode(inode); if (ret < 0) return ret; } filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; return dquot_file_open(inode, filp); } /* * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values * by calling generic_file_llseek_size() with the appropriate maxbytes * value for each. */ loff_t ext4_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; loff_t maxbytes; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; else maxbytes = inode->i_sb->s_maxbytes; switch (whence) { default: return generic_file_llseek_size(file, offset, whence, maxbytes, i_size_read(inode)); case SEEK_HOLE: inode_lock_shared(inode); offset = iomap_seek_hole(inode, offset, &ext4_iomap_report_ops); inode_unlock_shared(inode); break; case SEEK_DATA: inode_lock_shared(inode); offset = iomap_seek_data(inode, offset, &ext4_iomap_report_ops); inode_unlock_shared(inode); break; } if (offset < 0) return offset; return vfs_setpos(file, offset, maxbytes); } const struct file_operations ext4_file_operations = { .llseek = ext4_llseek, .read_iter = ext4_file_read_iter, .write_iter = ext4_file_write_iter, .iopoll = iomap_dio_iopoll, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, #endif .mmap = ext4_file_mmap, .mmap_supported_flags = MAP_SYNC, .open = ext4_file_open, .release = ext4_release_file, .fsync = ext4_sync_file, .get_unmapped_area = thp_get_unmapped_area, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ext4_fallocate, }; const struct inode_operations ext4_file_inode_operations = { .setattr = ext4_setattr, .getattr = ext4_file_getattr, .listxattr = ext4_listxattr, .get_acl = ext4_get_acl, .set_acl = ext4_set_acl, .fiemap = ext4_fiemap, };
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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #ifndef _NET_SEG6_H #define _NET_SEG6_H #include <linux/net.h> #include <linux/ipv6.h> #include <linux/seg6.h> #include <linux/rhashtable-types.h> static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) { __be32 diff[] = { ~from, to }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, __be32 *to) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } struct seg6_pernet_data { struct mutex lock; struct in6_addr __rcu *tun_src; #ifdef CONFIG_IPV6_SEG6_HMAC struct rhashtable hmac_infos; #endif }; static inline struct seg6_pernet_data *seg6_pernet(struct net *net) { #if IS_ENABLED(CONFIG_IPV6) return net->ipv6.seg6_data; #else return NULL; #endif } extern int seg6_init(void); extern void seg6_exit(void); extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); extern int seg6_local_init(void); extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id); #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_NETLINK_H #define __NET_NETLINK_H #include <linux/types.h> #include <linux/netlink.h> #include <linux/jiffies.h> #include <linux/in6.h> /* ======================================================================== * Netlink Messages and Attributes Interface (As Seen On TV) * ------------------------------------------------------------------------ * Messages Interface * ------------------------------------------------------------------------ * * Message Format: * <--- nlmsg_total_size(payload) ---> * <-- nlmsg_msg_size(payload) -> * +----------+- - -+-------------+- - -+-------- - - * | nlmsghdr | Pad | Payload | Pad | nlmsghdr * +----------+- - -+-------------+- - -+-------- - - * nlmsg_data(nlh)---^ ^ * nlmsg_next(nlh)-----------------------+ * * Payload Format: * <---------------------- nlmsg_len(nlh) ---------------------> * <------ hdrlen ------> <- nlmsg_attrlen(nlh, hdrlen) -> * +----------------------+- - -+--------------------------------+ * | Family Header | Pad | Attributes | * +----------------------+- - -+--------------------------------+ * nlmsg_attrdata(nlh, hdrlen)---^ * * Data Structures: * struct nlmsghdr netlink message header * * Message Construction: * nlmsg_new() create a new netlink message * nlmsg_put() add a netlink message to an skb * nlmsg_put_answer() callback based nlmsg_put() * nlmsg_end() finalize netlink message * nlmsg_get_pos() return current position in message * nlmsg_trim() trim part of message * nlmsg_cancel() cancel message construction * nlmsg_free() free a netlink message * * Message Sending: * nlmsg_multicast() multicast message to several groups * nlmsg_unicast() unicast a message to a single socket * nlmsg_notify() send notification message * * Message Length Calculations: * nlmsg_msg_size(payload) length of message w/o padding * nlmsg_total_size(payload) length of message w/ padding * nlmsg_padlen(payload) length of padding at tail * * Message Payload Access: * nlmsg_data(nlh) head of message payload * nlmsg_len(nlh) length of message payload * nlmsg_attrdata(nlh, hdrlen) head of attributes data * nlmsg_attrlen(nlh, hdrlen) length of attributes data * * Message Parsing: * nlmsg_ok(nlh, remaining) does nlh fit into remaining bytes? * nlmsg_next(nlh, remaining) get next netlink message * nlmsg_parse() parse attributes of a message * nlmsg_find_attr() find an attribute in a message * nlmsg_for_each_msg() loop over all messages * nlmsg_validate() validate netlink message incl. attrs * nlmsg_for_each_attr() loop over all attributes * * Misc: * nlmsg_report() report back to application? * * ------------------------------------------------------------------------ * Attributes Interface * ------------------------------------------------------------------------ * * Attribute Format: * <------- nla_total_size(payload) -------> * <---- nla_attr_size(payload) -----> * +----------+- - -+- - - - - - - - - +- - -+-------- - - * | Header | Pad | Payload | Pad | Header * +----------+- - -+- - - - - - - - - +- - -+-------- - - * <- nla_len(nla) -> ^ * nla_data(nla)----^ | * nla_next(nla)-----------------------------' * * Data Structures: * struct nlattr netlink attribute header * * Attribute Construction: * nla_reserve(skb, type, len) reserve room for an attribute * nla_reserve_nohdr(skb, len) reserve room for an attribute w/o hdr * nla_put(skb, type, len, data) add attribute to skb * nla_put_nohdr(skb, len, data) add attribute w/o hdr * nla_append(skb, len, data) append data to skb * * Attribute Construction for Basic Types: * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb * nla_put_u64_64bit(skb, type, * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb * nla_put_s64(skb, type, value, * padattr) add s64 attribute to skb * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb * nla_put_msecs(skb, type, jiffies, * padattr) add msecs attribute to skb * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * * Nested Attributes Construction: * nla_nest_start(skb, type) start a nested attribute * nla_nest_end(skb, nla) finalize a nested attribute * nla_nest_cancel(skb, nla) cancel nested attribute construction * * Attribute Length Calculations: * nla_attr_size(payload) length of attribute w/o padding * nla_total_size(payload) length of attribute w/ padding * nla_padlen(payload) length of padding * * Attribute Payload Access: * nla_data(nla) head of attribute payload * nla_len(nla) length of attribute payload * * Attribute Payload Access for Basic Types: * nla_get_u8(nla) get payload for a u8 attribute * nla_get_u16(nla) get payload for a u16 attribute * nla_get_u32(nla) get payload for a u32 attribute * nla_get_u64(nla) get payload for a u64 attribute * nla_get_s8(nla) get payload for