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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UIDGID_H #define _LINUX_UIDGID_H /* * A set of types for the internal kernel types representing uids and gids. * * The types defined in this header allow distinguishing which uids and gids in * the kernel are values used by userspace and which uid and gid values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; typedef struct { uid_t val; } kuid_t; typedef struct { gid_t val; } kgid_t; #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } #ifdef CONFIG_MULTIUSER static inline uid_t __kuid_val(kuid_t uid) { return uid.val; } static inline gid_t __kgid_val(kgid_t gid) { return gid.val; } #else static inline uid_t __kuid_val(kuid_t uid) { return 0; } static inline gid_t __kgid_val(kgid_t gid) { return 0; } #endif #define GLOBAL_ROOT_UID KUIDT_INIT(0) #define GLOBAL_ROOT_GID KGIDT_INIT(0) #define INVALID_UID KUIDT_INIT(-1) #define INVALID_GID KGIDT_INIT(-1) static inline bool uid_eq(kuid_t left, kuid_t right) { return __kuid_val(left) == __kuid_val(right); } static inline bool gid_eq(kgid_t left, kgid_t right) { return __kgid_val(left) == __kgid_val(right); } static inline bool uid_gt(kuid_t left, kuid_t right) { return __kuid_val(left) > __kuid_val(right); } static inline bool gid_gt(kgid_t left, kgid_t right) { return __kgid_val(left) > __kgid_val(right); } static inline bool uid_gte(kuid_t left, kuid_t right) { return __kuid_val(left) >= __kuid_val(right); } static inline bool gid_gte(kgid_t left, kgid_t right) { return __kgid_val(left) >= __kgid_val(right); } static inline bool uid_lt(kuid_t left, kuid_t right) { return __kuid_val(left) < __kuid_val(right); } static inline bool gid_lt(kgid_t left, kgid_t right) { return __kgid_val(left) < __kgid_val(right); } static inline bool uid_lte(kuid_t left, kuid_t right) { return __kuid_val(left) <= __kuid_val(right); } static inline bool gid_lte(kgid_t left, kgid_t right) { return __kgid_val(left) <= __kgid_val(right); } static inline bool uid_valid(kuid_t uid) { return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return from_kuid(ns, uid) != (uid_t) -1; } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return from_kgid(ns, gid) != (gid_t) -1; } #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); } static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) { return KGIDT_INIT(gid); } static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) { return __kuid_val(kuid); } static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) { return __kgid_val(kgid); } static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) { uid_t uid = from_kuid(to, kuid); if (uid == (uid_t)-1) uid = overflowuid; return uid; } static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) { gid_t gid = from_kgid(to, kgid); if (gid == (gid_t)-1) gid = overflowgid; return gid; } static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return gid_valid(gid); } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */
13 13 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM jbd2 #if !defined(_TRACE_JBD2_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_JBD2_H #include <linux/jbd2.h> #include <linux/tracepoint.h> struct transaction_chp_stats_s; struct transaction_run_stats_s; TRACE_EVENT(jbd2_checkpoint, TP_PROTO(journal_t *journal, int result), TP_ARGS(journal, result), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, result ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->result = result; ), TP_printk("dev %d,%d result %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->result) ); DECLARE_EVENT_CLASS(jbd2_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), TP_printk("dev %d,%d transaction %d sync %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit) ); DEFINE_EVENT(jbd2_commit, jbd2_start_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_locking, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_flushing, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_logging, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_drop_transaction, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); TRACE_EVENT(jbd2_end_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) __field( int, head ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; __entry->head = journal->j_tail_sequence; ), TP_printk("dev %d,%d transaction %d sync %d head %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit, __entry->head) ); TRACE_EVENT(jbd2_submit_inode_data, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); DECLARE_EVENT_CLASS(jbd2_handle_start_class, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, requested_blocks) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->requested_blocks = requested_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u " "requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_start, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_restart, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); TRACE_EVENT(jbd2_handle_extend, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int buffer_credits, int requested_blocks), TP_ARGS(dev, tid, type, line_no, buffer_credits, requested_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, buffer_credits ) __field( int, requested_blocks) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->buffer_credits = buffer_credits; __entry->requested_blocks = requested_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u " "buffer_credits %d requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->buffer_credits, __entry->requested_blocks) ); TRACE_EVENT(jbd2_handle_stats, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int interval, int sync, int requested_blocks, int dirtied_blocks), TP_ARGS(dev, tid, type, line_no, interval, sync, requested_blocks, dirtied_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, interval ) __field( int, sync ) __field( int, requested_blocks) __field( int, dirtied_blocks ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->interval = interval; __entry->sync = sync; __entry->requested_blocks = requested_blocks; __entry->dirtied_blocks = dirtied_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u interval %d " "sync %d requested_blocks %d dirtied_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->interval, __entry->sync, __entry->requested_blocks, __entry->dirtied_blocks) ); TRACE_EVENT(jbd2_run_stats, TP_PROTO(dev_t dev, unsigned long tid, struct transaction_run_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, wait ) __field( unsigned long, request_delay ) __field( unsigned long, running ) __field( unsigned long, locked ) __field( unsigned long, flushing ) __field( unsigned long, logging ) __field( __u32, handle_count ) __field( __u32, blocks ) __field( __u32, blocks_logged ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->wait = stats->rs_wait; __entry->request_delay = stats->rs_request_delay; __entry->running = stats->rs_running; __entry->locked = stats->rs_locked; __entry->flushing = stats->rs_flushing; __entry->logging = stats->rs_logging; __entry->handle_count = stats->rs_handle_count; __entry->blocks = stats->rs_blocks; __entry->blocks_logged = stats->rs_blocks_logged; ), TP_printk("dev %d,%d tid %lu wait %u request_delay %u running %u " "locked %u flushing %u logging %u handle_count %u " "blocks %u blocks_logged %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->wait), jiffies_to_msecs(__entry->request_delay), jiffies_to_msecs(__entry->running), jiffies_to_msecs(__entry->locked), jiffies_to_msecs(__entry->flushing), jiffies_to_msecs(__entry->logging), __entry->handle_count, __entry->blocks, __entry->blocks_logged) ); TRACE_EVENT(jbd2_checkpoint_stats, TP_PROTO(dev_t dev, unsigned long tid, struct transaction_chp_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, chp_time ) __field( __u32, forced_to_close ) __field( __u32, written ) __field( __u32, dropped ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->chp_time = stats->cs_chp_time; __entry->forced_to_close= stats->cs_forced_to_close; __entry->written = stats->cs_written; __entry->dropped = stats->cs_dropped; ), TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u " "written %u dropped %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->chp_time), __entry->forced_to_close, __entry->written, __entry->dropped) ); TRACE_EVENT(jbd2_update_log_tail, TP_PROTO(journal_t *journal, tid_t first_tid, unsigned long block_nr, unsigned long freed), TP_ARGS(journal, first_tid, block_nr, freed), TP_STRUCT__entry( __field( dev_t, dev ) __field( tid_t, tail_sequence ) __field( tid_t, first_tid ) __field(unsigned long, block_nr ) __field(unsigned long, freed ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->tail_sequence = journal->j_tail_sequence; __entry->first_tid = first_tid; __entry->block_nr = block_nr; __entry->freed = freed; ), TP_printk("dev %d,%d from %u to %u offset %lu freed %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tail_sequence, __entry->first_tid, __entry->block_nr, __entry->freed) ); TRACE_EVENT(jbd2_write_superblock, TP_PROTO(journal_t *journal, int write_op), TP_ARGS(journal, write_op), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, write_op ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->write_op = write_op; ), TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->write_op) ); TRACE_EVENT(jbd2_lock_buffer_stall, TP_PROTO(dev_t dev, unsigned long stall_ms), TP_ARGS(dev, stall_ms), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, stall_ms ) ), TP_fast_assign( __entry->dev = dev; __entry->stall_ms = stall_ms; ), TP_printk("dev %d,%d stall_ms %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->stall_ms) ); #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
3 3 3 3 3 3 3 3 3 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/vmscan.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for try_to_release_page(), buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; /* Can active pages be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped pages be reclaimed? */ unsigned int may_unmap:1; /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file pages on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate pages for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_page(_page, _base, _field) \ do { \ if ((_page)->lru.prev != _base) { \ struct page *prev; \ \ prev = lru_to_page(&(_page->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0) #endif /* * From 0 .. 200. Higher means more swappy. */ int vm_swappiness = 60; static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG /* * We allow subsystems to populate their shrinker-related * LRU lists before register_shrinker_prepared() is called * for the shrinker, since we don't want to impose * restrictions on their internal registration order. * In this case shrink_slab_memcg() may find corresponding * bit is set in the shrinkers map. * * This value is used by the function to detect registering * shrinkers and to skip do_shrink_slab() calls for them. */ #define SHRINKER_REGISTERING ((struct shrinker *)~0UL) static DEFINE_IDR(shrinker_idr); static int shrinker_nr_max; static int prealloc_memcg_shrinker(struct shrinker *shrinker) { int id, ret = -ENOMEM; down_write(&shrinker_rwsem); /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { if (memcg_expand_shrinker_maps(id)) { idr_remove(&shrinker_idr, id); goto unlock; } shrinker_nr_max = id + 1; } shrinker->id = id; ret = 0; unlock: up_write(&shrinker_rwsem); return ret; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { int id = shrinker->id; BUG_ON(id < 0); down_write(&shrinker_rwsem); idr_remove(&shrinker_idr, id); up_write(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_page_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } #else static int prealloc_memcg_shrinker(struct shrinker *shrinker) { return 0; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { } static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } #endif /* * This misses isolated pages which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated pages will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (get_nr_swap_pages() > 0) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) */ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) continue; if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } /* * Add a shrinker callback to be called from the vm. */ int prealloc_shrinker(struct shrinker *shrinker) { unsigned int size = sizeof(*shrinker->nr_deferred); if (shrinker->flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); if (!shrinker->nr_deferred) return -ENOMEM; if (shrinker->flags & SHRINKER_MEMCG_AWARE) { if (prealloc_memcg_shrinker(shrinker)) goto free_deferred; } return 0; free_deferred: kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; return -ENOMEM; } void free_prealloced_shrinker(struct shrinker *shrinker) { if (!shrinker->nr_deferred) return; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); #ifdef CONFIG_MEMCG if (shrinker->flags & SHRINKER_MEMCG_AWARE) idr_replace(&shrinker_idr, shrinker, shrinker->id); #endif up_write(&shrinker_rwsem); } int register_shrinker(struct shrinker *shrinker) { int err = prealloc_shrinker(shrinker); if (err) return err; register_shrinker_prepared(shrinker); return 0; } EXPORT_SYMBOL(register_shrinker); /* * Remove one */ void unregister_shrinker(struct shrinker *shrinker) { if (!shrinker->nr_deferred) return; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, struct shrinker *shrinker, int priority) { unsigned long freed = 0; unsigned long long delta; long total_scan; long freeable; long nr; long new_nr; int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; /* * copy the current shrinker scan count into a local variable * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); total_scan = nr; if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); } else { /* * These objects don't require any IO to create. Trim * them aggressively under memory pressure to keep * them from causing refetches in the IO caches. */ delta = freeable / 2; } total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); total_scan = freeable; next_deferred = nr; } else next_deferred = total_scan; /* * We need to avoid excessive windup on filesystem shrinkers * due to large numbers of GFP_NOFS allocations causing the * shrinkers to return -1 all the time. This results in a large * nr being built up so when a shrink that can do some work * comes along it empties the entire cache due to nr >>> * freeable. This is bad for sustaining a working set in * memory. * * Hence only allow the shrinker to scan the entire cache when * a large delta change is calculated directly. */ if (delta < freeable / 4) total_scan = min(total_scan, freeable / 2); /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ if (total_scan > freeable * 2) total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); /* * Normally, we should not scan less than batch_size objects in one * pass to avoid too frequent shrinker calls, but if the slab has less * than batch_size objects in total and we are really tight on memory, * we will try to reclaim all available objects, otherwise we can end * up failing allocations although there are plenty of reclaimable * objects spread over several slabs with usage less than the * batch_size. * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); shrinkctl->nr_to_scan = nr_to_scan; shrinkctl->nr_scanned = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); total_scan -= shrinkctl->nr_scanned; scanned += shrinkctl->nr_scanned; cond_resched(); } if (next_deferred >= scanned) next_deferred -= scanned; else next_deferred = 0; /* * move the unused scan count back into the shrinker in a * manner that handles concurrent updates. If we exhausted the * scan, there is no need to do an update. */ if (next_deferred > 0) new_nr = atomic_long_add_return(next_deferred, &shrinker->nr_deferred[nid]); else new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); return freed; } #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct memcg_shrinker_map *map; unsigned long ret, freed = 0; int i; if (!mem_cgroup_online(memcg)) return 0; if (!down_read_trylock(&shrinker_rwsem)) return 0; map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, true); if (unlikely(!map)) goto unlock; for_each_set_bit(i, map->map, shrinker_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; struct shrinker *shrinker; shrinker = idr_find(&shrinker_idr, i); if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { if (!shrinker) clear_bit(i, map->map); continue; } /* Call non-slab shrinkers even though kmem is disabled */ if (!memcg_kmem_enabled() && !(shrinker->flags & SHRINKER_NONSLAB)) continue; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { clear_bit(i, map->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in * the memcg shrinker map, a new object might have been * added. To make sure, we have the bit set in this * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in * memcg_set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() * <MB> <MB> * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; else memcg_set_shrinker_bit(memcg, nid, i); } freed += ret; if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } unlock: up_read(&shrinker_rwsem); return freed; } #else /* CONFIG_MEMCG */ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { return 0; } #endif /* CONFIG_MEMCG */ /** * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target * @memcg: memory cgroup whose slab caches to target * @priority: the reclaim priority * * Call the shrink functions to age shrinkable caches. * * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * * @memcg specifies the memory cgroup to target. Unaware shrinkers * are called only if it is the root cgroup. * * @priority is sc->priority, we take the number of objects and >> by priority * in order to get the scan target. * * Returns the number of reclaimed slab objects. */ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { unsigned long ret, freed = 0; struct shrinker *shrinker; /* * The root memcg might be allocated even though memcg is disabled * via "cgroup_disable=memory" boot parameter. This could make * mem_cgroup_is_root() return false, then just run memcg slab * shrink, but skip global shrink. This may result in premature * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) goto out; list_for_each_entry(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; /* * Bail out if someone want to register a new shrinker to * prevent the registration from being stalled for long periods * by parallel ongoing shrinking. */ if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } up_read(&shrinker_rwsem); out: cond_resched(); return freed; } void drop_slab_node(int nid) { unsigned long freed; do { struct mem_cgroup *memcg = NULL; if (fatal_signal_pending(current)) return; freed = 0; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); } while (freed > 10); } void drop_slab(void) { int nid; for_each_online_node(nid) drop_slab_node(nid); } static inline int is_page_cache_freeable(struct page *page) { /* * A freeable page cache page is referenced only by the caller * that isolated the page, the page cache and optional buffer * heads at page->private. */ int page_cache_pins = thp_nr_pages(page); return page_count(page) - page_has_private(page) == 1 + page_cache_pins; } static int may_write_to_inode(struct inode *inode) { if (current->flags & PF_SWAPWRITE) return 1; if (!inode_write_congested(inode)) return 1; if (inode_to_bdi(inode) == current->backing_dev_info) return 1; return 0; } /* * We detected a synchronous write error writing a page out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the page and once * that page is locked, the mapping is pinned. * * We're allowed to run sleeping lock_page() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct page *page, int error) { lock_page(page); if (page_mapping(page) == mapping) mapping_set_error(mapping, error); unlock_page(page); } /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ PAGE_KEEP, /* move page to the active list, page is locked */ PAGE_ACTIVATE, /* page has been sent to the disk successfully, page is unlocked */ PAGE_SUCCESS, /* page is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_page_list() for each dirty page. * Calls ->writepage(). */ static pageout_t pageout(struct page *page, struct address_space *mapping) { /* * If the page is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this page's queue, we can perform writeback even if that * will block. * * If the page is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(page)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned pages can have * page->mapping == NULL while being dirty with clean buffers. */ if (page_has_private(page)) { if (try_to_free_buffers(page)) { ClearPageDirty(page); pr_info("%s: orphaned page\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (!may_write_to_inode(mapping->host)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, }; SetPageReclaim(page); res = mapping->a_ops->writepage(page, &wbc); if (res < 0) handle_write_error(mapping, page, res); if (res == AOP_WRITEPAGE_ACTIVATE) { ClearPageReclaim(page); return PAGE_ACTIVATE; } if (!PageWriteback(page)) { /* synchronous write or broken a_ops? */ ClearPageReclaim(page); } trace_mm_vmscan_writepage(page); inc_node_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct page *page, bool reclaimed, struct mem_cgroup *target_memcg) { unsigned long flags; int refcount; void *shadow = NULL; BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); xa_lock_irqsave(&mapping->i_pages, flags); /* * The non racy check for a busy page. * * Must be careful with the order of the tests. When someone has * a ref to the page, it may be possible that they dirty it then * drop the reference. So if PageDirty is tested before page_count * here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !PageDirty(page) [good] * SetPageDirty(page); * put_page(page); * !page_count(page) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the page->flags * load is not satisfied before that of page->_refcount. * * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + compound_nr(page); if (!page_ref_freeze(page, refcount)) goto cannot_free; /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ if (unlikely(PageDirty(page))) { page_ref_unfreeze(page, refcount); goto cannot_free; } if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(page, target_memcg); __delete_from_swap_cache(page, swap, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); } else { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache pages found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && page_is_file_lru(page) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(page, target_memcg); __delete_from_page_cache(page, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); if (freepage != NULL) freepage(page); } return 1; cannot_free: xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } /* * Attempt to detach a locked page from its ->mapping. If it is dirty or if * someone else has a ref on the page, abort and return 0. If it was * successfully detached, return 1. Assumes the caller has a single ref on * this page. */ int remove_mapping(struct address_space *mapping, struct page *page) { if (__remove_mapping(mapping, page, false, NULL)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ page_ref_unfreeze(page, 1); return 1; } return 0; } /** * putback_lru_page - put previously isolated page onto appropriate LRU list * @page: page to be put back to appropriate lru list * * Add previously isolated @page to appropriate LRU list. * Page may still be unevictable for other reasons. * * lru_lock must not be held, interrupts must be enabled. */ void putback_lru_page(struct page *page) { lru_cache_add(page); put_page(page); /* drop ref from isolate */ } enum page_references { PAGEREF_RECLAIM, PAGEREF_RECLAIM_CLEAN, PAGEREF_KEEP, PAGEREF_ACTIVATE, }; static enum page_references page_check_references(struct page *page, struct scan_control *sc) { int referenced_ptes, referenced_page; unsigned long vm_flags; referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, &vm_flags); referenced_page = TestClearPageReferenced(page); /* * Mlock lost the isolation race with us. Let try_to_unmap() * move the page to the unevictable list. */ if (vm_flags & VM_LOCKED) return PAGEREF_RECLAIM; if (referenced_ptes) { /* * All mapped pages start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file page is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated pages as well * so that recently deactivated but used pages are * quickly recovered. */ SetPageReferenced(page); if (referenced_page || referenced_ptes > 1) return PAGEREF_ACTIVATE; /* * Activate file-backed executable pages after first usage. */ if ((vm_flags & VM_EXEC) && !PageSwapBacked(page)) return PAGEREF_ACTIVATE; return PAGEREF_KEEP; } /* Reclaim if clean, defer dirty pages to writeback */ if (referenced_page && !PageSwapBacked(page)) return PAGEREF_RECLAIM_CLEAN; return PAGEREF_RECLAIM; } /* Check if a page is dirty or under writeback */ static void page_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous pages are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them */ if (!page_is_file_lru(page) || (PageAnon(page) && !PageSwapBacked(page))) { *dirty = false; *writeback = false; return; } /* By default assume that the page flags are accurate */ *dirty = PageDirty(page); *writeback = PageWriteback(page); /* Verify dirty/writeback state if the filesystem supports it */ if (!page_has_private(page)) return; mapping = page_mapping(page); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(page, dirty, writeback); } /* * shrink_page_list() returns the number of reclaimed pages */ static unsigned int shrink_page_list(struct list_head *page_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; memset(stat, 0, sizeof(*stat)); cond_resched(); while (!list_empty(page_list)) { struct address_space *mapping; struct page *page; enum page_references references = PAGEREF_RECLAIM; bool dirty, writeback, may_enter_fs; unsigned int nr_pages; cond_resched(); page = lru_to_page(page_list); list_del(&page->lru); if (!trylock_page(page)) goto keep; VM_BUG_ON_PAGE(PageActive(page), page); nr_pages = compound_nr(page); /* Account the number of base pages even though THP */ sc->nr_scanned += nr_pages; if (unlikely(!page_evictable(page))) goto activate_locked; if (!sc->may_unmap && page_mapped(page)) goto keep_locked; may_enter_fs = (sc->gfp_mask & __GFP_FS) || (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); /* * The number of dirty pages determines if a node is marked * reclaim_congested which affects wait_iff_congested. kswapd * will stall and start writing pages if the tail of the LRU * is all dirty unqueued pages. */ page_check_dirty_writeback(page, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty++; if (dirty && !writeback) stat->nr_unqueued_dirty++; /* * Treat this page as congested if the underlying BDI is or if * pages are cycling through the LRU so quickly that the * pages marked for immediate reclaim are making it to the * end of the LRU a second time. */ mapping = page_mapping(page); if (((dirty || writeback) && mapping && inode_write_congested(mapping->host)) || (writeback && PageReclaim(page))) stat->nr_congested++; /* * If a page at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number of pages * under writeback and this page is both under writeback and * PageReclaim then it indicates that pages are being queued * for IO but are being recycled through the LRU before the * IO can complete. Waiting on the page itself risks an * indefinite stall if it is impossible to writeback the * page due to IO error or disconnected storage so instead * note that the LRU is being scanned too quickly and the * caller can stall after page list has been processed. * * 2) Global or new memcg reclaim encounters a page that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the page for immediate * reclaim and continue scanning. * * Require may_enter_fs because we would wait on fs, which * may not have submitted IO yet. And the loop driver might * enter reclaim, and deadlock if it waits on a page for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a page that is already marked * PageReclaim. memcg does not have any dirty pages * throttling so we could easily OOM just because too many * pages are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the pages to get them out of * the way while we continue scanning for clean pages on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (PageWriteback(page)) { /* Case 1 above */ if (current_is_kswapd() && PageReclaim(page) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate++; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !PageReclaim(page) || !may_enter_fs) { /* * This is slightly racy - end_page_writeback() * might have just cleared PageReclaim, then * setting PageReclaim here end up interpreted * as PageReadahead - but that does not matter * enough to care. What we do want is for this * page to have PageReclaim set next time memcg * reclaim reaches the tests above, so it will * then wait_on_page_writeback() to avoid OOM; * and it's also appropriate in global reclaim. */ SetPageReclaim(page); stat->nr_writeback++; goto activate_locked; /* Case 3 above */ } else { unlock_page(page); wait_on_page_writeback(page); /* then go back and try same page again */ list_add_tail(&page->lru, page_list); continue; } } if (!ignore_references) references = page_check_references(page, sc); switch (references) { case PAGEREF_ACTIVATE: goto activate_locked; case PAGEREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case PAGEREF_RECLAIM: case PAGEREF_RECLAIM_CLEAN: ; /* try to reclaim the page below */ } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree page could be freed directly */ if (PageAnon(page) && PageSwapBacked(page)) { if (!PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (page_maybe_dma_pinned(page)) goto keep_locked; if (PageTransHuge(page)) { /* cannot split THP, skip it */ if (!can_split_huge_page(page, NULL)) goto activate_locked; /* * Split pages without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ if (!compound_mapcount(page) && split_huge_page_to_list(page, page_list)) goto activate_locked; } if (!add_to_swap(page)) { if (!PageTransHuge(page)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_huge_page_to_list(page, page_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(page)) goto activate_locked_split; } may_enter_fs = true; /* Adding to swap updated mapping */ mapping = page_mapping(page); } } else if (unlikely(PageTransHuge(page))) { /* Split file THP */ if (split_huge_page_to_list(page, page_list)) goto keep_locked; } /* * THP may get split above, need minus tail pages and update * nr_pages to avoid accounting tail pages twice. * * The tail pages that are added into swap cache successfully * reach here. */ if ((nr_pages > 1) && !PageTransHuge(page)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The page is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (page_mapped(page)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = PageSwapBacked(page); if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; if (!try_to_unmap(page, flags)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && PageSwapBacked(page)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } if (PageDirty(page)) { /* * Only kswapd can writeback filesystem pages * to avoid risk of stack overflow. But avoid * injecting inefficient single-page IO into * flusher writeback as much as possible: only * write pages when we've encountered many * dirty pages, and when we've already scanned * the rest of the LRU for clean pages and see * the same dirty pages again (PageReclaim). */ if (page_is_file_lru(page) && (!current_is_kswapd() || !PageReclaim(page) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() * except we already have the page isolated * and know it's dirty */ inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); SetPageReclaim(page); goto activate_locked; } if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Page is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after IO * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(page, mapping)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: stat->nr_pageout += thp_nr_pages(page); if (PageWriteback(page)) goto keep; if (PageDirty(page)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the page. */ if (!trylock_page(page)) goto keep; if (PageDirty(page) || PageWriteback(page)) goto keep_locked; mapping = page_mapping(page); case PAGE_CLEAN: ; /* try to free the page below */ } } /* * If the page has buffers, try to free the buffer mappings * associated with this page. If we succeed we try to free * the page as well. * * We do this even if the page is PageDirty(). * try_to_release_page() does not perform I/O, but it is * possible for a page to have PageDirty set, but it is actually * clean (all its buffers are clean). This happens if the * buffers were written out directly, with submit_bh(). ext3 * will do this, as well as the blockdev mapping. * try_to_release_page() will discover that cleanness and will * drop the buffers and mark the page clean - it can be freed. * * Rarely, pages can have buffers and no ->mapping. These are * the pages which were not successfully invalidated in * truncate_complete_page(). We try to drop those buffers here * and if that worked, and the page is no longer mapped into * process address space (page_count == 1) it can be freed. * Otherwise, leave the page on the LRU so it is swappable. */ if (page_has_private(page)) { if (!try_to_release_page(page, sc->gfp_mask)) goto activate_locked; if (!mapping && page_count(page) == 1) { unlock_page(page); if (put_page_testzero(page)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this page shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed++; continue; } } } if (PageAnon(page) && !PageSwapBacked(page)) { /* follow __remove_mapping for reference */ if (!page_ref_freeze(page, 1)) goto keep_locked; if (PageDirty(page)) { page_ref_unfreeze(page, 1); goto keep_locked; } count_vm_event(PGLAZYFREED); count_memcg_page_event(page, PGLAZYFREED); } else if (!mapping || !__remove_mapping(mapping, page, true, sc->target_mem_cgroup)) goto keep_locked; unlock_page(page); free_it: /* * THP may get swapped out in a whole, need account * all base pages. */ nr_reclaimed += nr_pages; /* * Is there need to periodically free_page_list? It would * appear not as the counts should be low */ if (unlikely(PageTransHuge(page))) destroy_compound_page(page); else list_add(&page->lru, &free_pages); continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || PageMlocked(page))) try_to_free_swap(page); VM_BUG_ON_PAGE(PageActive(page), page); if (!PageMlocked(page)) { int type = page_is_file_lru(page); SetPageActive(page); stat->nr_activate[type] += nr_pages; count_memcg_page_event(page, PGACTIVATE); } keep_locked: unlock_page(page); keep: list_add(&page->lru, &ret_pages); VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_list(&free_pages); try_to_unmap_flush(); free_unref_page_list(&free_pages); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *page_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct page *page, *next; LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { if (page_is_file_lru(page) && !PageDirty(page) && !__PageMovable(page) && !PageUnevictable(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } } nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, &stat, true); list_splice(&clean_pages, page_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Attempt to remove the specified page from its LRU. Only take this page * if it is of the appropriate PageActive status. Pages which are being * freed elsewhere are also ignored. * * page: page to consider * mode: one of the LRU isolation modes defined above * * returns 0 on success, -ve errno on failure. */ int __isolate_lru_page(struct page *page, isolate_mode_t mode) { int ret = -EINVAL; /* Only take pages on the LRU. */ if (!PageLRU(page)) return ret; /* Compaction should not handle unevictable pages but CMA can do so */ if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) return ret; ret = -EBUSY; /* * To minimise LRU disruption, the caller can indicate that it only * wants to isolate pages it will be able to operate on without * blocking - clean pages for the most part. * * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages * that it is possible to migrate without blocking */ if (mode & ISOLATE_ASYNC_MIGRATE) { /* All the caller can do on PageWriteback is block */ if (PageWriteback(page)) return ret; if (PageDirty(page)) { struct address_space *mapping; bool migrate_dirty; /* * Only pages without mappings or that have a * ->migratepage callback are possible to migrate * without blocking. However, we can be racing with * truncation so it's necessary to lock the page * to stabilise the mapping as truncation holds * the page lock until after the page is removed * from the page cache. */ if (!trylock_page(page)) return ret; mapping = page_mapping(page); migrate_dirty = !mapping || mapping->a_ops->migratepage; unlock_page(page); if (!migrate_dirty) return ret; } } if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) return ret; if (likely(get_page_unless_zero(page))) { /* * Be careful not to clear PageLRU until after we're * sure the page is not being freed elsewhere -- the * page release code relies on it. */ ClearPageLRU(page); ret = 0; } return ret; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /** * pgdat->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Appropriate locks must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; LIST_HEAD(pages_skipped); isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct page *page; page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); VM_BUG_ON_PAGE(!PageLRU(page), page); nr_pages = compound_nr(page); total_scan += nr_pages; if (page_zonenum(page) > sc->reclaim_idx) { list_move(&page->lru, &pages_skipped); nr_skipped[page_zonenum(page)] += nr_pages; continue; } /* * Do not count skipped pages because that makes the function * return with no isolated pages if the LRU mostly contains * ineligible pages. This causes the VM to not reclaim any * pages, triggering a premature OOM. * * Account all tail pages of THP. This would not cause * premature OOM since __isolate_lru_page() returns -EBUSY * only when the page is being freed somewhere else. */ scan += nr_pages; switch (__isolate_lru_page(page, mode)) { case 0: nr_taken += nr_pages; nr_zone_taken[page_zonenum(page)] += nr_pages; list_move(&page->lru, dst); break; case -EBUSY: /* else it is being freed elsewhere */ list_move(&page->lru, src); continue; default: BUG(); } } /* * Splice any skipped pages to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same pages to skip and put the * system at risk of premature OOM. */ if (!list_empty(&pages_skipped)) { int zid; list_splice(&pages_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, mode, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * isolate_lru_page - tries to isolate a page from its LRU list * @page: page to isolate from its LRU list * * Isolates a @page from an LRU list, clears PageLRU and adjusts the * vmstat statistic corresponding to whatever LRU list the page was on. * * Returns 0 if the page was removed from an LRU list. * Returns -EBUSY if the page was not on an LRU list. * * The returned page will have PageLRU() cleared. If it was found on * the active list, it will have PageActive set. If it was found on * the unevictable list, it will have the PageUnevictable bit set. That flag * may need to be cleared by the caller before letting the page go. * * The vmstat statistic corresponding to the list on which the page was * found will be decremented. * * Restrictions: * * (1) Must be called with an elevated refcount on the page. This is a * fundamental difference from isolate_lru_pages (which is called * without a stable reference). * (2) the lru_lock must not be held. * (3) interrupts must be enabled. */ int isolate_lru_page(struct page *page) { int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); if (PageLRU(page)) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; spin_lock_irq(&pgdat->lru_lock); lruvec = mem_cgroup_page_lruvec(page, pgdat); if (PageLRU(page)) { int lru = page_lru(page); get_page(page); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, lru); ret = 0; } spin_unlock_irq(&pgdat->lru_lock); } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; if (current_is_kswapd()) return 0; if (!writeback_throttling_sane(sc)) return 0; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; return isolated > inactive; } /* * This moves pages from @list to corresponding LRU list. * * We move them the other way if the page is referenced by one or more * processes, from rmap. * * If the pages are mostly unmapped, the processing is fast and it is * appropriate to hold zone_lru_lock across the whole operation. But if * the pages are mapped, the processing is slow (page_referenced()) so we * should drop zone_lru_lock around each page. It's impossible to balance * this, so instead we remove the pages from the LRU while processing them. * It is safe to rely on PG_active against the non-LRU pages in here because * nobody will play with that bit on a non-LRU page. * * The downside is that we have to touch page->_refcount against each page. * But we had to alter page->flags anyway. * * Returns the number of pages moved to the given lruvec. */ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, struct list_head *list) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); int nr_pages, nr_moved = 0; LIST_HEAD(pages_to_free); struct page *page; enum lru_list lru; while (!list_empty(list)) { page = lru_to_page(list); VM_BUG_ON_PAGE(PageLRU(page), page); if (unlikely(!page_evictable(page))) { list_del(&page->lru); spin_unlock_irq(&pgdat->lru_lock); putback_lru_page(page); spin_lock_irq(&pgdat->lru_lock); continue; } lruvec = mem_cgroup_page_lruvec(page, pgdat); SetPageLRU(page); lru = page_lru(page); nr_pages = thp_nr_pages(page); update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); list_move(&page->lru, &lruvec->lists[lru]); if (put_page_testzero(page)) { __ClearPageLRU(page); __ClearPageActive(page); del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { spin_unlock_irq(&pgdat->lru_lock); destroy_compound_page(page); spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, &pages_to_free); } else { nr_moved += nr_pages; if (PageActive(page)) workingset_age_nonresident(lruvec, nr_pages); } } /* * To save our caller's stack, now use input list for pages to free. */ list_splice(&pages_to_free, list); return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services * a backing device by writing to the page cache it sets PF_LOCAL_THROTTLE. * In that case we should only throttle if the backing device it is * writing to is congested. In other cases it is safe to throttle. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE) || current->backing_dev_info == NULL || bdi_write_congested(current->backing_dev_info); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static noinline_for_stack unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(page_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ msleep(100); stalled = true; /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&pgdat->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false); spin_lock_irq(&pgdat->lru_lock); move_pages_to_lru(lruvec, &page_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); lru_note_cost(lruvec, file, stat.nr_pageout); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&page_list); free_unref_page_list(&page_list); /* * If dirty pages are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty pages to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty pages grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) wakeup_flusher_threads(WB_REASON_VMSCAN); sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The pages which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); struct page *page; unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&pgdat->lru_lock); while (!list_empty(&l_hold)) { cond_resched(); page = lru_to_page(&l_hold); list_del(&page->lru); if (unlikely(!page_evictable(page))) { putback_lru_page(page); continue; } if (unlikely(buffer_heads_over_limit)) { if (page_has_private(page) && trylock_page(page)) { if (page_has_private(page)) try_to_release_page(page, 0); unlock_page(page); } } if (page_referenced(page, 0, sc->target_mem_cgroup, &vm_flags)) { /* * Identify referenced, file-backed active pages and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon pages * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC pages, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) { nr_rotated += thp_nr_pages(page); list_add(&page->lru, &l_active); continue; } } ClearPageActive(page); /* we are de-activating */ SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } /* * Move pages back to the lru list. */ spin_lock_irq(&pgdat->lru_lock); nr_activate = move_pages_to_lru(lruvec, &l_active); nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); /* Keep all free pages in l_active list */ list_splice(&l_inactive, &l_active); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&l_active); free_unref_page_list(&l_active); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } unsigned long reclaim_pages(struct list_head *page_list) { int nid = NUMA_NO_NODE; unsigned int nr_reclaimed = 0; LIST_HEAD(node_page_list); struct reclaim_stat dummy_stat; struct page *page; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, }; while (!list_empty(page_list)) { page = lru_to_page(page_list); if (nid == NUMA_NO_NODE) { nid = page_to_nid(page); INIT_LIST_HEAD(&node_page_list); } if (nid == page_to_nid(page)) { ClearPageActive(page); list_move(&page->lru, &node_page_list); continue; } nr_reclaimed += shrink_page_list(&node_page_list, NODE_DATA(nid), &sc, &dummy_stat, false); while (!list_empty(&node_page_list)) { page = lru_to_page(&node_page_list); list_del(&page->lru); putback_lru_page(page); } nid = NUMA_NO_NODE; } if (!list_empty(&node_page_list)) { nr_reclaimed += shrink_page_list(&node_page_list, NODE_DATA(nid), &sc, &dummy_stat, false); while (!list_empty(&node_page_list)) { page = lru_to_page(&node_page_list); list_del(&page->lru); putback_lru_page(page); } } return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * page has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the pages are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; /* * Determine how aggressively the anon and file LRU lists should be * scanned. The relative value of each set of LRU lists is determined * by looking at the fraction of the pages scanned we did rotate back * onto the active list instead of evict. * * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = mem_cgroup_swappiness(memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; unsigned long ap, fp; enum lru_list lru; /* If we have no swap space, do not bother scanning anon pages. */ if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (200 - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; denominator = ap + fp; out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; struct blk_plug plug; bool scan_adjusted; get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || scan_adjusted) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); scan_adjusted = true; } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { case COMPACT_SUCCESS: case COMPACT_CONTINUE: return false; default: /* check next zone */ ; } } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup *memcg; memcg = mem_cgroup_iter(target_memcg, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; struct lruvec *target_lruvec; bool reclaimable = false; unsigned long file; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&pgdat->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&pgdat->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[0] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[1] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } shrink_node_memcgs(pgdat, sc); if (reclaim_state) { sc->nr_reclaimed += reclaim_state->reclaimed_slab; reclaim_state->reclaimed_slab = 0; } /* Record the subtree's reclaim efficiency */ vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so also forcibly stall. */ if (sc->nr.immediate) congestion_wait(BLK_RW_ASYNC, HZ/10); } /* * Tag a node/memcg as congested if all the dirty pages * scanned were backed by a congested BDI and * wait_iff_congested will stall. * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in wait_iff_congested(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && sc->nr.dirty && sc->nr.dirty == sc->nr.congested) set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* * Stall direct reclaim for IO completions if underlying BDIs * and node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) wait_iff_congested(BLK_RW_ASYNC, HZ/10); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; enum compact_result suitable; suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); if (suitable == COMPACT_SUCCESS) /* Allocation should succeed already. Don't reclaim. */ return true; if (suitable == COMPACT_SKIPPED) /* Compaction cannot yet proceed. Do reclaim. */ return false; /* * Compaction is already possible, but it takes time to run and there * are potentially other callers using the pages just freed. So proceed * with reclaim to make a buffer of free pages available to give * compaction a reasonable chance of completing and allocating the page. * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone) + compact_gap(sc->order); return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[0] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[1] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone)) continue; if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) { wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); goto check_pending; } /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); check_pending: if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_ORDER > S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, bool may_swap) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = may_swap, }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void age_active_anon(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (!total_swap_pages) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* * If a node has no populated zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim; } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging of the anon list, to give * pages a chance to be referenced before reclaiming. All * pages are rotated regardless of classzone as this is * about consistent aging. */ age_active_anon(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(); ret = try_to_freeze(); __fs_reclaim_acquire(); if (ret || kthread_should_stop()) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); for ( ; ; ) { bool ret; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (ret) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ int kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); int ret = 0; if (pgdat->kswapd) return 0; pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state < SYSTEM_RUNNING); pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); pgdat->kswapd = NULL; } return ret; } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * hold mem_hotplug_begin/end(). */ void kswapd_stop(int nid) { struct task_struct *kswapd = NODE_DATA(nid)->kswapd; if (kswapd) { kthread_stop(kswapd); NODE_DATA(nid)->kswapd = NULL; } } static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * These bit locations are exposed in the vm.zone_reclaim_mode sysctl * ABI. New bits are OK, but existing bits can never change. */ #define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ #define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ #define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP * and we also need to be able to write out pages for RECLAIM_WRITE * and RECLAIM_UNMAP. */ noreclaim_flag = memalloc_noreclaim_save(); p->flags |= PF_SWAPWRITE; set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); current->flags &= ~PF_SWAPWRITE; memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (!ret) count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_pages - check pages for evictability and move to * appropriate zone lru list * @pvec: pagevec with lru pages to check * * Checks pages for evictability, if an evictable page is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru pages. */ void check_move_unevictable_pages(struct pagevec *pvec) { struct lruvec *lruvec; struct pglist_data *pgdat = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); int nr_pages; if (PageTransTail(page)) continue; nr_pages = thp_nr_pages(page); pgscanned += nr_pages; if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irq(&pgdat->lru_lock); pgdat = pagepgdat; spin_lock_irq(&pgdat->lru_lock); } lruvec = mem_cgroup_page_lruvec(page, pgdat); if (!PageLRU(page) || !PageUnevictable(page)) continue; if (page_evictable(page)) { enum lru_list lru = page_lru_base_type(page); VM_BUG_ON_PAGE(PageActive(page), page); ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec, lru); pgrescued += nr_pages; } } if (pgdat) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); spin_unlock_irq(&pgdat->lru_lock); } } EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
50 50 50 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 /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG #define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->close_on_exec); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *__fcheck_files(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); if (fd < fdt->max_fds) { fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); } return NULL; } static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return __fcheck_files(files, fd); } /* * Check whether the specified fd has an open file. */ #define fcheck(fd) fcheck_files(current->files, fd) struct task_struct; struct files_struct *get_files_struct(struct task_struct *); void put_files_struct(struct files_struct *fs); void reset_files_struct(struct files_struct *); int unshare_files(struct files_struct **); struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int __alloc_fd(struct files_struct *files, unsigned start, unsigned end, unsigned flags); extern void __fd_install(struct files_struct *files, unsigned int fd, struct file *file); extern int __close_fd(struct files_struct *files, unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern int __close_fd_get_file(unsigned int fd, struct file **res); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_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 #undef TRACE_SYSTEM #define TRACE_SYSTEM qdisc #if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_QDISC_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/pkt_sched.h> #include <net/sch_generic.h> TRACE_EVENT(qdisc_dequeue, TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, int packets, struct sk_buff *skb), TP_ARGS(qdisc, txq, packets, skb), TP_STRUCT__entry( __field( struct Qdisc *, qdisc ) __field(const struct netdev_queue *, txq ) __field( int, packets ) __field( void *, skbaddr ) __field( int, ifindex ) __field( u32, handle ) __field( u32, parent ) __field( unsigned long, txq_state) ), /* skb==NULL indicate packets dequeued was 0, even when packets==1 */ TP_fast_assign( __entry->qdisc = qdisc; __entry->txq = txq; __entry->packets = skb ? packets : 0; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; __entry->parent = qdisc->parent; __entry->txq_state = txq->state; ), TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p", __entry->ifindex, __entry->handle, __entry->parent, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); TRACE_EVENT(qdisc_reset, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q)); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_destroy, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q)); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_create, TP_PROTO(const struct Qdisc_ops *ops, struct net_device *dev, u32 parent), TP_ARGS(ops, dev, parent), TP_STRUCT__entry( __string( dev, dev->name ) __string( kind, ops->id ) __field( u32, parent ) ), TP_fast_assign( __assign_str(dev, dev->name); __assign_str(kind, ops->id); __entry->parent = parent; ), TP_printk("dev=%s kind=%s parent=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent)) ); #endif /* _TRACE_QDISC_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
28 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void update_process_times(int user); extern void xtime_update(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family: read the current time in a multitude of ways, * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones wit * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Returns monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Returns the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * struct ktime_timestanps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp */ struct ktime_timestamps { u64 mono; u64 boot; u64 real; }; /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t raw; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the pointer to the * corresponding clocksource * @cycles: System counter value * @cs: Clocksource corresponding to system counter value. Used by * timekeeping code to verify comparibility of two cycle values */ struct system_counterval_t { u64 cycles; struct clocksource *cs; }; /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* NMI safe mono/boot/realtime timestamps */ extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); #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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) { return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL); } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { return __pte_alloc_one_kernel(mm); } #endif /** * pte_free_kernel - free PTE-level kernel page table page * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { free_page((unsigned long)pte); } /** * __pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocates a page and runs the pgtable_pte_page_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) { struct page *pte; pte = alloc_page(gfp); if (!pte) return NULL; if (!pgtable_pte_page_ctor(pte)) { __free_page(pte); return NULL; } return pte; } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pte_page_ctor(). * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, GFP_PGTABLE_USER); } #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table page * @mm: the mm_struct of the current context * @pte_page: the `struct page` representing the page table */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { pgtable_pte_page_dtor(pte_page); __free_page(pte_page); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate a page for PMD-level page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pmd_page_ctor(). * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; page = alloc_pages(gfp, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { __free_pages(page, 0); return NULL; } return (pmd_t *)page_address(page); } #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate a page for PUD-level page table * @mm: the mm_struct of the current context * * Allocates a page using %GFP_PGTABLE_USER for user context and * %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; return (pud_t *)get_zeroed_page(gfp); } #endif static inline void pud_free(struct mm_struct *mm, pud_t *pud) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); free_page((unsigned long)pud); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { free_page((unsigned long)pgd); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */
3 18 3 3 3 3 3 3 16 16 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writtable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ #define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_DN_RENAME 0x10000000 /* file renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_IN_ONESHOT 0x80000000 /* only send event once */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; unsigned long objectid; /* identifier for queue merges */ }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ /* * Valid fsnotify group priorities. Events are send in order from highest * priority to lowest priority. We default to the lowest priority. */ #define FS_PRIO_0 0 /* normal notifiers, no permissions */ #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t num_marks; /* 1 for each mark and 1 for not being * past the point of no return when freeing * a group */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ unsigned int max_marks; struct user_struct *user; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; default: return NULL; } } enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_PARENT, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; #define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) #define FSNOTIFY_OBJ_TYPE_PARENT_FL (1U << FSNOTIFY_OBJ_TYPE_PARENT) #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) #define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) static inline bool fsnotify_valid_obj_type(unsigned int type) { return (type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int type) { return (iter_info->report_mask & (1U << type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int type) { iter_info->report_mask |= (1U << type); } static inline void fsnotify_iter_set_report_type_mark( struct fsnotify_iter_info *iter_info, int type, struct fsnotify_mark *mark) { iter_info->marks[type] = mark; iter_info->report_mask |= (1U << type); } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_obj_type(type) \ for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached * to. fsnotify_connp_t * is how we refer from connector back to object. */ struct fsnotify_mark_connector; typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { /* Object pointer [lock] */ fsnotify_connp_t *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types to ignore [mark->lock, group->mark_mutex] */ __u32 ignored_mask; #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01 #define FSNOTIFY_MARK_FLAG_ALIVE 0x02 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x04 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following __fsnotify_update_child_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group); /* Get cached fsid of filesystem containing object */ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int type, int allow_dups, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int type, int allow_dups, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int allow_dups) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int allow_dups) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* run all the marks in a group, and clear all of the marks attached to given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event, unsigned long objectid) { INIT_LIST_HEAD(&event->list); event->objectid = objectid; } #else static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 /* SPDX-License-Identifier: GPL-2.0-only */ /* * IEEE802.15.4-2003 specification * * Copyright (C) 2007, 2008 Siemens AG * * Written by: * Pavel Smolenskiy <pavel.smolenskiy@gmail.com> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Maxim Osipov <maxim.osipov@siemens.com> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #ifndef LINUX_IEEE802154_H #define LINUX_IEEE802154_H #include <linux/types.h> #include <linux/random.h> #define IEEE802154_MTU 127 #define IEEE802154_ACK_PSDU_LEN 5 #define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_FCS_LEN 2 #define IEEE802154_MAX_AUTH_TAG_LEN 16 #define IEEE802154_FC_LEN 2 #define IEEE802154_SEQ_LEN 1 /* General MAC frame format: * 2 bytes: Frame Control * 1 byte: Sequence Number * 20 bytes: Addressing fields * 14 bytes: Auxiliary Security Header */ #define IEEE802154_MAX_HEADER_LEN (2 + 1 + 20 + 14) #define IEEE802154_MIN_HEADER_LEN (IEEE802154_ACK_PSDU_LEN - \ IEEE802154_FCS_LEN) #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_UNSPEC 0xfffe #define IEEE802154_EXTENDED_ADDR_LEN 8 #define IEEE802154_SHORT_ADDR_LEN 2 #define IEEE802154_PAN_ID_LEN 2 #define IEEE802154_LIFS_PERIOD 40 #define IEEE802154_SIFS_PERIOD 12 #define IEEE802154_MAX_SIFS_FRAME_SIZE 18 #define IEEE802154_MAX_CHANNEL 26 #define IEEE802154_MAX_PAGE 31 #define IEEE802154_FC_TYPE_BEACON 0x0 /* Frame is beacon */ #define IEEE802154_FC_TYPE_DATA 0x1 /* Frame is data */ #define IEEE802154_FC_TYPE_ACK 0x2 /* Frame is acknowledgment */ #define IEEE802154_FC_TYPE_MAC_CMD 0x3 /* Frame is MAC command */ #define IEEE802154_FC_TYPE_SHIFT 0 #define IEEE802154_FC_TYPE_MASK ((1 << 3) - 1) #define IEEE802154_FC_TYPE(x) ((x & IEEE802154_FC_TYPE_MASK) >> IEEE802154_FC_TYPE_SHIFT) #define IEEE802154_FC_SET_TYPE(v, x) do { \ v = (((v) & ~IEEE802154_FC_TYPE_MASK) | \ (((x) << IEEE802154_FC_TYPE_SHIFT) & IEEE802154_FC_TYPE_MASK)); \ } while (0) #define IEEE802154_FC_SECEN_SHIFT 3 #define IEEE802154_FC_SECEN (1 << IEEE802154_FC_SECEN_SHIFT) #define IEEE802154_FC_FRPEND_SHIFT 4 #define IEEE802154_FC_FRPEND (1 << IEEE802154_FC_FRPEND_SHIFT) #define IEEE802154_FC_ACK_REQ_SHIFT 5 #define IEEE802154_FC_ACK_REQ (1 << IEEE802154_FC_ACK_REQ_SHIFT) #define IEEE802154_FC_INTRA_PAN_SHIFT 6 #define IEEE802154_FC_INTRA_PAN (1 << IEEE802154_FC_INTRA_PAN_SHIFT) #define IEEE802154_FC_SAMODE_SHIFT 14 #define IEEE802154_FC_SAMODE_MASK (3 << IEEE802154_FC_SAMODE_SHIFT) #define IEEE802154_FC_DAMODE_SHIFT 10 #define IEEE802154_FC_DAMODE_MASK (3 << IEEE802154_FC_DAMODE_SHIFT) #define IEEE802154_FC_VERSION_SHIFT 12 #define IEEE802154_FC_VERSION_MASK (3 << IEEE802154_FC_VERSION_SHIFT) #define IEEE802154_FC_VERSION(x) ((x & IEEE802154_FC_VERSION_MASK) >> IEEE802154_FC_VERSION_SHIFT) #define IEEE802154_FC_SAMODE(x) \ (((x) & IEEE802154_FC_SAMODE_MASK) >> IEEE802154_FC_SAMODE_SHIFT) #define IEEE802154_FC_DAMODE(x) \ (((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT) #define IEEE802154_SCF_SECLEVEL_MASK 7 #define IEEE802154_SCF_SECLEVEL_SHIFT 0 #define IEEE802154_SCF_SECLEVEL(x) (x & IEEE802154_SCF_SECLEVEL_MASK) #define IEEE802154_SCF_KEY_ID_MODE_SHIFT 3 #define IEEE802154_SCF_KEY_ID_MODE_MASK (3 << IEEE802154_SCF_KEY_ID_MODE_SHIFT) #define IEEE802154_SCF_KEY_ID_MODE(x) \ ((x & IEEE802154_SCF_KEY_ID_MODE_MASK) >> IEEE802154_SCF_KEY_ID_MODE_SHIFT) #define IEEE802154_SCF_KEY_IMPLICIT 0 #define IEEE802154_SCF_KEY_INDEX 1 #define IEEE802154_SCF_KEY_SHORT_INDEX 2 #define IEEE802154_SCF_KEY_HW_INDEX 3 #define IEEE802154_SCF_SECLEVEL_NONE 0 #define IEEE802154_SCF_SECLEVEL_MIC32 1 #define IEEE802154_SCF_SECLEVEL_MIC64 2 #define IEEE802154_SCF_SECLEVEL_MIC128 3 #define IEEE802154_SCF_SECLEVEL_ENC 4 #define IEEE802154_SCF_SECLEVEL_ENC_MIC32 5 #define IEEE802154_SCF_SECLEVEL_ENC_MIC64 6 #define IEEE802154_SCF_SECLEVEL_ENC_MIC128 7 /* MAC footer size */ #define IEEE802154_MFR_SIZE 2 /* 2 octets */ /* MAC's Command Frames Identifiers */ #define IEEE802154_CMD_ASSOCIATION_REQ 0x01 #define IEEE802154_CMD_ASSOCIATION_RESP 0x02 #define IEEE802154_CMD_DISASSOCIATION_NOTIFY 0x03 #define IEEE802154_CMD_DATA_REQ 0x04 #define IEEE802154_CMD_PANID_CONFLICT_NOTIFY 0x05 #define IEEE802154_CMD_ORPHAN_NOTIFY 0x06 #define IEEE802154_CMD_BEACON_REQ 0x07 #define IEEE802154_CMD_COORD_REALIGN_NOTIFY 0x08 #define IEEE802154_CMD_GTS_REQ 0x09 /* * The return values of MAC operations */ enum { /* * The requested operation was completed successfully. * For a transmission request, this value indicates * a successful transmission. */ IEEE802154_SUCCESS = 0x0, /* The beacon was lost following a synchronization request. */ IEEE802154_BEACON_LOSS = 0xe0, /* * A transmission could not take place due to activity on the * channel, i.e., the CSMA-CA mechanism has failed. */ IEEE802154_CHNL_ACCESS_FAIL = 0xe1, /* The GTS request has been denied by the PAN coordinator. */ IEEE802154_DENINED = 0xe2, /* The attempt to disable the transceiver has failed. */ IEEE802154_DISABLE_TRX_FAIL = 0xe3, /* * The received frame induces a failed security check according to * the security suite. */ IEEE802154_FAILED_SECURITY_CHECK = 0xe4, /* * The frame resulting from secure processing has a length that is * greater than aMACMaxFrameSize. */ IEEE802154_FRAME_TOO_LONG = 0xe5, /* * The requested GTS transmission failed because the specified GTS * either did not have a transmit GTS direction or was not defined. */ IEEE802154_INVALID_GTS = 0xe6, /* * A request to purge an MSDU from the transaction queue was made using * an MSDU handle that was not found in the transaction table. */ IEEE802154_INVALID_HANDLE = 0xe7, /* A parameter in the primitive is out of the valid range.*/ IEEE802154_INVALID_PARAMETER = 0xe8, /* No acknowledgment was received after aMaxFrameRetries. */ IEEE802154_NO_ACK = 0xe9, /* A scan operation failed to find any network beacons.*/ IEEE802154_NO_BEACON = 0xea, /* No response data were available following a request. */ IEEE802154_NO_DATA = 0xeb, /* The operation failed because a short address was not allocated. */ IEEE802154_NO_SHORT_ADDRESS = 0xec, /* * A receiver enable request was unsuccessful because it could not be * completed within the CAP. */ IEEE802154_OUT_OF_CAP = 0xed, /* * A PAN identifier conflict has been detected and communicated to the * PAN coordinator. */ IEEE802154_PANID_CONFLICT = 0xee, /* A coordinator realignment command has been received. */ IEEE802154_REALIGMENT = 0xef, /* The transaction has expired and its information discarded. */ IEEE802154_TRANSACTION_EXPIRED = 0xf0, /* There is no capacity to store the transaction. */ IEEE802154_TRANSACTION_OVERFLOW = 0xf1, /* * The transceiver was in the transmitter enabled state when the * receiver was requested to be enabled. */ IEEE802154_TX_ACTIVE = 0xf2, /* The appropriate key is not available in the ACL. */ IEEE802154_UNAVAILABLE_KEY = 0xf3, /* * A SET/GET request was issued with the identifier of a PIB attribute * that is not supported. */ IEEE802154_UNSUPPORTED_ATTR = 0xf4, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. */ IEEE802154_SCAN_IN_PROGRESS = 0xfc, }; /* frame control handling */ #define IEEE802154_FCTL_FTYPE 0x0003 #define IEEE802154_FCTL_ACKREQ 0x0020 #define IEEE802154_FCTL_SECEN 0x0004 #define IEEE802154_FCTL_INTRA_PAN 0x0040 #define IEEE802154_FCTL_DADDR 0x0c00 #define IEEE802154_FCTL_SADDR 0xc000 #define IEEE802154_FTYPE_DATA 0x0001 #define IEEE802154_FCTL_ADDR_NONE 0x0000 #define IEEE802154_FCTL_DADDR_SHORT 0x0800 #define IEEE802154_FCTL_DADDR_EXTENDED 0x0c00 #define IEEE802154_FCTL_SADDR_SHORT 0x8000 #define IEEE802154_FCTL_SADDR_EXTENDED 0xc000 /* * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder */ static inline int ieee802154_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE802154_FCTL_FTYPE)) == cpu_to_le16(IEEE802154_FTYPE_DATA); } /** * ieee802154_is_secen - check if Security bit is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_secen(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_SECEN); } /** * ieee802154_is_ackreq - check if acknowledgment request bit is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_ackreq(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_ACKREQ); } /** * ieee802154_is_intra_pan - check if intra pan id communication * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_intra_pan(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); } /* * ieee802154_daddr_mode - get daddr mode from fc * @fc: frame control bytes in little-endian byteorder */ static inline __le16 ieee802154_daddr_mode(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_DADDR); } /* * ieee802154_saddr_mode - get saddr mode from fc * @fc: frame control bytes in little-endian byteorder */ static inline __le16 ieee802154_saddr_mode(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_SADDR); } /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: * 0-4 Reserved * 5 MPDU (Acknowledgment) * 6-8 Reserved * 9-127 MPDU * * @len: psdu len with (MHR + payload + MFR) */ static inline bool ieee802154_is_valid_psdu_len(u8 len) { return (len == IEEE802154_ACK_PSDU_LEN || (len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU)); } /** * ieee802154_is_valid_extended_unicast_addr - check if extended addr is valid * @addr: extended addr to check */ static inline bool ieee802154_is_valid_extended_unicast_addr(__le64 addr) { /* Bail out if the address is all zero, or if the group * address bit is set. */ return ((addr != cpu_to_le64(0x0000000000000000ULL)) && !(addr & cpu_to_le64(0x0100000000000000ULL))); } /** * ieee802154_is_broadcast_short_addr - check if short addr is broadcast * @addr: short addr to check */ static inline bool ieee802154_is_broadcast_short_addr(__le16 addr) { return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)); } /** * ieee802154_is_unspec_short_addr - check if short addr is unspecified * @addr: short addr to check */ static inline bool ieee802154_is_unspec_short_addr(__le16 addr) { return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC)); } /** * ieee802154_is_valid_src_short_addr - check if source short address is valid * @addr: short addr to check */ static inline bool ieee802154_is_valid_src_short_addr(__le16 addr) { return !(ieee802154_is_broadcast_short_addr(addr) || ieee802154_is_unspec_short_addr(addr)); } /** * ieee802154_random_extended_addr - generates a random extended address * @addr: extended addr pointer to place the random address */ static inline void ieee802154_random_extended_addr(__le64 *addr) { get_random_bytes(addr, IEEE802154_EXTENDED_ADDR_LEN); /* clear the group bit, and set the locally administered bit */ ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] &= ~0x01; ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] |= 0x02; } #endif /* LINUX_IEEE802154_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 1 3 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 1 2 3 3 3 3 3 3 3 3 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/inode.c * * Written 1992,1993 by Werner Almesberger * VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner * Rewritten for the constant inumbers support by Al Viro * * Fixes: * * Max Cohan: Fixed invalid FSINFO offset when info_sector is 0 */ #include <linux/module.h> #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/vfs.h> #include <linux/seq_file.h> #include <linux/parser.h> #include <linux/uio.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <asm/unaligned.h> #include <linux/random.h> #include <linux/iversion.h> #include "fat.h" #ifndef CONFIG_FAT_DEFAULT_IOCHARSET /* if user don't select VFAT, this is undefined. */ #define CONFIG_FAT_DEFAULT_IOCHARSET "" #endif #define KB_IN_SECTORS 2 /* DOS dates from 1980/1/1 through 2107/12/31 */ #define FAT_DATE_MIN (0<<9 | 1<<5 | 1) #define FAT_DATE_MAX (127<<9 | 12<<5 | 31) #define FAT_TIME_MAX (23<<11 | 59<<5 | 29) /* * A deserialized copy of the on-disk structure laid out in struct * fat_boot_sector. */ struct fat_bios_param_block { u16 fat_sector_size; u8 fat_sec_per_clus; u16 fat_reserved; u8 fat_fats; u16 fat_dir_entries; u16 fat_sectors; u16 fat_fat_length; u32 fat_total_sect; u8 fat16_state; u32 fat16_vol_id; u32 fat32_length; u32 fat32_root_cluster; u16 fat32_info_sector; u8 fat32_state; u32 fat32_vol_id; }; static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE; static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET; static struct fat_floppy_defaults { unsigned nr_sectors; unsigned sec_per_clus; unsigned dir_entries; unsigned media; unsigned fat_length; } floppy_defaults[] = { { .nr_sectors = 160 * KB_IN_SECTORS, .sec_per_clus = 1, .dir_entries = 64, .media = 0xFE, .fat_length = 1, }, { .nr_sectors = 180 * KB_IN_SECTORS, .sec_per_clus = 1, .dir_entries = 64, .media = 0xFC, .fat_length = 2, }, { .nr_sectors = 320 * KB_IN_SECTORS, .sec_per_clus = 2, .dir_entries = 112, .media = 0xFF, .fat_length = 1, }, { .nr_sectors = 360 * KB_IN_SECTORS, .sec_per_clus = 2, .dir_entries = 112, .media = 0xFD, .fat_length = 2, }, }; int fat_add_cluster(struct inode *inode) { int err, cluster; err = fat_alloc_clusters(inode, &cluster, 1); if (err) return err; /* FIXME: this cluster should be added after data of this * cluster is writed */ err = fat_chain_add(inode, cluster, 1); if (err) fat_free_clusters(inode, cluster); return err; } static inline int __fat_get_block(struct inode *inode, sector_t iblock, unsigned long *max_blocks, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); unsigned long mapped_blocks; sector_t phys, last_block; int err, offset; err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (phys) { map_bh(bh_result, sb, phys); *max_blocks = min(mapped_blocks, *max_blocks); return 0; } if (!create) return 0; if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) { fat_fs_error(sb, "corrupted file size (i_pos %lld, %lld)", MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); return -EIO; } last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9); offset = (unsigned long)iblock & (sbi->sec_per_clus - 1); /* * allocate a cluster according to the following. * 1) no more available blocks * 2) not part of fallocate region */ if (!offset && !(iblock < last_block)) { /* TODO: multiple cluster allocation would be desirable. */ err = fat_add_cluster(inode); if (err) return err; } /* available blocks on this cluster */ mapped_blocks = sbi->sec_per_clus - offset; *max_blocks = min(mapped_blocks, *max_blocks); MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits; err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (!phys) { fat_fs_error(sb, "invalid FAT chain (i_pos %lld, last_block %llu)", MSDOS_I(inode)->i_pos, (unsigned long long)last_block); return -EIO; } BUG_ON(*max_blocks != mapped_blocks); set_buffer_new(bh_result); map_bh(bh_result, sb, phys); return 0; } static int fat_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; int err; err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create); if (err) return err; bh_result->b_size = max_blocks << sb->s_blocksize_bits; return 0; } static int fat_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, fat_get_block, wbc); } static int fat_writepages(struct address_space *mapping, struct writeback_control *wbc) { return mpage_writepages(mapping, wbc, fat_get_block); } static int fat_readpage(struct file *file, struct page *page) { return mpage_readpage(page, fat_get_block); } static void fat_readahead(struct readahead_control *rac) { mpage_readahead(rac, fat_get_block); } static void fat_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; if (to > inode->i_size) { truncate_pagecache(inode, inode->i_size); fat_truncate_blocks(inode, inode->i_size); } } static int fat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { int err; *pagep = NULL; err = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); if (err < 0) fat_write_failed(mapping, pos + len); return err; } static int fat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *pagep, void *fsdata) { struct inode *inode = mapping->host; int err; err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); if (err < len) fat_write_failed(mapping, pos + len); if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); MSDOS_I(inode)->i_attrs |= ATTR_ARCH; mark_inode_dirty(inode); } return err; } static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; ssize_t ret; if (iov_iter_rw(iter) == WRITE) { /* * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), * so we need to update the ->mmu_private to block boundary. * * But we must fill the remaining area or hole by nul for * updating ->mmu_private. * * Return 0, and fallback to normal buffered write. */ loff_t size = offset + count; if (MSDOS_I(inode)->mmu_private < size) return 0; } /* * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) fat_write_failed(mapping, offset + count); return ret; } static int fat_get_block_bmap(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; int err; sector_t bmap; unsigned long mapped_blocks; BUG_ON(create != 0); err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true); if (err) return err; if (bmap) { map_bh(bh_result, sb, bmap); max_blocks = min(mapped_blocks, max_blocks); } bh_result->b_size = max_blocks << sb->s_blocksize_bits; return 0; } static sector_t _fat_bmap(struct address_space *mapping, sector_t block) { sector_t blocknr; /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ down_read(&MSDOS_I(mapping->host)->truncate_lock); blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap); up_read(&MSDOS_I(mapping->host)->truncate_lock); return blocknr; } /* * fat_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This is required during truncate to physically zeroout the tail end * of that block so it doesn't yield old data if the file is later grown. * Also, avoid causing failure from fsx for cases of "data past EOF" */ int fat_block_truncate_page(struct inode *inode, loff_t from) { return block_truncate_page(inode->i_mapping, from, fat_get_block); } static const struct address_space_operations fat_aops = { .readpage = fat_readpage, .readahead = fat_readahead, .writepage = fat_writepage, .writepages = fat_writepages, .write_begin = fat_write_begin, .write_end = fat_write_end, .direct_IO = fat_direct_IO, .bmap = _fat_bmap }; /* * New FAT inode stuff. We do the following: * a) i_ino is constant and has nothing with on-disk location. * b) FAT manages its own cache of directory entries. * c) *This* cache is indexed by on-disk location. * d) inode has an associated directory entry, all right, but * it may be unhashed. * e) currently entries are stored within struct inode. That should * change. * f) we deal with races in the following way: * 1. readdir() and lookup() do FAT-dir-cache lookup. * 2. rename() unhashes the F-d-c entry and rehashes it in * a new place. * 3. unlink() and rmdir() unhash F-d-c entry. * 4. fat_write_inode() checks whether the thing is unhashed. * If it is we silently return. If it isn't we do bread(), * check if the location is still valid and retry if it * isn't. Otherwise we do changes. * 5. Spinlock is used to protect hash/unhash/location check/lookup * 6. fat_evict_inode() unhashes the F-d-c entry. * 7. lookup() and readdir() do igrab() if they find a F-d-c entry * and consider negative result as cache miss. */ static void fat_hash_init(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); int i; spin_lock_init(&sbi->inode_hash_lock); for (i = 0; i < FAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); } static inline unsigned long fat_hash(loff_t i_pos) { return hash_32(i_pos, FAT_HASH_BITS); } static void dir_hash_init(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); int i; spin_lock_init(&sbi->dir_hash_lock); for (i = 0; i < FAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->dir_hashtable[i]); } void fat_attach(struct inode *inode, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); if (inode->i_ino != MSDOS_ROOT_INO) { struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); spin_lock(&sbi->inode_hash_lock); MSDOS_I(inode)->i_pos = i_pos; hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head); spin_unlock(&sbi->inode_hash_lock); } /* If NFS support is enabled, cache the mapping of start cluster * to directory inode. This is used during reconnection of * dentries to the filesystem root. */ if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { struct hlist_head *d_head = sbi->dir_hashtable; d_head += fat_dir_hash(MSDOS_I(inode)->i_logstart); spin_lock(&sbi->dir_hash_lock); hlist_add_head(&MSDOS_I(inode)->i_dir_hash, d_head); spin_unlock(&sbi->dir_hash_lock); } } EXPORT_SYMBOL_GPL(fat_attach); void fat_detach(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); spin_lock(&sbi->inode_hash_lock); MSDOS_I(inode)->i_pos = 0; hlist_del_init(&MSDOS_I(inode)->i_fat_hash); spin_unlock(&sbi->inode_hash_lock); if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { spin_lock(&sbi->dir_hash_lock); hlist_del_init(&MSDOS_I(inode)->i_dir_hash); spin_unlock(&sbi->dir_hash_lock); } } EXPORT_SYMBOL_GPL(fat_detach); struct inode *fat_iget(struct super_block *sb, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); struct msdos_inode_info *i; struct inode *inode = NULL; spin_lock(&sbi->inode_hash_lock); hlist_for_each_entry(i, head, i_fat_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_pos != i_pos) continue; inode = igrab(&i->vfs_inode); if (inode) break; } spin_unlock(&sbi->inode_hash_lock); return inode; } static int is_exec(unsigned char *extension) { unsigned char exe_extensions[] = "EXECOMBAT", *walk; for (walk = exe_extensions; *walk; walk += 3) if (!strncmp(extension, walk, 3)) return 1; return 0; } static int fat_calc_dir_size(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int ret, fclus, dclus; inode->i_size = 0; if (MSDOS_I(inode)->i_start == 0) return 0; ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus); if (ret < 0) return ret; inode->i_size = (fclus + 1) << sbi->cluster_bits; return 0; } static int fat_validate_dir(struct inode *dir) { struct super_block *sb = dir->i_sb; if (dir->i_nlink < 2) { /* Directory should have "."/".." entries at least. */ fat_fs_error(sb, "corrupted directory (invalid entries)"); return -EIO; } if (MSDOS_I(dir)->i_start == 0 || MSDOS_I(dir)->i_start == MSDOS_SB(sb)->root_cluster) { /* Directory should point valid cluster. */ fat_fs_error(sb, "corrupted directory (invalid i_start)"); return -EIO; } return 0; } /* doesn't deal with root inode */ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; MSDOS_I(inode)->i_pos = 0; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = prandom_u32(); if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { inode->i_generation &= ~1; inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; MSDOS_I(inode)->i_start = fat_get_start(sbi, de); MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; error = fat_calc_dir_size(inode); if (error < 0) return error; MSDOS_I(inode)->mmu_private = inode->i_size; set_nlink(inode, fat_subdirs(inode)); error = fat_validate_dir(inode); if (error < 0) return error; } else { /* not a directory */ inode->i_generation |= 1; inode->i_mode = fat_make_mode(sbi, de->attr, ((sbi->options.showexec && !is_exec(de->name + 8)) ? S_IRUGO|S_IWUGO : S_IRWXUGO)); MSDOS_I(inode)->i_start = fat_get_start(sbi, de); MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; inode->i_size = le32_to_cpu(de->size); inode->i_op = &fat_file_inode_operations; inode->i_fop = &fat_file_operations; inode->i_mapping->a_ops = &fat_aops; MSDOS_I(inode)->mmu_private = inode->i_size; } if (de->attr & ATTR_SYS) { if (sbi->options.sys_immutable) inode->i_flags |= S_IMMUTABLE; } fat_save_attrs(inode, de->attr); inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0); if (sbi->options.isvfat) { fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime, de->cdate, de->ctime_cs); fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0); } else fat_truncate_time(inode, &inode->i_mtime, S_ATIME|S_CTIME); return 0; } static inline void fat_lock_build_inode(struct msdos_sb_info *sbi) { if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) mutex_lock(&sbi->nfs_build_inode_lock); } static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi) { if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) mutex_unlock(&sbi->nfs_build_inode_lock); } struct inode *fat_build_inode(struct super_block *sb, struct msdos_dir_entry *de, loff_t i_pos) { struct inode *inode; int err; fat_lock_build_inode(MSDOS_SB(sb)); inode = fat_iget(sb, i_pos); if (inode) goto out; inode = new_inode(sb); if (!inode) { inode = ERR_PTR(-ENOMEM); goto out; } inode->i_ino = iunique(sb, MSDOS_ROOT_INO); inode_set_iversion(inode, 1); err = fat_fill_inode(inode, de); if (err) { iput(inode); inode = ERR_PTR(err); goto out; } fat_attach(inode, i_pos); insert_inode_hash(inode); out: fat_unlock_build_inode(MSDOS_SB(sb)); return inode; } EXPORT_SYMBOL_GPL(fat_build_inode); static int __fat_write_inode(struct inode *inode, int wait); static void fat_free_eofblocks(struct inode *inode) { /* Release unwritten fallocated blocks on inode eviction. */ if ((inode->i_blocks << 9) > round_up(MSDOS_I(inode)->mmu_private, MSDOS_SB(inode->i_sb)->cluster_size)) { int err; fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private); /* Fallocate results in updating the i_start/iogstart * for the zero byte file. So, make it return to * original state during evict and commit it to avoid * any corruption on the next access to the cluster * chain for the file. */ err = __fat_write_inode(inode, inode_needs_sync(inode)); if (err) { fat_msg(inode->i_sb, KERN_WARNING, "Failed to " "update on disk inode for unused " "fallocated blocks, inode could be " "corrupted. Please run fsck"); } } } static void fat_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; fat_truncate_blocks(inode, 0); } else fat_free_eofblocks(inode); invalidate_inode_buffers(inode); clear_inode(inode); fat_cache_inval_inode(inode); fat_detach(inode); } static void fat_set_state(struct super_block *sb, unsigned int set, unsigned int force) { struct buffer_head *bh; struct fat_boot_sector *b; struct msdos_sb_info *sbi = MSDOS_SB(sb); /* do not change any thing if mounted read only */ if (sb_rdonly(sb) && !force) return; /* do not change state if fs was dirty */ if (sbi->dirty) { /* warn only on set (mount). */ if (set) fat_msg(sb, KERN_WARNING, "Volume was not properly " "unmounted. Some data may be corrupt. " "Please run fsck."); return; } bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector " "to mark fs as dirty"); return; } b = (struct fat_boot_sector *) bh->b_data; if (is_fat32(sbi)) { if (set) b->fat32.state |= FAT_STATE_DIRTY; else b->fat32.state &= ~FAT_STATE_DIRTY; } else /* fat 16 and 12 */ { if (set) b->fat16.state |= FAT_STATE_DIRTY; else b->fat16.state &= ~FAT_STATE_DIRTY; } mark_buffer_dirty(bh); sync_dirty_buffer(bh); brelse(bh); } static void fat_reset_iocharset(struct fat_mount_options *opts) { if (opts->iocharset != fat_default_iocharset) { /* Note: opts->iocharset can be NULL here */ kfree(opts->iocharset); opts->iocharset = fat_default_iocharset; } } static void delayed_free(struct rcu_head *p) { struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); unload_nls(sbi->nls_disk); unload_nls(sbi->nls_io); fat_reset_iocharset(&sbi->options); kfree(sbi); } static void fat_put_super(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); fat_set_state(sb, 0, 0); iput(sbi->fsinfo_inode); iput(sbi->fat_inode); call_rcu(&sbi->rcu, delayed_free); } static struct kmem_cache *fat_inode_cachep; static struct inode *fat_alloc_inode(struct super_block *sb) { struct msdos_inode_info *ei; ei = kmem_cache_alloc(fat_inode_cachep, GFP_NOFS); if (!ei) return NULL; init_rwsem(&ei->truncate_lock); /* Zeroing to allow iput() even if partial initialized inode. */ ei->mmu_private = 0; ei->i_start = 0; ei->i_logstart = 0; ei->i_attrs = 0; ei->i_pos = 0; return &ei->vfs_inode; } static void fat_free_inode(struct inode *inode) { kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); } static void init_once(void *foo) { struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; spin_lock_init(&ei->cache_lru_lock); ei->nr_caches = 0; ei->cache_valid_id = FAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_fat_hash); INIT_HLIST_NODE(&ei->i_dir_hash); inode_init_once(&ei->vfs_inode); } static int __init fat_init_inodecache(void) { fat_inode_cachep = kmem_cache_create("fat_inode_cache", sizeof(struct msdos_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (fat_inode_cachep == NULL) return -ENOMEM; return 0; } static void __exit fat_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(fat_inode_cachep); } static int fat_remount(struct super_block *sb, int *flags, char *data) { bool new_rdonly; struct msdos_sb_info *sbi = MSDOS_SB(sb); *flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME); sync_filesystem(sb); /* make sure we update state on remount. */ new_rdonly = *flags & SB_RDONLY; if (new_rdonly != sb_rdonly(sb)) { if (new_rdonly) fat_set_state(sb, 0, 0); else fat_set_state(sb, 1, 1); } return 0; } static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); /* If the count of free cluster is still unknown, counts it here. */ if (sbi->free_clusters == -1 || !sbi->free_clus_valid) { int err = fat_count_free_clusters(dentry->d_sb); if (err) return err; } buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = sbi->cluster_size; buf->f_blocks = sbi->max_cluster - FAT_START_ENT; buf->f_bfree = sbi->free_clusters; buf->f_bavail = sbi->free_clusters; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = (sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE; return 0; } static int __fat_write_inode(struct inode *inode, int wait) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct msdos_dir_entry *raw_entry; loff_t i_pos; sector_t blocknr; int err, offset; if (inode->i_ino == MSDOS_ROOT_INO) return 0; retry: i_pos = fat_i_pos_read(sbi, inode); if (!i_pos) return 0; fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); bh = sb_bread(sb, blocknr); if (!bh) { fat_msg(sb, KERN_ERR, "unable to read inode block " "for updating (i_pos %lld)", i_pos); return -EIO; } spin_lock(&sbi->inode_hash_lock); if (i_pos != MSDOS_I(inode)->i_pos) { spin_unlock(&sbi->inode_hash_lock); brelse(bh); goto retry; } raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset]; if (S_ISDIR(inode->i_mode)) raw_entry->size = 0; else raw_entry->size = cpu_to_le32(inode->i_size); raw_entry->attr = fat_make_attrs(inode); fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart); fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time, &raw_entry->date, NULL); if (sbi->options.isvfat) { __le16 atime; fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime, &raw_entry->cdate, &raw_entry->ctime_cs); fat_time_unix2fat(sbi, &inode->i_atime, &atime, &raw_entry->adate, NULL); } spin_unlock(&sbi->inode_hash_lock); mark_buffer_dirty(bh); err = 0; if (wait) err = sync_dirty_buffer(bh); brelse(bh); return err; } static int fat_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; if (inode->i_ino == MSDOS_FSINFO_INO) { struct super_block *sb = inode->i_sb; mutex_lock(&MSDOS_SB(sb)->s_lock); err = fat_clusters_flush(sb); mutex_unlock(&MSDOS_SB(sb)->s_lock); } else err = __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); return err; } int fat_sync_inode(struct inode *inode) { return __fat_write_inode(inode, 1); } EXPORT_SYMBOL_GPL(fat_sync_inode); static int fat_show_options(struct seq_file *m, struct dentry *root); static const struct super_operations fat_sops = { .alloc_inode = fat_alloc_inode, .free_inode = fat_free_inode, .write_inode = fat_write_inode, .evict_inode = fat_evict_inode, .put_super = fat_put_super, .statfs = fat_statfs, .remount_fs = fat_remount, .show_options = fat_show_options, }; static int fat_show_options(struct seq_file *m, struct dentry *root) { struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb); struct fat_mount_options *opts = &sbi->options; int isvfat = opts->isvfat; if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, opts->fs_uid)); if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, opts->fs_gid)); seq_printf(m, ",fmask=%04o", opts->fs_fmask); seq_printf(m, ",dmask=%04o", opts->fs_dmask); if (opts->allow_utime) seq_printf(m, ",allow_utime=%04o", opts->allow_utime); if (sbi->nls_disk) /* strip "cp" prefix from displayed option */ seq_printf(m, ",codepage=%s", &sbi->nls_disk->charset[2]); if (isvfat) { if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); switch (opts->shortname) { case VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=win95"); break; case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT: seq_puts(m, ",shortname=winnt"); break; case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=mixed"); break; case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=lower"); break; default: seq_puts(m, ",shortname=unknown"); break; } } if (opts->name_check != 'n') seq_printf(m, ",check=%c", opts->name_check); if (opts->usefree) seq_puts(m, ",usefree"); if (opts->quiet) seq_puts(m, ",quiet"); if (opts->showexec) seq_puts(m, ",showexec"); if (opts->sys_immutable) seq_puts(m, ",sys_immutable"); if (!isvfat) { if (opts->dotsOK) seq_puts(m, ",dotsOK=yes"); if (opts->nocase) seq_puts(m, ",nocase"); } else { if (opts->utf8) seq_puts(m, ",utf8"); if (opts->unicode_xlate) seq_puts(m, ",uni_xlate"); if (!opts->numtail) seq_puts(m, ",nonumtail"); if (opts->rodir) seq_puts(m, ",rodir"); } if (opts->flush) seq_puts(m, ",flush"); if (opts->tz_set) { if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); else seq_puts(m, ",tz=UTC"); } if (opts->errors == FAT_ERRORS_CONT) seq_puts(m, ",errors=continue"); else if (opts->errors == FAT_ERRORS_PANIC) seq_puts(m, ",errors=panic"); else seq_puts(m, ",errors=remount-ro"); if (opts->nfs == FAT_NFS_NOSTALE_RO) seq_puts(m, ",nfs=nostale_ro"); else if (opts->nfs) seq_puts(m, ",nfs=stale_rw"); if (opts->discard) seq_puts(m, ",discard"); if (opts->dos1xfloppy) seq_puts(m, ",dos1xfloppy"); return 0; } enum { Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_codepage, Opt_usefree, Opt_nocase, Opt_quiet, Opt_showexec, Opt_debug, Opt_immutable, Opt_dots, Opt_nodots, Opt_charset, Opt_shortname_lower, Opt_shortname_win95, Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes, Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes, Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont, Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset, Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, Opt_dos1xfloppy, }; static const match_table_t fat_tokens = { {Opt_check_r, "check=relaxed"}, {Opt_check_s, "check=strict"}, {Opt_check_n, "check=normal"}, {Opt_check_r, "check=r"}, {Opt_check_s, "check=s"}, {Opt_check_n, "check=n"}, {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, {Opt_umask, "umask=%o"}, {Opt_dmask, "dmask=%o"}, {Opt_fmask, "fmask=%o"}, {Opt_allow_utime, "allow_utime=%o"}, {Opt_codepage, "codepage=%u"}, {Opt_usefree, "usefree"}, {Opt_nocase, "nocase"}, {Opt_quiet, "quiet"}, {Opt_showexec, "showexec"}, {Opt_debug, "debug"}, {Opt_immutable, "sys_immutable"}, {Opt_flush, "flush"}, {Opt_tz_utc, "tz=UTC"}, {Opt_time_offset, "time_offset=%d"}, {Opt_err_cont, "errors=continue"}, {Opt_err_panic, "errors=panic"}, {Opt_err_ro, "errors=remount-ro"}, {Opt_discard, "discard"}, {Opt_nfs_stale_rw, "nfs"}, {Opt_nfs_stale_rw, "nfs=stale_rw"}, {Opt_nfs_nostale_ro, "nfs=nostale_ro"}, {Opt_dos1xfloppy, "dos1xfloppy"}, {Opt_obsolete, "conv=binary"}, {Opt_obsolete, "conv=text"}, {Opt_obsolete, "conv=auto"}, {Opt_obsolete, "conv=b"}, {Opt_obsolete, "conv=t"}, {Opt_obsolete, "conv=a"}, {Opt_obsolete, "fat=%u"}, {Opt_obsolete, "blocksize=%u"}, {Opt_obsolete, "cvf_format=%20s"}, {Opt_obsolete, "cvf_options=%100s"}, {Opt_obsolete, "posix"}, {Opt_err, NULL}, }; static const match_table_t msdos_tokens = { {Opt_nodots, "nodots"}, {Opt_nodots, "dotsOK=no"}, {Opt_dots, "dots"}, {Opt_dots, "dotsOK=yes"}, {Opt_err, NULL} }; static const match_table_t vfat_tokens = { {Opt_charset, "iocharset=%s"}, {Opt_shortname_lower, "shortname=lower"}, {Opt_shortname_win95, "shortname=win95"}, {Opt_shortname_winnt, "shortname=winnt"}, {Opt_shortname_mixed, "shortname=mixed"}, {Opt_utf8_no, "utf8=0"}, /* 0 or no or false */ {Opt_utf8_no, "utf8=no"}, {Opt_utf8_no, "utf8=false"}, {Opt_utf8_yes, "utf8=1"}, /* empty or 1 or yes or true */ {Opt_utf8_yes, "utf8=yes"}, {Opt_utf8_yes, "utf8=true"}, {Opt_utf8_yes, "utf8"}, {Opt_uni_xl_no, "uni_xlate=0"}, /* 0 or no or false */ {Opt_uni_xl_no, "uni_xlate=no"}, {Opt_uni_xl_no, "uni_xlate=false"}, {Opt_uni_xl_yes, "uni_xlate=1"}, /* empty or 1 or yes or true */ {Opt_uni_xl_yes, "uni_xlate=yes"}, {Opt_uni_xl_yes, "uni_xlate=true"}, {Opt_uni_xl_yes, "uni_xlate"}, {Opt_nonumtail_no, "nonumtail=0"}, /* 0 or no or false */ {Opt_nonumtail_no, "nonumtail=no"}, {Opt_nonumtail_no, "nonumtail=false"}, {Opt_nonumtail_yes, "nonumtail=1"}, /* empty or 1 or yes or true */ {Opt_nonumtail_yes, "nonumtail=yes"}, {Opt_nonumtail_yes, "nonumtail=true"}, {Opt_nonumtail_yes, "nonumtail"}, {Opt_rodir, "rodir"}, {Opt_err, NULL} }; static int parse_options(struct super_block *sb, char *options, int is_vfat, int silent, int *debug, struct fat_mount_options *opts) { char *p; substring_t args[MAX_OPT_ARGS]; int option; char *iocharset; opts->isvfat = is_vfat; opts->fs_uid = current_uid(); opts->fs_gid = current_gid(); opts->fs_fmask = opts->fs_dmask = current_umask(); opts->allow_utime = -1; opts->codepage = fat_default_codepage; fat_reset_iocharset(opts); if (is_vfat) { opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; opts->rodir = 0; } else { opts->shortname = 0; opts->rodir = 1; } opts->name_check = 'n'; opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK = 0; opts->unicode_xlate = 0; opts->numtail = 1; opts->usefree = opts->nocase = 0; opts->tz_set = 0; opts->nfs = 0; opts->errors = FAT_ERRORS_RO; *debug = 0; opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat; if (!options) goto out; while ((p = strsep(&options, ",")) != NULL) { int token; if (!*p) continue; token = match_token(p, fat_tokens, args); if (token == Opt_err) { if (is_vfat) token = match_token(p, vfat_tokens, args); else token = match_token(p, msdos_tokens, args); } switch (token) { case Opt_check_s: opts->name_check = 's'; break; case Opt_check_r: opts->name_check = 'r'; break; case Opt_check_n: opts->name_check = 'n'; break; case Opt_usefree: opts->usefree = 1; break; case Opt_nocase: if (!is_vfat) opts->nocase = 1; else { /* for backward compatibility */ opts->shortname = VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95; } break; case Opt_quiet: opts->quiet = 1; break; case Opt_showexec: opts->showexec = 1; break; case Opt_debug: *debug = 1; break; case Opt_immutable: opts->sys_immutable = 1; break; case Opt_uid: if (match_int(&args[0], &option)) return -EINVAL; opts->fs_uid = make_kuid(current_user_ns(), option); if (!uid_valid(opts->fs_uid)) return -EINVAL; break; case Opt_gid: if (match_int(&args[0], &option)) return -EINVAL; opts->fs_gid = make_kgid(current_user_ns(), option); if (!gid_valid(opts->fs_gid)) return -EINVAL; break; case Opt_umask: if (match_octal(&args[0], &option)) return -EINVAL; opts->fs_fmask = opts->fs_dmask = option; break; case Opt_dmask: if (match_octal(&args[0], &option)) return -EINVAL; opts->fs_dmask = option; break; case Opt_fmask: if (match_octal(&args[0], &option)) return -EINVAL; opts->fs_fmask = option; break; case Opt_allow_utime: if (match_octal(&args[0], &option)) return -EINVAL; opts->allow_utime = option & (S_IWGRP | S_IWOTH); break; case Opt_codepage: if (match_int(&args[0], &option)) return -EINVAL; opts->codepage = option; break; case Opt_flush: opts->flush = 1; break; case Opt_time_offset: if (match_int(&args[0], &option)) return -EINVAL; /* * GMT+-12 zones may have DST corrections so at least * 13 hours difference is needed. Make the limit 24 * just in case someone invents something unusual. */ if (option < -24 * 60 || option > 24 * 60) return -EINVAL; opts->tz_set = 1; opts->time_offset = option; break; case Opt_tz_utc: opts->tz_set = 1; opts->time_offset = 0; break; case Opt_err_cont: opts->errors = FAT_ERRORS_CONT; break; case Opt_err_panic: opts->errors = FAT_ERRORS_PANIC; break; case Opt_err_ro: opts->errors = FAT_ERRORS_RO; break; case Opt_nfs_stale_rw: opts->nfs = FAT_NFS_STALE_RW; break; case Opt_nfs_nostale_ro: opts->nfs = FAT_NFS_NOSTALE_RO; break; case Opt_dos1xfloppy: opts->dos1xfloppy = 1; break; /* msdos specific */ case Opt_dots: opts->dotsOK = 1; break; case Opt_nodots: opts->dotsOK = 0; break; /* vfat specific */ case Opt_charset: fat_reset_iocharset(opts); iocharset = match_strdup(&args[0]); if (!iocharset) return -ENOMEM; opts->iocharset = iocharset; break; case Opt_shortname_lower: opts->shortname = VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95; break; case Opt_shortname_win95: opts->shortname = VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95; break; case Opt_shortname_winnt: opts->shortname = VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT; break; case Opt_shortname_mixed: opts->shortname = VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95; break; case Opt_utf8_no: /* 0 or no or false */ opts->utf8 = 0; break; case Opt_utf8_yes: /* empty or 1 or yes or true */ opts->utf8 = 1; break; case Opt_uni_xl_no: /* 0 or no or false */ opts->unicode_xlate = 0; break; case Opt_uni_xl_yes: /* empty or 1 or yes or true */ opts->unicode_xlate = 1; break; case Opt_nonumtail_no: /* 0 or no or false */ opts->numtail = 1; /* negated option */ break; case Opt_nonumtail_yes: /* empty or 1 or yes or true */ opts->numtail = 0; /* negated option */ break; case Opt_rodir: opts->rodir = 1; break; case Opt_discard: opts->discard = 1; break; /* obsolete mount options */ case Opt_obsolete: fat_msg(sb, KERN_INFO, "\"%s\" option is obsolete, " "not supported now", p); break; /* unknown option */ default: if (!silent) { fat_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" " "or missing value", p); } return -EINVAL; } } out: /* UTF-8 doesn't provide FAT semantics */ if (!strcmp(opts->iocharset, "utf8")) { fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset" " for FAT filesystems, filesystem will be " "case sensitive!"); } /* If user doesn't specify allow_utime, it's initialized from dmask. */ if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH); if (opts->unicode_xlate) opts->utf8 = 0; if (opts->nfs == FAT_NFS_NOSTALE_RO) { sb->s_flags |= SB_RDONLY; sb->s_export_op = &fat_export_ops_nostale; } return 0; } static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = 0; inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; if (is_fat32(sbi)) { MSDOS_I(inode)->i_start = sbi->root_cluster; error = fat_calc_dir_size(inode); if (error < 0) return error; } else { MSDOS_I(inode)->i_start = 0; inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry); } inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; MSDOS_I(inode)->i_logstart = 0; MSDOS_I(inode)->mmu_private = inode->i_size; fat_save_attrs(inode, ATTR_DIR); inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0; inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0; set_nlink(inode, fat_subdirs(inode)+2); return 0; } static unsigned long calc_fat_clusters(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); /* Divide first to avoid overflow */ if (!is_fat12(sbi)) { unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; return ent_per_sec * sbi->fat_length; } return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; } static bool fat_bpb_is_zero(struct fat_boot_sector *b) { if (get_unaligned_le16(&b->sector_size)) return false; if (b->sec_per_clus) return false; if (b->reserved) return false; if (b->fats) return false; if (get_unaligned_le16(&b->dir_entries)) return false; if (get_unaligned_le16(&b->sectors)) return false; if (b->media) return false; if (b->fat_length) return false; if (b->secs_track) return false; if (b->heads) return false; return true; } static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b, int silent, struct fat_bios_param_block *bpb) { int error = -EINVAL; /* Read in BPB ... */ memset(bpb, 0, sizeof(*bpb)); bpb->fat_sector_size = get_unaligned_le16(&b->sector_size); bpb->fat_sec_per_clus = b->sec_per_clus; bpb->fat_reserved = le16_to_cpu(b->reserved); bpb->fat_fats = b->fats; bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries); bpb->fat_sectors = get_unaligned_le16(&b->sectors); bpb->fat_fat_length = le16_to_cpu(b->fat_length); bpb->fat_total_sect = le32_to_cpu(b->total_sect); bpb->fat16_state = b->fat16.state; bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id); bpb->fat32_length = le32_to_cpu(b->fat32.length); bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster); bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector); bpb->fat32_state = b->fat32.state; bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id); /* Validate this looks like a FAT filesystem BPB */ if (!bpb->fat_reserved) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of reserved sectors"); goto out; } if (!bpb->fat_fats) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); goto out; } /* * Earlier we checked here that b->secs_track and b->head are nonzero, * but it turns out valid FAT filesystems can have zero there. */ if (!fat_valid_media(b->media)) { if (!silent) fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", (unsigned)b->media); goto out; } if (!is_power_of_2(bpb->fat_sector_size) || (bpb->fat_sector_size < 512) || (bpb->fat_sector_size > 4096)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus logical sector size %u", (unsigned)bpb->fat_sector_size); goto out; } if (!is_power_of_2(bpb->fat_sec_per_clus)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", (unsigned)bpb->fat_sec_per_clus); goto out; } if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of FAT sectors"); goto out; } error = 0; out: return error; } static int fat_read_static_bpb(struct super_block *sb, struct fat_boot_sector *b, int silent, struct fat_bios_param_block *bpb) { static const char *notdos1x = "This doesn't look like a DOS 1.x volume"; struct fat_floppy_defaults *fdefaults = NULL; int error = -EINVAL; sector_t bd_sects; unsigned i; bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE; /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */ if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) { if (!silent) fat_msg(sb, KERN_ERR, "%s; no bootstrapping code", notdos1x); goto out; } /* * If any value in this region is non-zero, it isn't archaic * DOS. */ if (!fat_bpb_is_zero(b)) { if (!silent) fat_msg(sb, KERN_ERR, "%s; DOS 2.x BPB is non-zero", notdos1x); goto out; } for (i = 0; i < ARRAY_SIZE(floppy_defaults); i++) { if (floppy_defaults[i].nr_sectors == bd_sects) { fdefaults = &floppy_defaults[i]; break; } } if (fdefaults == NULL) { if (!silent) fat_msg(sb, KERN_WARNING, "This looks like a DOS 1.x volume, but isn't a recognized floppy size (%llu sectors)", (u64)bd_sects); goto out; } if (!silent) fat_msg(sb, KERN_INFO, "This looks like a DOS 1.x volume; assuming default BPB values"); memset(bpb, 0, sizeof(*bpb)); bpb->fat_sector_size = SECTOR_SIZE; bpb->fat_sec_per_clus = fdefaults->sec_per_clus; bpb->fat_reserved = 1; bpb->fat_fats = 2; bpb->fat_dir_entries = fdefaults->dir_entries; bpb->fat_sectors = fdefaults->nr_sectors; bpb->fat_fat_length = fdefaults->fat_length; error = 0; out: return error; } /* * Read the super block of an MS-DOS FS. */ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, void (*setup)(struct super_block *)) { struct inode *root_inode = NULL, *fat_inode = NULL; struct inode *fsinfo_inode = NULL; struct buffer_head *bh; struct fat_bios_param_block bpb; struct msdos_sb_info *sbi; u16 logical_sector_size; u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; int debug; long error; char buf[50]; struct timespec64 ts; /* * GFP_KERNEL is ok here, because while we do hold the * superblock lock, memory pressure can't call back into * the filesystem, since we're only just about to mount * it and have no inodes etc active! */ sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; sb->s_flags |= SB_NODIRATIME; sb->s_magic = MSDOS_SUPER_MAGIC; sb->s_op = &fat_sops; sb->s_export_op = &fat_export_ops; /* * fat timestamps are complex and truncated by fat itself, so * we set 1 here to be fast */ sb->s_time_gran = 1; mutex_init(&sbi->nfs_build_inode_lock); ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); error = parse_options(sb, data, isvfat, silent, &debug, &sbi->options); if (error) goto out_fail; setup(sb); /* flavour-specific stuff that needs options */ error = -EIO; sb_min_blocksize(sb, 512); bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector"); goto out_fail; } error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, &bpb); if (error == -EINVAL && sbi->options.dos1xfloppy) error = fat_read_static_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, &bpb); brelse(bh); if (error == -EINVAL) goto out_invalid; else if (error) goto out_fail; logical_sector_size = bpb.fat_sector_size; sbi->sec_per_clus = bpb.fat_sec_per_clus; error = -EIO; if (logical_sector_size < sb->s_blocksize) { fat_msg(sb, KERN_ERR, "logical sector size too small for device" " (logical sector size = %u)", logical_sector_size); goto out_fail; } if (logical_sector_size > sb->s_blocksize) { struct buffer_head *bh_resize; if (!sb_set_blocksize(sb, logical_sector_size)) { fat_msg(sb, KERN_ERR, "unable to set blocksize %u", logical_sector_size); goto out_fail; } /* Verify that the larger boot sector is fully readable */ bh_resize = sb_bread(sb, 0); if (bh_resize == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector" " (logical sector size = %lu)", sb->s_blocksize); goto out_fail; } brelse(bh_resize); } mutex_init(&sbi->s_lock); sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus; sbi->cluster_bits = ffs(sbi->cluster_size) - 1; sbi->fats = bpb.fat_fats; sbi->fat_bits = 0; /* Don't know yet */ sbi->fat_start = bpb.fat_reserved; sbi->fat_length = bpb.fat_fat_length; sbi->root_cluster = 0; sbi->free_clusters = -1; /* Don't know yet */ sbi->free_clus_valid = 0; sbi->prev_free = FAT_START_ENT; sb->s_maxbytes = 0xffffffff; fat_time_fat2unix(sbi, &ts, 0, cpu_to_le16(FAT_DATE_MIN), 0); sb->s_time_min = ts.tv_sec; fat_time_fat2unix(sbi, &ts, cpu_to_le16(FAT_TIME_MAX), cpu_to_le16(FAT_DATE_MAX), 0); sb->s_time_max = ts.tv_sec; if (!sbi->fat_length && bpb.fat32_length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; sbi->fat_length = bpb.fat32_length; sbi->root_cluster = bpb.fat32_root_cluster; /* MC - if info_sector is 0, don't multiply by 0 */ sbi->fsinfo_sector = bpb.fat32_info_sector; if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; fsinfo_bh = sb_bread(sb, sbi->fsinfo_sector); if (fsinfo_bh == NULL) { fat_msg(sb, KERN_ERR, "bread failed, FSINFO block" " (sector = %lu)", sbi->fsinfo_sector); goto out_fail; } fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; if (!IS_FSINFO(fsinfo)) { fat_msg(sb, KERN_WARNING, "Invalid FSINFO signature: " "0x%08x, 0x%08x (sector = %lu)", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); } else { if (sbi->options.usefree) sbi->free_clus_valid = 1; sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters); sbi->prev_free = le32_to_cpu(fsinfo->next_cluster); } brelse(fsinfo_bh); } /* interpret volume ID as a little endian 32 bit integer */ if (is_fat32(sbi)) sbi->vol_id = bpb.fat32_vol_id; else /* fat 16 or 12 */ sbi->vol_id = bpb.fat16_vol_id; sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry); sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1; sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length; sbi->dir_entries = bpb.fat_dir_entries; if (sbi->dir_entries & (sbi->dir_per_block - 1)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of directory entries" " (%u)", sbi->dir_entries); goto out_invalid; } rootdir_sectors = sbi->dir_entries * sizeof(struct msdos_dir_entry) / sb->s_blocksize; sbi->data_start = sbi->dir_start + rootdir_sectors; total_sectors = bpb.fat_sectors; if (total_sectors == 0) total_sectors = bpb.fat_total_sect; total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; if (!is_fat32(sbi)) sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ if (is_fat32(sbi)) sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; else /* fat 16 or 12 */ sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY; /* check that FAT table does not overflow */ fat_clusters = calc_fat_clusters(sb); total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); if (total_clusters > max_fat(sb)) { if (!silent) fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", total_clusters); goto out_invalid; } sbi->max_cluster = total_clusters + FAT_START_ENT; /* check the free_clusters, it's not necessarily correct */ if (sbi->free_clusters != -1 && sbi->free_clusters > total_clusters) sbi->free_clusters = -1; /* check the prev_free, it's not necessarily correct */ sbi->prev_free %= sbi->max_cluster; if (sbi->prev_free < FAT_START_ENT) sbi->prev_free = FAT_START_ENT; /* set up enough so that it can read an inode */ fat_hash_init(sb); dir_hash_init(sb); fat_ent_access_init(sb); /* * The low byte of the first FAT entry must have the same value as * the media field of the boot sector. But in real world, too many * devices are writing wrong values. So, removed that validity check. * * The removed check compared the first FAT entry to a value dependent * on the media field like this: * == (0x0F00 | media), for FAT12 * == (0XFF00 | media), for FAT16 * == (0x0FFFFF | media), for FAT32 */ error = -EINVAL; sprintf(buf, "cp%d", sbi->options.codepage); sbi->nls_disk = load_nls(buf); if (!sbi->nls_disk) { fat_msg(sb, KERN_ERR, "codepage %s not found", buf); goto out_fail; } /* FIXME: utf8 is using iocharset for upper/lower conversion */ if (sbi->options.isvfat) { sbi->nls_io = load_nls(sbi->options.iocharset); if (!sbi->nls_io) { fat_msg(sb, KERN_ERR, "IO charset %s not found", sbi->options.iocharset); goto out_fail; } } error = -ENOMEM; fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); root_inode = new_inode(sb); if (!root_inode) goto out_fail; root_inode->i_ino = MSDOS_ROOT_INO; inode_set_iversion(root_inode, 1); error = fat_read_root(root_inode); if (error < 0) { iput(root_inode); goto out_fail; } error = -ENOMEM; insert_inode_hash(root_inode); fat_attach(root_inode, 0); sb->s_root = d_make_root(root_inode); if (!sb->s_root) { fat_msg(sb, KERN_ERR, "get root inode failed"); goto out_fail; } if (sbi->options.discard) { struct request_queue *q = bdev_get_queue(sb->s_bdev); if (!blk_queue_discard(q)) fat_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but " "the device does not support discard"); } fat_set_state(sb, 1, 0); return 0; out_invalid: error = -EINVAL; if (!silent) fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); out_fail: if (fsinfo_inode) iput(fsinfo_inode); if (fat_inode) iput(fat_inode); unload_nls(sbi->nls_io); unload_nls(sbi->nls_disk); fat_reset_iocharset(&sbi->options); sb->s_fs_info = NULL; kfree(sbi); return error; } EXPORT_SYMBOL_GPL(fat_fill_super); /* * helper function for fat_flush_inodes. This writes both the inode * and the file data blocks, waiting for in flight data blocks before * the start of the call. It does not wait for any io started * during the call */ static int writeback_inode(struct inode *inode) { int ret; /* if we used wait=1, sync_inode_metadata waits for the io for the * inode to finish. So wait=0 is sent down to sync_inode_metadata * and filemap_fdatawrite is used for the data blocks */ ret = sync_inode_metadata(inode, 0); if (!ret) ret = filemap_fdatawrite(inode->i_mapping); return ret; } /* * write data and metadata corresponding to i1 and i2. The io is * started but we do not wait for any of it to finish. * * filemap_flush is used for the block device, so if there is a dirty * page for a block already in flight, we will not wait and start the * io over again */ int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2) { int ret = 0; if (!MSDOS_SB(sb)->options.flush) return 0; if (i1) ret = writeback_inode(i1); if (!ret && i2) ret = writeback_inode(i2); if (!ret) { struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; ret = filemap_flush(mapping); } return ret; } EXPORT_SYMBOL_GPL(fat_flush_inodes); static int __init init_fat_fs(void) { int err; err = fat_cache_init(); if (err) return err; err = fat_init_inodecache(); if (err) goto failed; return 0; failed: fat_cache_destroy(); return err; } static void __exit exit_fat_fs(void) { fat_cache_destroy(); fat_destroy_inodecache(); } module_init(init_fat_fs) module_exit(exit_fat_fs) MODULE_LICENSE("GPL");
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MATH64_H #define _LINUX_MATH64_H #include <linux/types.h> #include <vdso/math64.h> #include <asm/div64.h> #if BITS_PER_LONG == 64 #define div64_long(x, y) div64_s64((x), (y)) #define div64_ul(x, y) div64_u64((x), (y)) /** * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder * @dividend: unsigned 64bit dividend * @divisor: unsigned 32bit divisor * @remainder: pointer to unsigned 32bit remainder * * Return: sets ``*remainder``, then returns dividend / divisor * * This is commonly provided by 32bit archs to provide an optimized 64bit * divide. */ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) { *remainder = dividend % divisor; return dividend / divisor; } /* * div_s64_rem - signed 64bit divide with 32bit divisor with remainder * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor * @remainder: pointer to signed 32bit remainder * * Return: sets ``*remainder``, then returns dividend / divisor */ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) { *remainder = dividend % divisor; return dividend / divisor; } /* * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor * @remainder: pointer to unsigned 64bit remainder * * Return: sets ``*remainder``, then returns dividend / divisor */ static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) { *remainder = dividend % divisor; return dividend / divisor; } /* * div64_u64 - unsigned 64bit divide with 64bit divisor * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor * * Return: dividend / divisor */ static inline u64 div64_u64(u64 dividend, u64 divisor) { return dividend / divisor; } /* * div64_s64 - signed 64bit divide with 64bit divisor * @dividend: signed 64bit dividend * @divisor: signed 64bit divisor * * Return: dividend / divisor */ static inline s64 div64_s64(s64 dividend, s64 divisor) { return dividend / divisor; } #elif BITS_PER_LONG == 32 #define div64_long(x, y) div_s64((x), (y)) #define div64_ul(x, y) div_u64((x), (y)) #ifndef div_u64_rem static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) { *remainder = do_div(dividend, divisor); return dividend; } #endif #ifndef div_s64_rem extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder); #endif #ifndef div64_u64_rem extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder); #endif #ifndef div64_u64 extern u64 div64_u64(u64 dividend, u64 divisor); #endif #ifndef div64_s64 extern s64 div64_s64(s64 dividend, s64 divisor); #endif #endif /* BITS_PER_LONG */ /** * div_u64 - unsigned 64bit divide with 32bit divisor * @dividend: unsigned 64bit dividend * @divisor: unsigned 32bit divisor * * This is the most common 64bit divide and should be used if possible, * as many 32bit archs can optimize this variant better than a full 64bit * divide. */ #ifndef div_u64 static inline u64 div_u64(u64 dividend, u32 divisor) { u32 remainder; return div_u64_rem(dividend, divisor, &remainder); } #endif /** * div_s64 - signed 64bit divide with 32bit divisor * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor */ #ifndef div_s64 static inline s64 div_s64(s64 dividend, s32 divisor) { s32 remainder; return div_s64_rem(dividend, divisor, &remainder); } #endif u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder); #ifndef mul_u32_u32 /* * Many a GCC version messes this up and generates a 64x64 mult :-( */ static inline u64 mul_u32_u32(u32 a, u32 b) { return (u64)a * b; } #endif #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) #ifndef mul_u64_u32_shr static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { return (u64)(((unsigned __int128)a * mul) >> shift); } #endif /* mul_u64_u32_shr */ #ifndef mul_u64_u64_shr static inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) { return (u64)(((unsigned __int128)a * mul) >> shift); } #endif /* mul_u64_u64_shr */ #else #ifndef mul_u64_u32_shr static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { u32 ah, al; u64 ret; al = a; ah = a >> 32; ret = mul_u32_u32(al, mul) >> shift; if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); return ret; } #endif /* mul_u64_u32_shr */ #ifndef mul_u64_u64_shr static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) { union { u64 ll; struct { #ifdef __BIG_ENDIAN u32 high, low; #else u32 low, high; #endif } l; } rl, rm, rn, rh, a0, b0; u64 c; a0.ll = a; b0.ll = b; rl.ll = mul_u32_u32(a0.l.low, b0.l.low); rm.ll = mul_u32_u32(a0.l.low, b0.l.high); rn.ll = mul_u32_u32(a0.l.high, b0.l.low); rh.ll = mul_u32_u32(a0.l.high, b0.l.high); /* * Each of these lines computes a 64-bit intermediate result into "c", * starting at bits 32-95. The low 32-bits go into the result of the * multiplication, the high 32-bits are carried into the next step. */ rl.l.high = c = (u64)rl.l.high + rm.l.low + rn.l.low; rh.l.low = c = (c >> 32) + rm.l.high + rn.l.high + rh.l.low; rh.l.high = (c >> 32) + rh.l.high; /* * The 128-bit result of the multiplication is in rl.ll and rh.ll, * shift it right and throw away the high part of the result. */ if (shift == 0) return rl.ll; if (shift < 64) return (rl.ll >> shift) | (rh.ll << (64 - shift)); return rh.ll >> (shift & 63); } #endif /* mul_u64_u64_shr */ #endif #ifndef mul_u64_u32_div static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) { union { u64 ll; struct { #ifdef __BIG_ENDIAN u32 high, low; #else u32 low, high; #endif } l; } u, rl, rh; u.ll = a; rl.ll = mul_u32_u32(u.l.low, mul); rh.ll = mul_u32_u32(u.l.high, mul) + rl.l.high; /* Bits 32-63 of the result will be in rh.l.low. */ rl.l.high = do_div(rh.ll, divisor); /* Bits 0-31 of the result will be in rl.l.low. */ do_div(rl.ll, divisor); rl.l.high = rh.l.low; return rl.ll; } #endif /* mul_u64_u32_div */ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); #define DIV64_U64_ROUND_UP(ll, d) \ ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) /** * DIV64_U64_ROUND_CLOSEST - unsigned 64bit divide with 64bit divisor rounded to nearest integer * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor * * Divide unsigned 64bit dividend by unsigned 64bit divisor * and round to closest integer. * * Return: dividend / divisor rounded to nearest integer */ #define DIV64_U64_ROUND_CLOSEST(dividend, divisor) \ ({ u64 _tmp = (divisor); div64_u64((dividend) + _tmp / 2, _tmp); }) /* * DIV_S64_ROUND_CLOSEST - signed 64bit divide with 32bit divisor rounded to nearest integer * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor * * Divide signed 64bit dividend by signed 32bit divisor * and round to closest integer. * * Return: dividend / divisor rounded to nearest integer */ #define DIV_S64_ROUND_CLOSEST(dividend, divisor)( \ { \ s64 __x = (dividend); \ s32 __d = (divisor); \ ((__x > 0) == (__d > 0)) ? \ div_s64((__x + (__d / 2)), __d) : \ div_s64((__x - (__d / 2)), __d); \ } \ ) #endif /* _LINUX_MATH64_H */
3 3 3 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 // SPDX-License-Identifier: GPL-2.0 /* * Workingset detection * * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner */ #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/writeback.h> #include <linux/shmem_fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/swap.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/mm.h> /* * Double CLOCK lists * * Per node, two clock lists are maintained for file pages: the * inactive and the active list. Freshly faulted pages start out at * the head of the inactive list and page reclaim scans pages from the * tail. Pages that are accessed multiple times on the inactive list * are promoted to the active list, to protect them from reclaim, * whereas active pages are demoted to the inactive list when the * active list grows too big. * * fault ------------------------+ * | * +--------------+ | +-------------+ * reclaim <- | inactive | <-+-- demotion | active | <--+ * +--------------+ +-------------+ | * | | * +-------------- promotion ------------------+ * * * Access frequency and refault distance * * A workload is thrashing when its pages are frequently used but they * are evicted from the inactive list every time before another access * would have promoted them to the active list. * * In cases where the average access distance between thrashing pages * is bigger than the size of memory there is nothing that can be * done - the thrashing set could never fit into memory under any * circumstance. * * However, the average access distance could be bigger than the * inactive list, yet smaller than the size of memory. In this case, * the set could fit into memory if it weren't for the currently * active pages - which may be used more, hopefully less frequently: * * +-memory available to cache-+ * | | * +-inactive------+-active----+ * a b | c d e f g h i | J K L M N | * +---------------+-----------+ * * It is prohibitively expensive to accurately track access frequency * of pages. But a reasonable approximation can be made to measure * thrashing on the inactive list, after which refaulting pages can be * activated optimistically to compete with the existing active pages. * * Approximating inactive page access frequency - Observations: * * 1. When a page is accessed for the first time, it is added to the * head of the inactive list, slides every existing inactive page * towards the tail by one slot, and pushes the current tail page * out of memory. * * 2. When a page is accessed for the second time, it is promoted to * the active list, shrinking the inactive list by one slot. This * also slides all inactive pages that were faulted into the cache * more recently than the activated page towards the tail of the * inactive list. * * Thus: * * 1. The sum of evictions and activations between any two points in * time indicate the minimum number of inactive pages accessed in * between. * * 2. Moving one inactive page N page slots towards the tail of the * list requires at least N inactive page accesses. * * Combining these: * * 1. When a page is finally evicted from memory, the number of * inactive pages accessed while the page was in cache is at least * the number of page slots on the inactive list. * * 2. In addition, measuring the sum of evictions and activations (E) * at the time of a page's eviction, and comparing it to another * reading (R) at the time the page faults back into memory tells * the minimum number of accesses while the page was not cached. * This is called the refault distance. * * Because the first access of the page was the fault and the second * access the refault, we combine the in-cache distance with the * out-of-cache distance to get the complete minimum access distance * of this page: * * NR_inactive + (R - E) * * And knowing the minimum access distance of a page, we can easily * tell if the page would be able to stay in cache assuming all page * slots in the cache were available: * * NR_inactive + (R - E) <= NR_inactive + NR_active * * which can be further simplified to * * (R - E) <= NR_active * * Put into words, the refault distance (out-of-cache) can be seen as * a deficit in inactive list space (in-cache). If the inactive list * had (R - E) more page slots, the page would not have been evicted * in between accesses, but activated instead. And on a full system, * the only thing eating into inactive list space is active pages. * * * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given * time there is actually a good chance that pages on the active list * are no longer in active use. * * So when a refault distance of (R - E) is observed and there are at * least (R - E) active pages, the refaulting page is activated * optimistically in the hope that (R - E) active pages are actually * used less frequently than the refaulting page - or even not used at * all anymore. * * That means if inactive cache is refaulting with a suitable refault * distance, we assume the cache workingset is transitioning and put * pressure on the current active list. * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. * * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * * Refaulting active pages * * If on the other hand the refaulting pages have recently been * deactivated, it means that the active list is no longer protecting * actively used cache from reclaim. The cache is NOT transitioning to * a different workingset; the existing workingset is thrashing in the * space allocated to the page cache. * * * Implementation * * For each node's LRU lists, a counter for inactive evictions and * activations is maintained (node->nonresident_age). * * On eviction, a snapshot of this counter (along with some bits to * identify the node) is stored in the now empty page cache * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible * refault distance will immediately activate the refaulting page. */ #define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* * Eviction timestamps need to be able to cover the full range of * actionable refaults. However, bits are tight in the xarray * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group * evictions into coarser buckets by shaving off lower timestamp bits. */ static unsigned int bucket_order __read_mostly; static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, bool workingset) { eviction >>= bucket_order; eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; eviction = (eviction << 1) | workingset; return xa_mk_value(eviction); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, unsigned long *evictionp, bool *workingsetp) { unsigned long entry = xa_to_value(shadow); int memcgid, nid; bool workingset; workingset = entry & 1; entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); entry >>= MEM_CGROUP_ID_SHIFT; *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; *workingsetp = workingset; } /** * workingset_age_nonresident - age non-resident entries as LRU ages * @lruvec: the lruvec that was aged * @nr_pages: the number of pages to count * * As in-memory pages are aged, non-resident pages need to be aged as * well, in order for the refault distances later on to be comparable * to the in-memory dimensions. This function allows reclaim and LRU * operations to drive the non-resident aging along in parallel. */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) { /* * Reclaiming a cgroup means reclaiming all its children in a * round-robin fashion. That means that each cgroup has an LRU * order that is composed of the LRU orders of its child * cgroups; and every page has an LRU position not just in the * cgroup that owns it, but in all of that group's ancestors. * * So when the physical inactive list of a leaf cgroup ages, * the virtual inactive lists of all its parents, including * the root cgroup's, age as well. */ do { atomic_long_add(nr_pages, &lruvec->nonresident_age); } while ((lruvec = parent_lruvec(lruvec))); } /** * workingset_eviction - note the eviction of a page from memory * @target_memcg: the cgroup that is causing the reclaim * @page: the page being evicted * * Returns a shadow entry to be stored in @page->mapping->i_pages in place * of the evicted @page so that a later refault can be detected. */ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) { struct pglist_data *pgdat = page_pgdat(page); unsigned long eviction; struct lruvec *lruvec; int memcgid; /* Page is fully exclusive and pins page->mem_cgroup */ VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); lruvec = mem_cgroup_lruvec(target_memcg, pgdat); workingset_age_nonresident(lruvec, thp_nr_pages(page)); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); eviction = atomic_long_read(&lruvec->nonresident_age); return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } /** * workingset_refault - evaluate the refault of a previously evicted page * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node and the memcg whose memory * pressure caused the eviction. */ void workingset_refault(struct page *page, void *shadow) { bool file = page_is_file_lru(page); struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; unsigned long refault_distance; unsigned long workingset_size; struct pglist_data *pgdat; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; bool workingset; int memcgid; unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might * have been deleted since the page's eviction. * * Note that in rare events the ID could have been recycled * for a new cgroup that refaults a shared page. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging * algorithm's job to shake out the minimum access frequency * for the active cache. * * XXX: On !CONFIG_MEMCG, this will always return NULL; it * would be better if the root_mem_cgroup existed in all * configurations instead. */ eviction_memcg = mem_cgroup_from_id(memcgid); if (!mem_cgroup_disabled() && !eviction_memcg) goto out; eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); refault = atomic_long_read(&eviction_lruvec->nonresident_age); /* * Calculate the refault distance * * The unsigned subtraction here gives an accurate distance * across nonresident_age overflows in most cases. There is a * special case: usually, shadow entries have a short lifetime * and are either refaulted or reclaimed along with the inode * before they get too old. But it is not impossible for the * nonresident_age to lap a shadow entry in the field, which * can then result in a false small refault distance, leading * to a false activation should this old entry actually * refault again. However, earlier kernels used to deactivate * unconditionally with *every* reclaim invocation for the * longest time, so the occasional inappropriate activation * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; /* * The activation decision for this page is made at the level * where the eviction occurred, as that is where the LRU order * during page reclaim is being determined. * * However, the cgroup that will own the page is the one that * is actually experiencing the refault event. */ memcg = page_memcg(page); lruvec = mem_cgroup_lruvec(memcg, pgdat); inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if * all the memory was available to the workingset. Whether * workingset competition needs to consider anon or not depends * on having swap. */ workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); if (!file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_FILE); } if (mem_cgroup_get_nr_swap_pages(memcg) > 0) { workingset_size += lruvec_page_state(eviction_lruvec, NR_ACTIVE_ANON); if (file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_ANON); } } if (refault_distance > workingset_size) goto out; SetPageActive(page); workingset_age_nonresident(lruvec, thp_nr_pages(page)); inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file); /* Page was active prior to eviction */ if (workingset) { SetPageWorkingset(page); /* XXX: Move to lru_cache_add() when it supports new vs putback */ spin_lock_irq(&page_pgdat(page)->lru_lock); lru_note_cost_page(page); spin_unlock_irq(&page_pgdat(page)->lru_lock); inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file); } out: rcu_read_unlock(); } /** * workingset_activation - note a page activation * @page: page that is being activated */ void workingset_activation(struct page *page) { struct mem_cgroup *memcg; struct lruvec *lruvec; rcu_read_lock(); /* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. * * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); workingset_age_nonresident(lruvec, thp_nr_pages(page)); out: rcu_read_unlock(); } /* * Shadow entries reflect the share of the working set that does not * fit into memory, so their number depends on the access pattern of * the workload. In most cases, they will refault or get reclaimed * along with the inode, but a (malicious) workload that streams * through files with a total size several times that of available * memory, while preventing the inodes from being reclaimed, can * create excessive amounts of shadow nodes. To keep a lid on this, * track shadow nodes and reclaim them when they grow way past the * point where they would still be useful. */ static struct list_lru shadow_nodes; void workingset_update_node(struct xa_node *node) { /* * Track non-empty nodes that contain only shadow entries; * unlink those that contain pages or are being freed. * * Avoid acquiring the list_lru lock when the nodes are * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */ if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add(&shadow_nodes, &node->private_list); __inc_lruvec_slab_state(node, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { list_lru_del(&shadow_nodes, &node->private_list); __dec_lruvec_slab_state(node, WORKINGSET_NODES); } } } static unsigned long count_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long max_nodes; unsigned long nodes; unsigned long pages; nodes = list_lru_shrink_count(&shadow_nodes, sc); /* * Approximate a reasonable limit for the nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. * * The size of the active list converges toward 100% of * overall page cache as memory grows, with only a tiny * inactive list. Assume the total cache size for that. * * Nodes might be sparsely populated, with only one shadow * entry in the extreme case. Obviously, we cannot keep one * node for every eligible shadow entry, so compromise on a * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. * * On 64-bit with 7 xa_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume * ~1.8% of available memory: * * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE */ #ifdef CONFIG_MEMCG if (sc->memcg) { struct lruvec *lruvec; int i; lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) pages += lruvec_page_state_local(lruvec, NR_LRU_BASE + i); pages += lruvec_page_state_local( lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT; pages += lruvec_page_state_local( lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT; } else #endif pages = node_present_pages(sc->nid); max_nodes = pages >> (XA_CHUNK_SHIFT - 3); if (!nodes) return SHRINK_EMPTY; if (nodes <= max_nodes) return 0; return nodes - max_nodes; } static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) __must_hold(lru_lock) { struct xa_node *node = container_of(item, struct xa_node, private_list); struct address_space *mapping; int ret; /* * Page cache insertions and deletions synchronously maintain * the shadow node LRU under the i_pages lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the lru_lock. */ mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { spin_unlock_irq(lru_lock); ret = LRU_RETRY; goto out; } list_lru_isolate(lru, item); __dec_lruvec_slab_state(node, WORKINGSET_NODES); spin_unlock(lru_lock); /* * The nodes should only contain one or more shadow entries, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; mapping->nrexceptional -= node->nr_values; xa_delete_node(node, workingset_update_node); __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM); out_invalid: xa_unlock_irq(&mapping->i_pages); ret = LRU_REMOVED_RETRY; out: cond_resched(); spin_lock_irq(lru_lock); return ret; } static unsigned long scan_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { /* list_lru lock nests inside the IRQ-safe i_pages lock */ return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate, NULL); } static struct shrinker workingset_shadow_shrinker = { .count_objects = count_shadow_nodes, .scan_objects = scan_shadow_nodes, .seeks = 0, /* ->count reports only fully expendable nodes */ .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, }; /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * i_pages lock. */ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { unsigned int timestamp_bits; unsigned int max_order; int ret; BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* * Calculate the eviction bucket size to cover the longest * actionable refault distance, which is currently half of * memory (totalram_pages/2). However, memory hotplug may add * some more pages at runtime, so keep working with up to * double the initial memory by using totalram_pages as-is. */ timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT; max_order = fls_long(totalram_pages() - 1); if (max_order > timestamp_bits) bucket_order = max_order - timestamp_bits; pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); ret = prealloc_shrinker(&workingset_shadow_shrinker); if (ret) goto err; ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, &workingset_shadow_shrinker); if (ret) goto err_list_lru; register_shrinker_prepared(&workingset_shadow_shrinker); return 0; err_list_lru: free_prealloced_shrinker(&workingset_shadow_shrinker); err: return ret; } module_init(workingset_init);
35 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_64_H #define _ASM_X86_UACCESS_64_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/lockdep.h> #include <linux/kasan-checks.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/page.h> /* * Copy To/From Userspace */ /* Handles exceptions in both to and from, but doesn't do access_ok */ __must_check unsigned long copy_user_enhanced_fast_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_unrolled(void *to, const void *from, unsigned len); static __always_inline __must_check unsigned long copy_user_generic(void *to, const void *from, unsigned len) { unsigned ret; /* * If CPU has ERMS feature, use copy_user_enhanced_fast_string. * Otherwise, if CPU has rep_good feature, use copy_user_generic_string. * Otherwise, use copy_user_generic_unrolled. */ alternative_call_2(copy_user_generic_unrolled, copy_user_generic_string, X86_FEATURE_REP_GOOD, copy_user_enhanced_fast_string, X86_FEATURE_ERMS, ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from), "=d" (len)), "1" (to), "2" (from), "3" (len) : "memory", "rcx", "r8", "r9", "r10", "r11"); return ret; } static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { return copy_user_generic(dst, (__force void *)src, size); } static __always_inline __must_check unsigned long raw_copy_to_user(void __user *dst, const void *src, unsigned long size) { return copy_user_generic((__force void *)dst, src, size); } static __always_inline __must_check unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size) { return copy_user_generic((__force void *)dst, (__force void *)src, size); } extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size); extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len); static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); return __copy_user_nocache(dst, src, size, 0); } static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } #endif /* _ASM_X86_UACCESS_64_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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset:8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * configfs_internal.h - Internal stuff for configfs * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. */ #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> #include <linux/list.h> #include <linux/spinlock.h> struct configfs_fragment { atomic_t frag_count; struct rw_semaphore frag_sem; bool frag_dead; }; void put_fragment(struct configfs_fragment *); struct configfs_fragment *get_fragment(struct configfs_fragment *); struct configfs_dirent { atomic_t s_count; int s_dependent_count; struct list_head s_sibling; struct list_head s_children; int s_links; void * s_element; int s_type; umode_t s_mode; struct dentry * s_dentry; struct iattr * s_iattr; #ifdef CONFIG_LOCKDEP int s_depth; #endif struct configfs_fragment *s_frag; }; #define CONFIGFS_ROOT 0x0001 #define CONFIGFS_DIR 0x0002 #define CONFIGFS_ITEM_ATTR 0x0004 #define CONFIGFS_ITEM_BIN_ATTR 0x0008 #define CONFIGFS_ITEM_LINK 0x0020 #define CONFIGFS_USET_DIR 0x0040 #define CONFIGFS_USET_DEFAULT 0x0080 #define CONFIGFS_USET_DROPPING 0x0100 #define CONFIGFS_USET_IN_MKDIR 0x0200 #define CONFIGFS_USET_CREATING 0x0400 #define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR) extern struct mutex configfs_symlink_mutex; extern spinlock_t configfs_dirent_lock; extern struct kmem_cache *configfs_dir_cachep; extern int configfs_is_root(struct config_item *item); extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *); extern struct inode *configfs_create(struct dentry *, umode_t mode); extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); extern int configfs_create_bin_file(struct config_item *, const struct configfs_bin_attribute *); extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *, void *, umode_t, int, struct configfs_fragment *); extern int configfs_dirent_is_ready(struct configfs_dirent *); extern void configfs_hash_and_remove(struct dentry * dir, const char * name); extern const unsigned char * configfs_get_name(struct configfs_dirent *sd); extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent); extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr); extern struct dentry *configfs_pin_fs(void); extern void configfs_release_fs(void); extern const struct file_operations configfs_dir_operations; extern const struct file_operations configfs_file_operations; extern const struct file_operations configfs_bin_file_operations; extern const struct inode_operations configfs_dir_inode_operations; extern const struct inode_operations configfs_root_inode_operations; extern const struct inode_operations configfs_symlink_inode_operations; extern const struct dentry_operations configfs_dentry_ops; extern int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname); extern int configfs_unlink(struct inode *dir, struct dentry *dentry); int configfs_create_link(struct configfs_dirent *target, struct dentry *parent, struct dentry *dentry, char *body); static inline struct config_item * to_item(struct dentry * dentry) { struct configfs_dirent * sd = dentry->d_fsdata; return ((struct config_item *) sd->s_element); } static inline struct configfs_attribute * to_attr(struct dentry * dentry) { struct configfs_dirent * sd = dentry->d_fsdata; return ((struct configfs_attribute *) sd->s_element); } static inline struct configfs_bin_attribute *to_bin_attr(struct dentry *dentry) { struct configfs_attribute *attr = to_attr(dentry); return container_of(attr, struct configfs_bin_attribute, cb_attr); } static inline struct config_item *configfs_get_config_item(struct dentry *dentry) { struct config_item * item = NULL; spin_lock(&dentry->d_lock); if (!d_unhashed(dentry)) { struct configfs_dirent * sd = dentry->d_fsdata; item = config_item_get(sd->s_element); } spin_unlock(&dentry->d_lock); return item; } static inline void release_configfs_dirent(struct configfs_dirent * sd) { if (!(sd->s_type & CONFIGFS_ROOT)) { kfree(sd->s_iattr); put_fragment(sd->s_frag); kmem_cache_free(configfs_dir_cachep, sd); } } static inline struct configfs_dirent * configfs_get(struct configfs_dirent * sd) { if (sd) { WARN_ON(!atomic_read(&sd->s_count)); atomic_inc(&sd->s_count); } return sd; } static inline void configfs_put(struct configfs_dirent * sd) { WARN_ON(!atomic_read(&sd->s_count)); if (atomic_dec_and_test(&sd->s_count)) release_configfs_dirent(sd); }
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 1 1 1 1 1 1 1 1 3 3 3 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/vfat/namei.c * * Written 1992,1993 by Werner Almesberger * * Windows95/Windows NT compatible extended MSDOS filesystem * by Gordon Chaffee Copyright (C) 1995. Send bug reports for the * VFAT filesystem to <chaffee@cs.berkeley.edu>. Specify * what file operation caused you trouble and if you can duplicate * the problem, send a script that demonstrates it. * * Short name translation 1999, 2001 by Wolfram Pienkoss <wp@bszh.de> * * Support Multibyte characters and cleanup by * OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> */ #include <linux/module.h> #include <linux/ctype.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/kernel.h> #include <linux/iversion.h> #include "fat.h" static inline unsigned long vfat_d_version(struct dentry *dentry) { return (unsigned long) dentry->d_fsdata; } static inline void vfat_d_version_set(struct dentry *dentry, unsigned long version) { dentry->d_fsdata = (void *) version; } /* * If new entry was created in the parent, it could create the 8.3 * alias (the shortname of logname). So, the parent may have the * negative-dentry which matches the created 8.3 alias. * * If it happened, the negative dentry isn't actually negative * anymore. So, drop it. */ static int vfat_revalidate_shortname(struct dentry *dentry) { int ret = 1; spin_lock(&dentry->d_lock); if (!inode_eq_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry))) ret = 0; spin_unlock(&dentry->d_lock); return ret; } static int vfat_revalidate(struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; /* This is not negative dentry. Always valid. */ if (d_really_is_positive(dentry)) return 1; return vfat_revalidate_shortname(dentry); } static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; /* * This is not negative dentry. Always valid. * * Note, rename() to existing directory entry will have ->d_inode, * and will use existing name which isn't specified name by user. * * We may be able to drop this positive dentry here. But dropping * positive dentry isn't good idea. So it's unsupported like * rename("filename", "FILENAME") for now. */ if (d_really_is_positive(dentry)) return 1; /* * This may be nfsd (or something), anyway, we can't see the * intent of this. So, since this can be for creation, drop it. */ if (!flags) return 0; /* * Drop the negative dentry, in order to make sure to use the * case sensitive name which is specified by user if this is * for creation. */ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; return vfat_revalidate_shortname(dentry); } /* returns the length of a struct qstr, ignoring trailing dots */ static unsigned int __vfat_striptail_len(unsigned int len, const char *name) { while (len && name[len - 1] == '.') len--; return len; } static unsigned int vfat_striptail_len(const struct qstr *qstr) { return __vfat_striptail_len(qstr->len, qstr->name); } /* * Compute the hash for the vfat name corresponding to the dentry. * Note: if the name is invalid, we leave the hash code unchanged so * that the existing dentry can be used. The vfat fs routines will * return ENOENT or EINVAL as appropriate. */ static int vfat_hash(const struct dentry *dentry, struct qstr *qstr) { qstr->hash = full_name_hash(dentry, qstr->name, vfat_striptail_len(qstr)); return 0; } /* * Compute the hash for the vfat name corresponding to the dentry. * Note: if the name is invalid, we leave the hash code unchanged so * that the existing dentry can be used. The vfat fs routines will * return ENOENT or EINVAL as appropriate. */ static int vfat_hashi(const struct dentry *dentry, struct qstr *qstr) { struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io; const unsigned char *name; unsigned int len; unsigned long hash; name = qstr->name; len = vfat_striptail_len(qstr); hash = init_name_hash(dentry); while (len--) hash = partial_name_hash(nls_tolower(t, *name++), hash); qstr->hash = end_name_hash(hash); return 0; } /* * Case insensitive compare of two vfat names. */ static int vfat_cmpi(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io; unsigned int alen, blen; /* A filename cannot end in '.' or we treat it like it has none */ alen = vfat_striptail_len(name); blen = __vfat_striptail_len(len, str); if (alen == blen) { if (nls_strnicmp(t, name->name, str, alen) == 0) return 0; } return 1; } /* * Case sensitive compare of two vfat names. */ static int vfat_cmp(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { unsigned int alen, blen; /* A filename cannot end in '.' or we treat it like it has none */ alen = vfat_striptail_len(name); blen = __vfat_striptail_len(len, str); if (alen == blen) { if (strncmp(name->name, str, alen) == 0) return 0; } return 1; } static const struct dentry_operations vfat_ci_dentry_ops = { .d_revalidate = vfat_revalidate_ci, .d_hash = vfat_hashi, .d_compare = vfat_cmpi, }; static const struct dentry_operations vfat_dentry_ops = { .d_revalidate = vfat_revalidate, .d_hash = vfat_hash, .d_compare = vfat_cmp, }; /* Characters that are undesirable in an MS-DOS file name */ static inline wchar_t vfat_bad_char(wchar_t w) { return (w < 0x0020) || (w == '*') || (w == '?') || (w == '<') || (w == '>') || (w == '|') || (w == '"') || (w == ':') || (w == '/') || (w == '\\'); } static inline wchar_t vfat_replace_char(wchar_t w) { return (w == '[') || (w == ']') || (w == ';') || (w == ',') || (w == '+') || (w == '='); } static wchar_t vfat_skip_char(wchar_t w) { return (w == '.') || (w == ' '); } static inline int vfat_is_used_badchars(const wchar_t *s, int len) { int i; for (i = 0; i < len; i++) if (vfat_bad_char(s[i])) return -EINVAL; if (s[i - 1] == ' ') /* last character cannot be space */ return -EINVAL; return 0; } static int vfat_find_form(struct inode *dir, unsigned char *name) { struct fat_slot_info sinfo; int err = fat_scan(dir, name, &sinfo); if (err) return -ENOENT; brelse(sinfo.bh); return 0; } /* * 1) Valid characters for the 8.3 format alias are any combination of * letters, uppercase alphabets, digits, any of the * following special characters: * $ % ' ` - @ { } ~ ! # ( ) & _ ^ * In this case Longfilename is not stored in disk. * * WinNT's Extension: * File name and extension name is contain uppercase/lowercase * only. And it is expressed by CASE_LOWER_BASE and CASE_LOWER_EXT. * * 2) File name is 8.3 format, but it contain the uppercase and * lowercase char, muliti bytes char, etc. In this case numtail is not * added, but Longfilename is stored. * * 3) When the one except for the above, or the following special * character are contained: * . [ ] ; , + = * numtail is added, and Longfilename must be stored in disk . */ struct shortname_info { unsigned char lower:1, upper:1, valid:1; }; #define INIT_SHORTNAME_INFO(x) do { \ (x)->lower = 1; \ (x)->upper = 1; \ (x)->valid = 1; \ } while (0) static inline int to_shortname_char(struct nls_table *nls, unsigned char *buf, int buf_size, wchar_t *src, struct shortname_info *info) { int len; if (vfat_skip_char(*src)) { info->valid = 0; return 0; } if (vfat_replace_char(*src)) { info->valid = 0; buf[0] = '_'; return 1; } len = nls->uni2char(*src, buf, buf_size); if (len <= 0) { info->valid = 0; buf[0] = '_'; len = 1; } else if (len == 1) { unsigned char prev = buf[0]; if (buf[0] >= 0x7F) { info->lower = 0; info->upper = 0; } buf[0] = nls_toupper(nls, buf[0]); if (isalpha(buf[0])) { if (buf[0] == prev) info->lower = 0; else info->upper = 0; } } else { info->lower = 0; info->upper = 0; } return len; } /* * Given a valid longname, create a unique shortname. Make sure the * shortname does not exist * Returns negative number on error, 0 for a normal * return, and 1 for valid shortname */ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls, wchar_t *uname, int ulen, unsigned char *name_res, unsigned char *lcase) { struct fat_mount_options *opts = &MSDOS_SB(dir->i_sb)->options; wchar_t *ip, *ext_start, *end, *name_start; unsigned char base[9], ext[4], buf[5], *p; unsigned char charbuf[NLS_MAX_CHARSET_SIZE]; int chl, chi; int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen; int is_shortname; struct shortname_info base_info, ext_info; is_shortname = 1; INIT_SHORTNAME_INFO(&base_info); INIT_SHORTNAME_INFO(&ext_info); /* Now, we need to create a shortname from the long name */ ext_start = end = &uname[ulen]; while (--ext_start >= uname) { if (*ext_start == 0x002E) { /* is `.' */ if (ext_start == end - 1) { sz = ulen; ext_start = NULL; } break; } } if (ext_start == uname - 1) { sz = ulen; ext_start = NULL; } else if (ext_start) { /* * Names which start with a dot could be just * an extension eg. "...test". In this case Win95 * uses the extension as the name and sets no extension. */ name_start = &uname[0]; while (name_start < ext_start) { if (!vfat_skip_char(*name_start)) break; name_start++; } if (name_start != ext_start) { sz = ext_start - uname; ext_start++; } else { sz = ulen; ext_start = NULL; } } numtail_baselen = 6; numtail2_baselen = 2; for (baselen = i = 0, p = base, ip = uname; i < sz; i++, ip++) { chl = to_shortname_char(nls, charbuf, sizeof(charbuf), ip, &base_info); if (chl == 0) continue; if (baselen < 2 && (baselen + chl) > 2) numtail2_baselen = baselen; if (baselen < 6 && (baselen + chl) > 6) numtail_baselen = baselen; for (chi = 0; chi < chl; chi++) { *p++ = charbuf[chi]; baselen++; if (baselen >= 8) break; } if (baselen >= 8) { if ((chi < chl - 1) || (ip + 1) - uname < sz) is_shortname = 0; break; } } if (baselen == 0) { return -EINVAL; } extlen = 0; if (ext_start) { for (p = ext, ip = ext_start; extlen < 3 && ip < end; ip++) { chl = to_shortname_char(nls, charbuf, sizeof(charbuf), ip, &ext_info); if (chl == 0) continue; if ((extlen + chl) > 3) { is_shortname = 0; break; } for (chi = 0; chi < chl; chi++) { *p++ = charbuf[chi]; extlen++; } if (extlen >= 3) { if (ip + 1 != end) is_shortname = 0; break; } } } ext[extlen] = '\0'; base[baselen] = '\0'; /* Yes, it can happen. ".\xe5" would do it. */ if (base[0] == DELETED_FLAG) base[0] = 0x05; /* OK, at this point we know that base is not longer than 8 symbols, * ext is not longer than 3, base is nonempty, both don't contain * any bad symbols (lowercase transformed to uppercase). */ memset(name_res, ' ', MSDOS_NAME); memcpy(name_res, base, baselen); memcpy(name_res + 8, ext, extlen); *lcase = 0; if (is_shortname && base_info.valid && ext_info.valid) { if (vfat_find_form(dir, name_res) == 0) return -EEXIST; if (opts->shortname & VFAT_SFN_CREATE_WIN95) { return (base_info.upper && ext_info.upper); } else if (opts->shortname & VFAT_SFN_CREATE_WINNT) { if ((base_info.upper || base_info.lower) && (ext_info.upper || ext_info.lower)) { if (!base_info.upper && base_info.lower) *lcase |= CASE_LOWER_BASE; if (!ext_info.upper && ext_info.lower) *lcase |= CASE_LOWER_EXT; return 1; } return 0; } else { BUG(); } } if (opts->numtail == 0) if (vfat_find_form(dir, name_res) < 0) return 0; /* * Try to find a unique extension. This used to * iterate through all possibilities sequentially, * but that gave extremely bad performance. Windows * only tries a few cases before using random * values for part of the base. */ if (baselen > 6) { baselen = numtail_baselen; name_res[7] = ' '; } name_res[baselen] = '~'; for (i = 1; i < 10; i++) { name_res[baselen + 1] = i + '0'; if (vfat_find_form(dir, name_res) < 0) return 0; } i = jiffies; sz = (jiffies >> 16) & 0x7; if (baselen > 2) { baselen = numtail2_baselen; name_res[7] = ' '; } name_res[baselen + 4] = '~'; name_res[baselen + 5] = '1' + sz; while (1) { snprintf(buf, sizeof(buf), "%04X", i & 0xffff); memcpy(&name_res[baselen], buf, 4); if (vfat_find_form(dir, name_res) < 0) break; i -= 11; } return 0; } /* Translate a string, including coded sequences into Unicode */ static int xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, int *longlen, int *outlen, int escape, int utf8, struct nls_table *nls) { const unsigned char *ip; unsigned char *op; int i, fill; int charlen; if (utf8) { *outlen = utf8s_to_utf16s(name, len, UTF16_HOST_ENDIAN, (wchar_t *) outname, FAT_LFN_LEN + 2); if (*outlen < 0) return *outlen; else if (*outlen > FAT_LFN_LEN) return -ENAMETOOLONG; op = &outname[*outlen * sizeof(wchar_t)]; } else { for (i = 0, ip = name, op = outname, *outlen = 0; i < len && *outlen < FAT_LFN_LEN; *outlen += 1) { if (escape && (*ip == ':')) { u8 uc[2]; if (i > len - 5) return -EINVAL; if (hex2bin(uc, ip + 1, 2) < 0) return -EINVAL; *(wchar_t *)op = uc[0] << 8 | uc[1]; op += 2; ip += 5; i += 5; } else { charlen = nls->char2uni(ip, len - i, (wchar_t *)op); if (charlen < 0) return -EINVAL; ip += charlen; i += charlen; op += 2; } } if (i < len) return -ENAMETOOLONG; } *longlen = *outlen; if (*outlen % 13) { *op++ = 0; *op++ = 0; *outlen += 1; if (*outlen % 13) { fill = 13 - (*outlen % 13); for (i = 0; i < fill; i++) { *op++ = 0xff; *op++ = 0xff; } *outlen += fill; } } return 0; } static int vfat_build_slots(struct inode *dir, const unsigned char *name, int len, int is_dir, int cluster, struct timespec64 *ts, struct msdos_dir_slot *slots, int *nr_slots) { struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb); struct fat_mount_options *opts = &sbi->options; struct msdos_dir_slot *ps; struct msdos_dir_entry *de; unsigned char cksum, lcase; unsigned char msdos_name[MSDOS_NAME]; wchar_t *uname; __le16 time, date; u8 time_cs; int err, ulen, usize, i; loff_t offset; *nr_slots = 0; uname = __getname(); if (!uname) return -ENOMEM; err = xlate_to_uni(name, len, (unsigned char *)uname, &ulen, &usize, opts->unicode_xlate, opts->utf8, sbi->nls_io); if (err) goto out_free; err = vfat_is_used_badchars(uname, ulen); if (err) goto out_free; err = vfat_create_shortname(dir, sbi->nls_disk, uname, ulen, msdos_name, &lcase); if (err < 0) goto out_free; else if (err == 1) { de = (struct msdos_dir_entry *)slots; err = 0; goto shortname; } /* build the entry of long file name */ cksum = fat_checksum(msdos_name); *nr_slots = usize / 13; for (ps = slots, i = *nr_slots; i > 0; i--, ps++) { ps->id = i; ps->attr = ATTR_EXT; ps->reserved = 0; ps->alias_checksum = cksum; ps->start = 0; offset = (i - 1) * 13; fatwchar_to16(ps->name0_4, uname + offset, 5); fatwchar_to16(ps->name5_10, uname + offset + 5, 6); fatwchar_to16(ps->name11_12, uname + offset + 11, 2); } slots[0].id |= 0x40; de = (struct msdos_dir_entry *)ps; shortname: /* build the entry of 8.3 alias name */ (*nr_slots)++; memcpy(de->name, msdos_name, MSDOS_NAME); de->attr = is_dir ? ATTR_DIR : ATTR_ARCH; de->lcase = lcase; fat_time_unix2fat(sbi, ts, &time, &date, &time_cs); de->time = de->ctime = time; de->date = de->cdate = de->adate = date; de->ctime_cs = time_cs; fat_set_start(de, cluster); de->size = 0; out_free: __putname(uname); return err; } static int vfat_add_entry(struct inode *dir, const struct qstr *qname, int is_dir, int cluster, struct timespec64 *ts, struct fat_slot_info *sinfo) { struct msdos_dir_slot *slots; unsigned int len; int err, nr_slots; len = vfat_striptail_len(qname); if (len == 0) return -ENOENT; slots = kmalloc_array(MSDOS_SLOTS, sizeof(*slots), GFP_NOFS); if (slots == NULL) return -ENOMEM; err = vfat_build_slots(dir, qname->name, len, is_dir, cluster, ts, slots, &nr_slots); if (err) goto cleanup; err = fat_add_entries(dir, slots, nr_slots, sinfo); if (err) goto cleanup; /* update timestamp */ fat_truncate_time(dir, ts, S_CTIME|S_MTIME); if (IS_DIRSYNC(dir)) (void)fat_sync_inode(dir); else mark_inode_dirty(dir); cleanup: kfree(slots); return err; } static int vfat_find(struct inode *dir, const struct qstr *qname, struct fat_slot_info *sinfo) { unsigned int len = vfat_striptail_len(qname); if (len == 0) return -ENOENT; return fat_search_long(dir, qname->name, len, sinfo); } static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; struct inode *inode; struct dentry *alias; int err; mutex_lock(&MSDOS_SB(sb)->s_lock); err = vfat_find(dir, &dentry->d_name, &sinfo); if (err) { if (err == -ENOENT) { inode = NULL; goto out; } goto error; } inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto error; } alias = d_find_alias(inode); /* * Checking "alias->d_parent == dentry->d_parent" to make sure * FS is not corrupted (especially double linked dir). */ if (alias && alias->d_parent == dentry->d_parent) { /* * This inode has non anonymous-DCACHE_DISCONNECTED * dentry. This means, the user did ->lookup() by an * another name (longname vs 8.3 alias of it) in past. * * Switch to new one for reason of locality if possible. */ if (!S_ISDIR(inode->i_mode)) d_move(alias, dentry); iput(inode); mutex_unlock(&MSDOS_SB(sb)->s_lock); return alias; } else dput(alias); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); if (!inode) vfat_d_version_set(dentry, inode_query_iversion(dir)); return d_splice_alias(inode, dentry); error: mutex_unlock(&MSDOS_SB(sb)->s_lock); return ERR_PTR(err); } static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; struct fat_slot_info sinfo; struct timespec64 ts; int err; mutex_lock(&MSDOS_SB(sb)->s_lock); ts = current_time(dir); err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo); if (err) goto out; inode_inc_iversion(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out; } inode_inc_iversion(inode); fat_truncate_time(inode, &ts, S_ATIME|S_CTIME|S_MTIME); /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); return err; } static int vfat_rmdir(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; int err; mutex_lock(&MSDOS_SB(sb)->s_lock); err = fat_dir_empty(inode); if (err) goto out; err = vfat_find(dir, &dentry->d_name, &sinfo); if (err) goto out; err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; drop_nlink(dir); clear_nlink(inode); fat_truncate_time(inode, NULL, S_ATIME|S_MTIME); fat_detach(inode); vfat_d_version_set(dentry, inode_query_iversion(dir)); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); return err; } static int vfat_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; int err; mutex_lock(&MSDOS_SB(sb)->s_lock); err = vfat_find(dir, &dentry->d_name, &sinfo); if (err) goto out; err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; clear_nlink(inode); fat_truncate_time(inode, NULL, S_ATIME|S_MTIME); fat_detach(inode); vfat_d_version_set(dentry, inode_query_iversion(dir)); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); return err; } static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; struct fat_slot_info sinfo; struct timespec64 ts; int err, cluster; mutex_lock(&MSDOS_SB(sb)->s_lock); ts = current_time(dir); cluster = fat_alloc_new_dir(dir, &ts); if (cluster < 0) { err = cluster; goto out; } err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &ts, &sinfo); if (err) goto out_free; inode_inc_iversion(dir); inc_nlink(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); if (IS_ERR(inode)) { err = PTR_ERR(inode); /* the directory was completed, just return a error */ goto out; } inode_inc_iversion(inode); set_nlink(inode, 2); fat_truncate_time(inode, &ts, S_ATIME|S_CTIME|S_MTIME); /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); mutex_unlock(&MSDOS_SB(sb)->s_lock); return 0; out_free: fat_free_clusters(dir, cluster); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); return err; } static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct buffer_head *dotdot_bh; struct msdos_dir_entry *dotdot_de; struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; struct timespec64 ts; loff_t new_i_pos; int err, is_dir, update_dotdot, corrupt = 0; struct super_block *sb = old_dir->i_sb; if (flags & ~RENAME_NOREPLACE) return -EINVAL; old_sinfo.bh = sinfo.bh = dotdot_bh = NULL; old_inode = d_inode(old_dentry); new_inode = d_inode(new_dentry); mutex_lock(&MSDOS_SB(sb)->s_lock); err = vfat_find(old_dir, &old_dentry->d_name, &old_sinfo); if (err) goto out; is_dir = S_ISDIR(old_inode->i_mode); update_dotdot = (is_dir && old_dir != new_dir); if (update_dotdot) { if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de)) { err = -EIO; goto out; } } ts = current_time(old_dir); if (new_inode) { if (is_dir) { err = fat_dir_empty(new_inode); if (err) goto out; } new_i_pos = MSDOS_I(new_inode)->i_pos; fat_detach(new_inode); } else { err = vfat_add_entry(new_dir, &new_dentry->d_name, is_dir, 0, &ts, &sinfo); if (err) goto out; new_i_pos = sinfo.i_pos; } inode_inc_iversion(new_dir); fat_detach(old_inode); fat_attach(old_inode, new_i_pos); if (IS_DIRSYNC(new_dir)) { err = fat_sync_inode(old_inode); if (err) goto error_inode; } else mark_inode_dirty(old_inode); if (update_dotdot) { fat_set_start(dotdot_de, MSDOS_I(new_dir)->i_logstart); mark_buffer_dirty_inode(dotdot_bh, old_inode); if (IS_DIRSYNC(new_dir)) { err = sync_dirty_buffer(dotdot_bh); if (err) goto error_dotdot; } drop_nlink(old_dir); if (!new_inode) inc_nlink(new_dir); } err = fat_remove_entries(old_dir, &old_sinfo); /* and releases bh */ old_sinfo.bh = NULL; if (err) goto error_dotdot; inode_inc_iversion(old_dir); fat_truncate_time(old_dir, &ts, S_CTIME|S_MTIME); if (IS_DIRSYNC(old_dir)) (void)fat_sync_inode(old_dir); else mark_inode_dirty(old_dir); if (new_inode) { drop_nlink(new_inode); if (is_dir) drop_nlink(new_inode); fat_truncate_time(new_inode, &ts, S_CTIME); } out: brelse(sinfo.bh); brelse(dotdot_bh); brelse(old_sinfo.bh); mutex_unlock(&MSDOS_SB(sb)->s_lock); return err; error_dotdot: /* data cluster is shared, serious corruption */ corrupt = 1; if (update_dotdot) { fat_set_start(dotdot_de, MSDOS_I(old_dir)->i_logstart); mark_buffer_dirty_inode(dotdot_bh, old_inode); corrupt |= sync_dirty_buffer(dotdot_bh); } error_inode: fat_detach(old_inode); fat_attach(old_inode, old_sinfo.i_pos); if (new_inode) { fat_attach(new_inode, new_i_pos); if (corrupt) corrupt |= fat_sync_inode(new_inode); } else { /* * If new entry was not sharing the data cluster, it * shouldn't be serious corruption. */ int err2 = fat_remove_entries(new_dir, &sinfo); if (corrupt) corrupt |= err2; sinfo.bh = NULL; } if (corrupt < 0) { fat_fs_error(new_dir->i_sb, "%s: Filesystem corrupted (i_pos %lld)", __func__, sinfo.i_pos); } goto out; } static const struct inode_operations vfat_dir_inode_operations = { .create = vfat_create, .lookup = vfat_lookup, .unlink = vfat_unlink, .mkdir = vfat_mkdir, .rmdir = vfat_rmdir, .rename = vfat_rename, .setattr = fat_setattr, .getattr = fat_getattr, .update_time = fat_update_time, }; static void setup(struct super_block *sb) { MSDOS_SB(sb)->dir_ops = &vfat_dir_inode_operations; if (MSDOS_SB(sb)->options.name_check != 's') sb->s_d_op = &vfat_ci_dentry_ops; else sb->s_d_op = &vfat_dentry_ops; } static int vfat_fill_super(struct super_block *sb, void *data, int silent) { return fat_fill_super(sb, data, silent, 1, setup); } static struct dentry *vfat_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_bdev(fs_type, flags, dev_name, data, vfat_fill_super); } static struct file_system_type vfat_fs_type = { .owner = THIS_MODULE, .name = "vfat", .mount = vfat_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("vfat"); static int __init init_vfat_fs(void) { return register_filesystem(&vfat_fs_type); } static void __exit exit_vfat_fs(void) { unregister_filesystem(&vfat_fs_type); } MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VFAT filesystem support"); MODULE_AUTHOR("Gordon Chaffee"); module_init(init_vfat_fs) module_exit(exit_vfat_fs)
16 33 22 34 35 41 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 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 /* SPDX-License-Identifier: GPL-2.0 */ /* * This header provides generic wrappers for memory access instrumentation that * the compiler cannot emit for: KASAN, KCSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> #include <linux/types.h> /** * instrument_read - instrument regular read access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_read(v, size); } /** * instrument_write - instrument regular write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_write(v, size); } /** * instrument_read_write - instrument regular read-write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_read_write(v, size); } /** * instrument_atomic_read - instrument atomic read access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_atomic_read(v, size); } /** * instrument_atomic_write - instrument atomic write access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_write(v, size); } /** * instrument_atomic_read_write - instrument atomic read-write access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_read_write(v, size); } /** * instrument_copy_to_user - instrument reads of copy_to_user * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); } /** * instrument_copy_from_user - instrument writes of copy_from_user * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } #endif /* _LINUX_INSTRUMENTED_H */
1 10 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 /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_i